Hui Zhang

AAAI Conference 2026 Conference Paper

Anomagic: Crossmodal Prompt-driven Zero-shot Anomaly Generation

• Yuxin Jiang
• Wei Luo
• Hui Zhang
• Qiyu Chen
• Haiming Yao
• Weiming Shen
• Yunkang Cao

We propose Anomagic, a zero-shot anomaly generation method that produces semantically coherent anomalies without requiring any exemplar anomalies. By unifying both visual and textual cues through a crossmodal prompt encoding scheme, Anomagic leverages rich contextual information to steer an inpainting‐based generation pipeline. A subsequent contrastive refinement strategy enforces precise alignment between synthesized anomalies and their masks, thereby bolstering downstream anomaly detection accuracy. To facilitate training, we introduce AnomVerse, a collection of 12,987 anomaly–mask–caption triplets assembled from 13 publicly available datasets, where captions are automatically generated by multimodal large language models using structured visual prompts and template‐based textual hints. Extensive experiments demonstrate that Anomagic trained on AnomVerse can synthesize more realistic and varied anomalies than prior methods, yielding superior improvements in downstream anomaly detection. Furthermore, Anomagic can generate anomalies for any normal‐category image using user‐defined prompts, establishing a versatile foundation model for anomaly generation.

JBHI Journal 2026 Journal Article

Federated Spatial Prior-Based Source-Free Domain Adaptation for White Matter Hyperintensities Segmentation

• Yu Cheng
• Yuxiang Dai
• Rencheng Zheng
• Beini Fei
• Hui Zhang
• Xinran Wu
• Boyu Zhang
• Haoran Peng

White matter hyperintensities (WMH) are important imaging biomarkers for cerebral small vessel disease, and their automatic segmentation across data with different distributions is crucial for assessing brain health and supporting diagnosis. However, cross-domain WMH segmentation remains challenging in privacy-sensitive and label-scarce clinical settings. Existing methods either relied on source domain data, violating privacy constraints, or lacked spatial guidance, which resulted in poor generalization, such as low sensitivity to small lesions. To address these challenges, we developed a source-free domain adaptation (SFDA) framework enhanced by federated spatial prior modeling. Our method used a dual-path pseudo-label generator that leveraged spatial priors to improve boundary accuracy and enhance the detection of small lesions. These priors were optimized via federated learning across multiple sites without sharing raw data, boosting model generalization while preserving privacy. The model was then fine-tuned using refined pseudo-labels. Experimental results demonstrated that our method consistently outperforms state-of-the-art UDA and SFDA methods, achieving 3–10% DSC improvement in most sites across 3 public and 7 private datasets. It also showed superior performance in small lesion detection and boundary delineation. Our method offered a robust, privacy-preserving solution for WMH segmentation and provided valuable support for early diagnosis and risk assessment of cerebrovascular diseases.

AAAI Conference 2026 Conference Paper

FedSDWC: Federated Synergistic Dual-Representation Weak Causal Learning for OOD

• Zhenyuan Huang
• Hui Zhang
• Wenzhong Tang
• Haijun Yang

Amid growing demands for data privacy and advances in computational infrastructure, federated learning (FL) has emerged as a prominent distributed learning paradigm. Nevertheless, differences in data distribution (such as covariate and semantic shifts) severely affect its reliability in real-world deployments. To address this issue, we propose FedSDWC, a causal inference method that integrates both invariant and variant features. FedSDWC infers causal semantic representations by modeling the weak causal influence between invariant and variant features, effectively overcoming the limitations of existing invariant learning methods in accurately capturing invariant features and directly constructing causal representations. This approach significantly enhances FL's ability to generalize and detect OOD data. Theoretically, we derive FedSDWC's generalization error bound under specific conditions and, for the first time, establish its relationship with client prior distributions. Moreover, extensive experiments conducted on multiple benchmark datasets validate the superior performance of FedSDWC in handling covariate and semantic shifts. For example, FedSDWC outperforms FedICON, the next best baseline, by an average of 3.04% on CIFAR-10 and 8.11% on CIFAR-100.

AAAI Conference 2026 Conference Paper

From Discriminative to Generative: A Diffusion-Based Paradigm for Multi-Agent Collaborative Perception

• Kexin Gong
• Puyi Yao
• Guiyang Luo
• Quan Yuan
• Tiange Fu
• Hui Zhang
• Jinglin Li

Collaborative perception leveraging intermediate feature fusion has emerged as a leading paradigm to significantly enhance the environmental perception capabilities of autonomous driving systems. However, existing methods typically rely on discriminative supervision guided by downstream tasks. This paradigm compels models to learn minimal, task-specific representations, which conflicts with the goal of cooperative perception to capture comprehensive information, thereby limiting generalization. To address this issue, we propose DiGS-CP, a novel two-stage generative supervised collaborative perception framework. Specifically, we introduce a diffusion-based generative task that conditions on fused object-level features to generate representations of object-level point clouds. The proposed generative supervision provides fine-grained, task-agnostic signals that encourages the fusion module to learn comprehensive representations beyond task-specific requirements. By preserving and integrating complementary information from collaborative agents, our approach overcomes the limitations of task-specific learning and enhances the generalizability of the learned features. Furthermore, our two-stage architecture requires agents to transmit only object-level features, significantly reducing communication overhead. Extensive experiments on three benchmark datasets demonstrate that DiGS-CP achieves state-of-the-art performance in 3D object detection, while maintaining low bandwidth requirements and exhibiting excellent generalization ability.

AAAI Conference 2026 Conference Paper

LLaVA-MS-PIT: Multi-Modal Schema-Guided Progressive Instruction Tuning for Multi-Modal Event Extraction

• Hui Zhang
• Po Hu
• Wei Emma Zhang

The proliferation of multi-modal data on the internet has intensified the need for structured event understanding across textual and visual modalities. However, existing multi-modal event extraction models suffer from three major limitations: the absence of explicit event schema guidance, coarse-grained multi-modal alignment strategies, and reliance on heterogeneous, misaligned multi-modal training datasets. To address these issues, we propose LLaVA-MS-PIT, a Multi-modal Schema-Guided Progressive Instruction Tuning Framework that explicitly injects structured multi-modal event schema knowledge into the model before event extraction. Specifically, we introduce the textual event schema to establish the model’s prior knowledge of event concepts and enhance its ability to reason about event structures, while the visual event schema is employed to bridge the representation gap between textual and visual modalities at the event level, enabling unified and semantically aligned event representations across modalities. Moreover, to alleviate data scarcity and modality misalignment inherent in current benchmarks, we construct imSitu-MEE, a high-quality multi-modal parallel dataset generated and annotated through schema-guided procedures. Extensive experiments demonstrate that LLaVA-MS-PIT achieves competitive performance on multi-modal event extraction benchmarks, underscoring the effectiveness and necessity of schema-guided progressive instruction tuning.

AAAI Conference 2026 System Paper

Magnol.AI Copilot: Multimodal LLMs for Conversational Insight Generation

• Hui Zhang
• Guangchen Ruan
• Hui Xiao

We present Magnol.AI Copilot, an extension of the Magnol.AI digital biomarker platform that integrates multimodal large language models (LLMs) to transform digital health technology (DHT) trial dashboards into conversational systems. Copilot augments the platform with a multi-agent orchestration layer and vision-enabled LLMs that interpret visualizations, tabular summaries, and textual metadata. The system enables natural language queries and automatic generation of contextual insights, allowing researchers to interact with wearable data through dialogue rather than static inspection. A case study with an actigraphy device demonstrates Copilot’s ability to identify nightly compliance gaps and provide contextual explanations, reducing cognitive load compared to manual dashboard review. This work presents a novel integration of IoMT infrastructure with multimodal LLMs, advancing digital biomarker research toward conversational and accessible DHT trial platforms.

AAAI Conference 2026 Conference Paper

Primary Visual Cortex Inspired Point Cloud Analysis Framework

• Jisheng Dang
• Delin Deng
• Bimei Wang
• Jingze Wu
• Hui Zhang
• Haijiang Li
• Jingmei Jiao
• Dengyue Pan

Despite significant advancements in point cloud analysis, reducing energy consumption and improving robustness remain understudied, largely due to the inherent limitations of Convolutional Neural Networks (CNNs). To address this, we take the cue from the primary visual cortex and propose a Dendritic-Connected Continuous-Coupled Neural Network (DC-CCNN), a novel Brain-Inspired Neural Network (BINN) architecture tailored for point cloud analysis. By leveraging the unique characteristics of point clouds, our design combines discrete and continuous encoding, replacing traditional Multilayer Perceptrons (MLPs) with more efficient and robust BINNs. Our approach substantially improves the performance of Brain-Inspired Neural Networks on point analysis tasks and maintaining performance comparable to state-of-the-art methods. Furthermore, DC-CCNN exhibits enhanced robustness against various point cloud deformations and corruptions. Our experimental results demonstrate that DC-CCNN achieves competitive performance on benchmark datasets, making it a promising alternative to traditional deep learning methods for point cloud analysis. With its high efficiency and robustness, DC-CCNN has the potential for widespread adoption in 3D computer vision, robotics, and autonomous systems.

AAAI Conference 2026 Conference Paper

Proxy Zero-Shot Hashing with Multimodal Fusion via Stable Diffusion

• Hui Zhang
• Weikang Gao
• Tao Yang
• Yuan Cao

With the rapid growth of visual content in open-world environments, zero-shot hashing image retrieval (ZSHIR) has emerged to tackle the challenge of recognizing novel classes using attribute-level and semantic information. However, existing methods often rely on shallow fusion of multi-source cues (e.g., attributes, labels, and visual features) through external supervision or feature concatenation, failing to capture the underlying semantic structure in a generative way. Particularly, current bridging strategies between modalities suffer from information fragmentation and weak alignment, hindering the model's ability to fully understand complex attribute-visual relations. Moreover, subtle semantic gaps or “semantic drift” between seen and unseen classes further degrade inter-class separability and the scalability of hashing models. To address these issues, we propose a novel framework called Proxy Zero-Shot Hashing with Multimodal Fusion via Stable Diffusion (PZSH), which integrates generative modeling and contrastive learning. PZSH leverages a pre-trained Stable Diffusion (SD) model to synthesize multimodal content, and uses dual BLIP encoders to enhance semantic alignment across modalities. We further design a proxy hashing loss to enforce discriminative binary representations. Extensive experiments on benchmark datasets show that PZSH achieves state-of-the-art performance with stronger generalization to unseen classes.

AAAI Conference 2026 Conference Paper

Remember Me: Bridging the Long-Range Gap in LVLMs with Three-Step Inference-Only Decay Resilience Strategies

• Peng Gao
• Yujian Lee
• Xiaofeng Zhang
• Zailong Chen
• Hui Zhang

Large Vision-Language Models (LVLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they still face critical challenges in modeling long-range dependencies under the usage of Rotary Positional Encoding (ROPE). Although it can facilitate precise modeling of token positions, it induces progressive attention decay as token distance increases, especially with progressive attention decay over distant token pairs, which severely impairs the model's ability to remember global context. To alleviate this issue, we propose inference-only Three-step Decay Resilience Strategies (T-DRS), comprising (1) Semantic-Driven DRS (SD-DRS), amplifying semantically meaningful but distant signals via content-aware residuals, (2) Distance-aware Control DRS (DC-DRS), which can purify attention by smoothly modulating weights based on positional distances, suppressing noise while preserving locality, and (3) re-Reinforce Distant DRS (reRD-DRS), consolidating the remaining informative remote dependencies to maintain global coherence. Together, the T-DRS recover suppressed long-range token pairs without harming local inductive biases. Extensive experiments on Vision Question Answering (VQA) benchmarks demonstrate that T-DRS can consistently improve performance in an inference-only manner.

JBHI Journal 2026 Journal Article

Restore-RWKV: Efficient and Effective Medical Image Restoration With RWKV

• Zhiwen Yang
• Jiayin Li
• Hui Zhang
• Dan Zhao
• Bingzheng Wei
• Yan Xu

Transformers have revolutionized medical image restoration, but the quadratic complexity still poses limitations for their application to high-resolution medical images. The recent advent of the Receptance Weighted Key Value (RWKV) model in the natural language processing field has attracted much attention due to its ability to process long sequences efficiently. To leverage its advanced design, we propose Restore-RWKV, the first RWKV-based model for medical image restoration. Since the original RWKV model is designed for 1D sequences, we make two necessary modifications for modeling spatial relations in 2D medical images. First, we present a recurrent WKV (Re-WKV) attention mechanism that captures global dependencies with linear computational complexity. Re-WKV incorporates bidirectional attention as basic for a global receptive field and recurrent attention to effectively model 2D dependencies from various scan directions. Second, we develop an omnidirectional token shift (Omni-Shift) layer that enhances local dependencies by shifting tokens from all directions and across a wide context range. These adaptations make the proposed Restore-RWKV an efficient and effective model for medical image restoration. Even a lightweight variant of Restore-RWKV, with only 1. 16 million parameters, achieves comparable or even superior results compared to existing state-of-the-art (SOTA) methods. Extensive experiments demonstrate that the resulting Restore-RWKV achieves SOTA performance across a range of medical image restoration tasks, including PET image synthesis, CT image denoising, MRI image super-resolution, and all-in-one medical image restoration.

AAAI Conference 2026 Conference Paper

Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial Defects

• Yuqi Cheng
• Yihan Sun
• Hui Zhang
• Weiming Shen
• Yunkang Cao

In industrial point cloud analysis, detecting subtle anomalies demands high-resolution spatial data, yet prevailing benchmarks emphasize low-resolution inputs. To address this disparity, we propose a scalable pipeline for generating realistic and subtle 3D anomalies. Employing this pipeline, we developed MiniShift, the inaugural high-resolution 3D anomaly detection dataset, encompassing 2,577 point clouds, each with 500,000 points and anomalies occupying less than 1% of the total. We further introduce Simple3D, an efficient framework integrating Multi-scale Neighborhood Descriptors (MSND) and Local Feature Spatial Aggregation (LFSA) to capture intricate geometric details with minimal computational overhead, achieving real-time inference exceeding 20 fps. Extensive evaluations on MiniShift and established benchmarks demonstrate that Simple3D surpasses state-of-the-art methods in both accuracy and speed, highlighting the pivotal role of high-resolution data and effective feature aggregation in advancing practical 3D anomaly detection.

AAAI Conference 2026 Conference Paper

VGGS: VGGT-guided Gaussian Splatting for Efficient and Faithful Sparse-View Surface Reconstruction

• Peng Xiang
• Liang Han
• Hui Zhang
• Yu-Shen Liu
• Zhizhong Han

Reconstructing a faithful geometric surface from sparse images remains a fundamental challenge in 3D computer vision. While recent methods have achieved remarkable progress, they still struggle to recover reliable geometry due to the lack of multi-view geometric cues, particularly in non-overlapping regions. To address this issue, we introduce VGGS, a Gaussian Splatting (GS) method that exploits multi-view geometric priors from VGGT for efficient and high-fidelity sparse-view surface reconstruction. Our primary contribution is an anchor-calibrated depth estimation scheme, which yields accurate depth maps. The insight is to align the VGGT depth prior to the underlying surface with a sparse set of multi-view consistent anchors, then infer depth for unreliable regions by relative depth estimation. Furthermore, to mitigate misalignment in complex scenes, we propose a relative depth consistency loss that penalizes the rendered depth if its relative depth relationship in local regions is inconsistent to the multi-view prior. Extensive experiments on widely-used benchmarks show that VGGS surpasses state-of-the-art methods in both accuracy and efficiency, delivering 4–7× faster optimization while reducing memory consumption compared to previous GS-based approaches.

AAAI Conference 2025 Conference Paper

AdaDiff: Adaptive Step Selection for Fast Diffusion Models

• Hui Zhang
• Zuxuan Wu
• Zhen Xing
• Jie Shao
• Yu-Gang Jiang

Diffusion models, as a type of generative model, have achieved impressive results in generating images and videos conditioned on textual conditions. However, the generation process of diffusion models involves denoising dozens of steps to produce photorealistic images/videos, which is computationally expensive. Unlike previous methods that design ``one-size-fits-all'' approaches for speed up, we argue denoising steps should be sample-specific conditioned on the richness of input texts. To this end, we introduce AdaDiff, a lightweight framework designed to learn instance-specific step usage policies, which are then used by the diffusion model for generation. AdaDiff is optimized using a policy gradient method to maximize a carefully designed reward function, balancing inference time and generation quality. We conduct experiments on three image generation and two video generation benchmarks and demonstrate that our approach achieves similar visual quality compared to the baseline using a fixed 50 denoising steps while reducing inference time by at least 33%, going as high as 40%. Furthermore, our method can be used on top of other acceleration methods to provide further speed benefits. Lastly, qualitative analysis shows that AdaDiff allocates more steps to more informative prompts and fewer steps to simpler prompts.

AAAI Conference 2025 Conference Paper

CoDTS: Enhancing Sparsely Supervised Collaborative Perception with a Dual Teacher-Student Framework

• Yushan Han
• Hui Zhang
• Honglei Zhang
• Jing Wang
• Yidong Li

Current collaborative perception methods often rely on fully annotated datasets, which can be expensive to obtain in practical situations. To reduce annotation costs, some works adopt sparsely supervised learning techniques and generate pseudo labels for the missing instances. However, these methods fail to achieve an optimal confidence threshold that harmonizes the quality and quantity of pseudo labels. To address this issue, we propose an end-to-end Collaborative perception Dual Teacher-Student framework (CoDTS), which employs adaptive complementary learning to produce both high-quality and high-quantity pseudo labels. Specifically, the Main Foreground Mining (MFM) module generates high-quality pseudo labels based on the prediction of the static teacher. Subsequently, the Supplement Foreground Mining (SFM) module ensures a balance between the quality and quantity of pseudo labels by adaptively identifying missing instances based on the prediction of the dynamic teacher. Additionally, the Neighbor Anchor Sampling (NAS) module is incorporated to enhance the representation of pseudo labels. To promote the adaptive complementary learning, we implement a staged training strategy that trains the student and dynamic teacher in a mutually beneficial manner. Extensive experiments demonstrate that the CoDTS effectively ensures an optimal balance of pseudo labels in both quality and quantity, establishing a new state-of-the-art in sparsely supervised collaborative perception.

NeurIPS Conference 2025 Conference Paper

CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modeling

• Beibu Li
• Qichao Shentu
• Yang Shu
• Hui Zhang
• Ming Li
• Ning Jin
• Bin Yang
• Chenjuan Guo

Time series anomaly detection plays a crucial role in a wide range of real-world applications. Given that time series data can exhibit different patterns at different sampling granularities, multi-scale modeling has proven beneficial for uncovering latent anomaly patterns that may not be apparent at a single scale. However, existing methods often model multi-scale information independently or rely on simple feature fusion strategies, neglecting the dynamic changes in cross-scale associations that occur during anomalies. Moreover, most approaches perform multi-scale modeling based on fixed sliding windows, which limits their ability to capture comprehensive contextual information. In this work, we propose CrossAD, a novel framework for time series Anomaly Detection that takes Cross-scale associations and Cross-window modeling into account. We propose a cross-scale reconstruction that reconstructs fine-grained series from coarser series, explicitly capturing cross-scale associations. Furthermore, we design a query library and incorporate global multi-scale context to overcome the limitations imposed by fixed window sizes. Extensive experiments conducted on seven real-world datasets using nine evaluation metrics validate the effectiveness of CrossAD, demonstrating state-of-the-art performance in anomaly detection.

EAAI Journal 2025 Journal Article

Explainable graph convolutional network based on catastrophe theory and its application to group activity recognition

• Junpeng Kang
• Jing Zhang
• Lin Chen
• Hui Zhang
• Li Zhuo

Graph convolutional networks (graph models for short) are crucial for understanding model decisions through mathematical white-box interpretation, which can radically improve the performance and credibility of downstream artificial intelligence applications. To address the limitations of existing interpretability of over-smoothing and over-squashing, we propose an explainable graph model based on nonlinear catastrophe theory and apply it to group activity recognition to validate the usefulness of interpretability. (1) We introduce catastrophe mathematical theory to explore the internal processes of graph models and construct the explainable dynamical equations of the graph convolutional network; (2) When graph node features lose uniqueness, leading to over-smoothing, which reduces the discriminative power of the graph model, we propose a mathematical method to predict over-smoothing; (3) In response to the over-squashing of the node feature values that is excessively compressed, we design a channel expansion unit to extend the transmission paths of graph nodes and alleviate the over-squashing in the graph structure. Finally, we apply our model to group activity recognition tasks to capture complex interactions within groups. We obtain the competitive results on five publicly available graph structure datasets (Actor, Chameleon, Texas, Cornell, Cora) and our self-built group activity dataset. Our model can effectively capture node and graph-level features with stronger generalization capabilities. For complex and diverse real-world group activity data, our model offers intuitive graph-level explanations for group activity analysis. Through the analysis of over-smoothing and over-squashing, our method extends new theoretical approaches in explainable artificial intelligence.

AAAI Conference 2025 Conference Paper

HGSFusion: Radar-Camera Fusion with Hybrid Generation and Synchronization for 3D Object Detection

• Zijian Gu
• Jianwei Ma
• Yan Huang
• Honghao Wei
• Zhanye Chen
• Hui Zhang
• Wei Hong

Millimeter-wave radar plays a vital role in 3D object detection for autonomous driving due to its all-weather and all-lighting-condition capabilities for perception. However, radar point clouds suffer from pronounced sparsity and unavoidable angle estimation errors. To address these limitations, incorporating a camera may partially help mitigate the shortcomings. Nevertheless, the direct fusion of radar and camera data can lead to negative or even opposite effects due to the lack of depth information in images and low-quality image features under adverse lighting conditions. Hence, in this paper, we present the radar-camera fusion network with Hybrid Generation and Synchronization (HGSFusion), designed to better fuse radar potentials and image features for 3D object detection. Specifically, we propose the Radar Hybrid Generation Module (RHGM), which fully considers the Direction-Of-Arrival (DOA) estimation errors in radar signal processing. This module generates denser radar points through different Probability Density Functions (PDFs) with the assistance of semantic information. Meanwhile, we introduce the Dual Sync Module (DSM), comprising spatial sync and modality sync, to enhance image features with radar positional information and facilitate the fusion of distinct characteristics in different modalities. Extensive experiments demonstrate the effectiveness of our approach, outperforming the state-of-the-art methods in the VoD and TJ4DRadSet datasets by 6.53% and 2.03% in RoI AP and BEV AP, respectively.

IROS Conference 2025 Conference Paper

Inverse-Free and Data-Driven Motion Tracking Control for Redundant Robot with Fuzzy Recurrent Neural Network

• Min Yang
• Siying Zhu
• Hui Zhang

Precise motion tracking control with unknown structural knowledge and noise disturbance for redundant robots remains a critical and unresolved challenge. This article proposes a novel data-driven fuzzy discrete recurrent neural network (D 2 -FDRNN) model to address two fundamental limitations of existing models: dependency on known kinematic knowledge and fixed sampling schemes. First, a Jacobian pseudo-inverse estimator is developed to reconstruct the manipulator’s necessary kinematic knowledge using input and output data, eliminating the need for explicit Jacobian inversion. Second, a fuzzy logic-based adaptive sampling strategy dynamically adjusts the step size to balance computational efficiency and tracking precision. In addition, a Kalman filter algorithm is applied to reduce the impact of noise. Rigorous proofs confirm the model’s exponential convergence and noise immunity. To validate the proposed D 2 -FDRNN model, simulations and physical experiments are carried out. The source code is available at https://github.com/YingluckZ/DD-FDRNN.git.

IROS Conference 2025 Conference Paper

Novel Data-Driven Repetitive Motion Control Scheme for Redundant Manipulators With Zeroing Neurodynamics

• Min Yang
• Kaixu Chen
• Hui Zhang

Repetitive motion control of redundant manipulators typically requires precise kinematic models to construct Jacobian matrices. However, model-based approaches are inherently limited when manipulator parameters are unavailable or only partially known. This paper introduces a novel data-driven discrete zeroing neurodynamics (DDZN) model for repetitive motion control. Specifically, a Jacobian matrix estimation method based on data-driven technology is proposed, which eliminates the need for prior models by leveraging historical input-output information. By integrating the Jacobian matrix estimation with a discrete zeroing neurodynamics (DZN) model, the approach enables simultaneous trajectory tracking and repeatable configuration recovery without relying on structural parameters. Theoretical analysis verifies the performance of DDZN model under noise environment. Furthermore, abundant experiment results validate its reliability and superior performance compared with various models.

IROS Conference 2025 Conference Paper

Parameterized Motion Planning for Aerial Manipulators in Contact with Unstructured Surfaces

• Zhixing Zhang
• Hang Zhong
• Chaoquan Lin
• Weizheng Wang
• Hean Hua
• Hui Zhang
• Yaonan Wang

Motion planning for continuous contact-based aerial manipulators on complex unstructured surfaces remains a substantial challenge due to the sophisticated topology of unstructured surfaces. While direct planning in the high-dimensional configuration space manifolds faces efficiency limitations, simplified planning in the parametric space sacrifices trajectory quality. Therefore, this paper proposes a sampling-based motion planning method, namely, parameter-configuration space fast marching tree (PCS-FMT*), which integrates both configuration and parameter space information. The proposed PCS-FMT* introduces a reparameterization strategy that compresses the planning space into a low-dimensional parameter manifold while preserving metric consistency with the original configuration space. Thus, PCS-FMT* can efficiently plan in the parameter space and optimize the motion trajectory. Simulations on challenging unstructured surfaces validate the effectiveness of PCS-FMT* for aerial manipulators in contact with unstructured surfaces.

NeurIPS Conference 2025 Conference Paper

Seg2Any: Open-set Segmentation-Mask-to-Image Generation with Precise Shape and Semantic Control

• Danfeng Li
• Hui Zhang
• Sheng Wang
• Jiacheng Li
• Zuxuan Wu

Despite recent advances in diffusion models, top-tier text-to-image (T2I) models still struggle to achieve precise spatial layout control, i. e. accurately generating entities with specified attributes and locations. Segmentation-mask-to-image (S2I) generation has emerged as a promising solution by incorporating pixel-level spatial guidance and regional text prompts. However, existing S2I methods fail to simultaneously ensure semantic consistency and shape consistency. To address these challenges, we propose Seg2Any, a novel S2I framework built upon advanced multimodal diffusion transformers ( e. g. FLUX). First, to achieve both semantic and shape consistency, we decouple segmentation mask conditions into regional semantic and high-frequency shape components. The regional semantic condition is introduced by a Semantic Alignment Attention Mask, ensuring that generated entities adhere to their assigned text prompts. The high-frequency shape condition, representing entity boundaries, is encoded as an Entity Contour Map and then introduced as an additional modality via multi-modal attention to guide image spatial structure. Second, to prevent attribute leakage across entities in multi-entity scenarios, we introduce an Attribute Isolation Attention Mask mechanism, which constrains each entity’s image tokens to attend exclusively to themselves during image self-attention. To support open-set S2I generation, we construct SACap-1M, a large-scale dataset containing 1 million images with 5. 9 million segmented entities and detailed regional captions, along with a SACap-Eval benchmark for comprehensive S2I evaluation. Extensive experiments demonstrate that Seg2Any achieves state-of-the-art performance on both open-set and closed-set S2I benchmarks, particularly in fine-grained spatial and attribute control of entities.

NeurIPS Conference 2025 Conference Paper

Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting

• Chenchen Tan
• Youyang Qu
• Xinghao Li
• Hui Zhang
• Shujie Cui
• Cunjian Chen
• Longxiang Gao

The increase in computing power and the necessity of AI-assisted decision-making boost the growing application of large language models (LLMs). Along with this, the potential retention of sensitive data of LLMs has spurred increasing research into machine unlearning. However, existing unlearning approaches face a critical dilemma: Aggressive unlearning compromises model utility, while conservative strategies preserve utility but risk hallucinated responses. This significantly limits LLMs' reliability in knowledge-intensive applications. To address this, we introduce a novel Attention-Shifting (AS) framework for selective unlearning. AS is driven by two design objectives: (1) context-preserving suppression that attenuates attention to fact-bearing tokens without disrupting LLMs' linguistic structure; and (2) hallucination-resistant response shaping that discourages fabricated completions when queried about unlearning content. AS realizes these objectives through two attention-level interventions, which are importance-aware suppression applied to the unlearning set to reduce reliance on memorized knowledge and attention-guided retention enhancement that reinforces attention toward semantically essential tokens in the retained dataset to mitigate unintended degradation. These two components are jointly optimized via a dual-loss objective, which forms a soft boundary that localizes unlearning while preserving unrelated knowledge under representation superposition. Experimental results show that AS improves performance preservation over the state-of-the-art unlearning methods, achieving up to 15\% higher accuracy on the ToFU benchmark and 10\% on the TDEC benchmark, while maintaining competitive hallucination-free unlearning effectiveness. Compared to existing methods, AS demonstrates a superior balance between unlearning effectiveness, generalization, and response reliability.

JBHI Journal 2024 Journal Article

Collaborative Transfer Network for Multi-Classification of Breast Cancer Histopathological Images

• Liangliang Liu
• Ying Wang
• Pei Zhang
• Hongbo Qiao
• Tong Sun
• Hui Zhang
• Xue Xu
• Hongcai Shang

The incidence of breast cancer is increasing rapidly around the world. Accurate classification of the breast cancer subtype from hematoxylin and eosin images is the key to improve the precision of treatment. However, the high consistency of disease subtypes and uneven distribution of cancer cells seriously affect the performance of multi-classification methods. Furthermore, it is difficult to apply existing classification methods to multiple datasets. In this article, we propose a collaborative transfer network (CTransNet) for multi-classification of breast cancer histopathological images. CTransNet consists of a transfer learning backbone branch, a residual collaborative branch, and a feature fusion module. The transfer learning branch adopts the pre-trained DenseNet structure to extract image features from ImageNet. The residual branch extracts target features from pathological images in a collaborative manner. The feature fusion strategy of optimizing these two branches is used to train and fine-tune CTransNet. Experiments show that CTransNet achieves 98. 29% classification accuracy on the public BreaKHis breast cancer dataset, exceeding the performance of state-of-the-art methods. Visual analysis is carried out under the guidance of oncologists. Based on the training parameters of the BreaKHis dataset, CTransNet achieves superior performance on other two public breast cancer datasets (breast-cancer-grade-ICT and ICIAR2018_BACH_Challenge), indicating that CTransNet has good generalization performance.

IJCAI Conference 2024 Conference Paper

Innovative Directional Encoding in Speech Processing: Leveraging Spherical Harmonics Injection for Multi-Channel Speech Enhancement

• Jiahui Pan
• Pengjie Shen
• Hui Zhang
• Xueliang Zhang

Multi-channel speech enhancement leverages multiple microphones to extract target speech signals amid background noise. Effectively utilizing directional cues is key for robust enhancement. While deep learning shows promise for multi-channel speech processing, most methods operate on short-time Fourier transform (STFT) coefficients directly. We propose using spherical harmonics transform (SHT) coefficients as auxiliary inputs to models. which concisely represent spatial distributions. SHT allows signals from varying numbers of microphones to be converted into coefficients of a consistent dimension. The proposed technique enables a single model to generalize to microphone arrays with varying configurations, rather than requiring a specialized model for each array layout. We present two architectures with SHT-based auxiliary inputs: parallel and serial. Specifically, the parallel model contains two encoders - one for STFT and another for SHT. By fusing both encoders' outputs in the decoder to estimate the enhanced STFT, it effectively incorporates spatial context. For the serial approach, we first apply SHT to the signals and then take STFT of the transformed signals as network inputs. Evaluations of the TIMIT dataset under fluctuating noise and reverberation demonstrate our model outperforms established benchmarks. Remarkably, these results are attained with reduced computations and parameters. Furthermore, experiments on the MS-SNSD dataset show the proposed method can enhance the generalization ability of networks. The source code is publicly accessible at https: //github. com/Pandade1997/SH_injection.

NeurIPS Conference 2024 Conference Paper

Is Your HD Map Constructor Reliable under Sensor Corruptions?

• Xiaoshuai Hao
• Mengchuan Wei
• Yifan Yang
• Haimei Zhao
• Hui Zhang
• Yi Zhou
• Qiang Wang
• Weiming Li

Driving systems often rely on high-definition (HD) maps for precise environmental information, which is crucial for planning and navigation. While current HD map constructors perform well under ideal conditions, their resilience to real-world challenges, \eg, adverse weather and sensor failures, is not well understood, raising safety concerns. This work introduces MapBench, the first comprehensive benchmark designed to evaluate the robustness of HD map construction methods against various sensor corruptions. Our benchmark encompasses a total of 29 types of corruptions that occur from cameras and LiDAR sensors. Extensive evaluations across 31 HD map constructors reveal significant performance degradation of existing methods under adverse weather conditions and sensor failures, underscoring critical safety concerns. We identify effective strategies for enhancing robustness, including innovative approaches that leverage multi-modal fusion, advanced data augmentation, and architectural techniques. These insights provide a pathway for developing more reliable HD map construction methods, which are essential for the advancement of autonomous driving technology. The benchmark toolkit and affiliated code and model checkpoints have been made publicly accessible.

YNIMG Journal 2024 Journal Article

Neural mechanisms distinguishing two types of cooperative problem-solving approaches: An fNIRS hyperscanning study

• Mingming Zhang
• Zijun Yin
• Xue Zhang
• Hui Zhang
• Mingjing Bao
• Bin Xuan

Collaborative cooperation (CC) and division of labor cooperation (DLC) are two prevalent forms of cooperative problem-solving approaches in daily life. Despite extensive research on the neural mechanisms underlying cooperative problem-solving approaches, a notable gap exists between the neural processes that support CC and DLC. The present study utilized a functional near-infrared spectroscopy (fNIRS) hyperscanning technique along with a classic cooperative tangram puzzle task to investigate the neural mechanisms engaged by both friends and stranger dyads during CC versus DLC. The key findings of this study were as follows: (1) Dyads exhibited superior behavioral performance in the DLC task than in the CC task. The CC task bolstered intra-brain functional connectivity and inter-brain synchrony (IBS) in regions linked to the mirror neuron system (MNS), spatial perception (SP) and cognitive control. (2) Friend dyads showed stronger IBS in brain regions associated with the MNS than stranger dyads. (3) Perspective-taking predicted not only dyads' behavioral performance in the CC task but also their IBS in brain regions associated with SP during the DLC task. Taken together, these findings elucidate the divergent behavioral performance and neural connection patterns between the two cooperative problem-solving approaches. This study provides novel insights into the various neurocognitive processes underlying flexible coordination strategies in real-world cooperative contexts.

AAAI Conference 2024 Conference Paper

UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding

• Chenpeng Du
• Yiwei Guo
• Feiyu Shen
• Zhijun Liu
• Zheng Liang
• Xie Chen
• Shuai Wang
• Hui Zhang

The utilization of discrete speech tokens, divided into semantic tokens and acoustic tokens, has been proven superior to traditional acoustic feature mel-spectrograms in terms of naturalness and robustness for text-to-speech (TTS) synthesis. Recent popular models, such as VALL-E and SPEAR-TTS, allow zero-shot speaker adaptation through auto-regressive (AR) continuation of acoustic tokens extracted from a short speech prompt. However, these AR models are restricted to generate speech only in a left-to-right direction, making them unsuitable for speech editing where both preceding and following contexts are provided. Furthermore, these models rely on acoustic tokens, which have audio quality limitations imposed by the performance of audio codec models. In this study, we propose a unified context-aware TTS framework called UniCATS, which is capable of both speech continuation and editing. UniCATS comprises two components, an acoustic model CTX-txt2vec and a vocoder CTX-vec2wav. CTX-txt2vec employs contextual VQ-diffusion to predict semantic tokens from the input text, enabling it to incorporate the semantic context and maintain seamless concatenation with the surrounding context. Following that, CTX-vec2wav utilizes contextual vocoding to convert these semantic tokens into waveforms, taking into consideration the acoustic context. Our experimental results demonstrate that CTX-vec2wav outperforms HifiGAN and AudioLM in terms of speech resynthesis from semantic tokens. Moreover, we show that UniCATS achieves state-of-the-art performance in both speech continuation and editing. Audio samples are available at https://cpdu.github.io/unicats.

JBHI Journal 2024 Journal Article

WDFF-Net: Weighted Dual-Branch Feature Fusion Network for Polyp Segmentation With Object-Aware Attention Mechanism

• Jie Cao
• Xin Wang
• Zhiwei Qu
• Li Zhuo
• Xiaoguang Li
• Hui Zhang
• Yang Yang
• Wei Wei

Colon polyps in colonoscopy images exhibit significant differences in color, size, shape, appearance, and location, posing significant challenges to accurate polyp segmentation. In this paper, a Weighted Dual-branch Feature Fusion Network is proposed for Polyp Segmentation, named WDFF-Net, which adopts HarDNet68 as the backbone network. First, a dual-branch feature fusion network architecture is constructed, which includes a shared feature extractor and two feature fusion branches, i. e. Progressive Feature Fusion (PFF) branch and Scale-aware Feature Fusion (SFF) branch. The branches fuse the deep features of multiple layers for different purposes and with different fusion ways. The PFF branch is to address the under-segmentation or over-segmentation problems of flat polyps with low-edge contrast by iteratively fusing the features from low, medium, and high layers. The SFF branch is to tackle the the problem of drastic variations in polyp size and shape, especially the missed segmentation problem for small polyps. These two branches are complementary and play different roles, in improving segmentation accuracy. Second, an Object-aware Attention Mechanism (OAM) is proposed to enhance the features of the target regions and suppress those of the background regions, to interfere with the segmentation performance. Third, a weighted dual-branch the segmentation loss function is specifically designed, which dynamically assigns the weight factors of the loss functions for two branches to optimize their collaborative training. Experimental results on five public colon polyp datasets demonstrate that, the proposed WDFF-Net can achieve a superior segmentation performance with lower model complexity and faster inference speed, while maintaining good generalization ability.

JBHI Journal 2023 Journal Article

A Segmentation Framework With Unsupervised Learning-Based Label Mapper for the Ventricular Target of Intracranial Germ Cell Tumor

• Xianyu Wang
• Shuai Liu
• Ne Yang
• Fang Chen
• Longfei Ma
• Guochen Ning
• Hui Zhang
• Xiaoguang Qiu

Intracranial germ cell tumors are rare tumors that mainly affect children and adolescents. Radiotherapy is the cornerstone of interdisciplinary treatment methods. Radiation of the whole ventricle system and the local tumor can reduce the complications in the late stage of radiotherapy while ensuring the curative effect. However, manually delineating the ventricular system is labor-intensive and time-consuming for physicians. The diverse ventricle shape and the hydrocephalus-induced ventricle dilation increase the difficulty of automatic segmentation algorithms. Therefore, this study proposed a fully automatic segmentation framework. Firstly, we designed a novel unsupervised learning-based label mapper, which is used to handle the ventricle shape variations and obtain the preliminary segmentation result. Then, to boost the segmentation performance of the framework, we improved the region growth algorithm and combined the fully connected conditional random field to optimize the preliminary results from both regional and voxel scales. In the case of only one set of annotated data is required, the average time cost is 153. 01 s, and the average target segmentation accuracy can reach 84. 69%. Furthermore, we verified the algorithm in practical clinical applications. The results demonstrate that our proposed method is beneficial for physicians to delineate radiotherapy targets, which is feasible and clinically practical, and may fill the gap of automatic delineation methods for the ventricular target of intracranial germ celltumors.

AAAI Conference 2023 Conference Paper

AlphaRoute: Large-Scale Coordinated Route Planning via Monte Carlo Tree Search

• Guiyang Luo
• Yantao Wang
• Hui Zhang
• Quan Yuan
• Jinglin Li

This paper proposes AlphaRoute, an AlphaGo inspired algorithm for coordinating large-scale routes, built upon graph attention reinforcement learning and Monte Carlo Tree Search (MCTS). We first partition the road network into regions and model large-scale coordinated route planning as a Markov game, where each partitioned region is treated as a player instead of each driver. Then, AlphaRoute applies a bilevel optimization framework, consisting of several region planners and a global planner, where the region planner coordinates the route choices for vehicles located in the region and generates several strategies, and the global planner evaluates the combination of strategies. AlphaRoute is built on graph attention network for evaluating each state and MCTS algorithm for dynamically visiting and simulating the future state for narrowing down the search space. AlphaRoute is capable of 1) bridging user fairness and system efficiency, 2) achieving higher search efficiency by alleviating the curse of dimensionality problems, and 3) making an effective and informed route planning by simulating over the future to capture traffic dynamics. Comprehensive experiments are conducted on two real-world road networks as compared with several baselines to evaluate the performance, and results show that AlphaRoute achieves the lowest travel time, and is efficient and effective for coordinating large-scale routes and alleviating the traffic congestion problem. The code will be publicly available.

YNIMG Journal 2023 Journal Article

Equivalent processing of facial expression and identity by macaque visual system and task-optimized neural network

• Hui Zhang
• Xuetong Ding
• Ning Liu
• Rachel Nolan
• Leslie G Ungerleider
• Shruti Japee

Both the primate visual system and artificial deep neural network (DNN) models show an extraordinary ability to simultaneously classify facial expression and identity. However, the neural computations underlying the two systems are unclear. Here, we developed a multi-task DNN model that optimally classified both monkey facial expressions and identities. By comparing the fMRI neural representations of the macaque visual cortex with the best-performing DNN model, we found that both systems: (1) share initial stages for processing low-level face features which segregate into separate branches at later stages for processing facial expression and identity respectively, and (2) gain more specificity for the processing of either facial expression or identity as one progresses along each branch towards higher stages. Correspondence analysis between the DNN and monkey visual areas revealed that the amygdala and anterior fundus face patch (AF) matched well with later layers of the DNN's facial expression branch, while the anterior medial face patch (AM) matched well with later layers of the DNN's facial identity branch. Our results highlight the anatomical and functional similarities between macaque visual system and DNN model, suggesting a common mechanism between the two systems.

EAAI Journal 2022 Journal Article

A surrogate-assisted Jaya algorithm based on optimal directional guidance and historical learning mechanism

• Fuqing Zhao
• Hui Zhang
• Ling Wang
• Ru Ma
• Tianpeng Xu
• Ningning Zhu
• Jonrinaldi

An improved Jaya algorithm named surrogate-assisted Jaya algorithm based on optimal directional guidance and historical learning mechanism (SDH-Jaya) is proposed in this study to address the continuous optimization problems. In the SDH-Jaya, a surrogate-assisted model combined with the polynomial model and radial basis model built by the individual with real fitness is introduced to decrease the expensive computational simulations and accelerate the convergence speed. Two co-evolutionary mechanisms, which are named assisted co-evolutionary mechanism and self-learning co-evolutionary mechanism, are proposed to optimize the surrogate model and evolutionary population. Search directions and steps of the SDH-Jaya are adjusted adaptively by the differential vector resulting from the best solution and worst solution in the candidates at each generation. The historical population stored in an archive is selected randomly to provide new search areas for improving the diversity of the population during the evolution process of the SDH-Jaya. The performance of SDH-Jaya is tested on CEC2017 benchmark problems. The experimental results reveal that the effectiveness of the SDH-Jaya algorithm outperforms the classical Jaya algorithm, its variants, and state-of-the-art algorithms in terms of the quality of solution and execution time.

YNIMG Journal 2022 Journal Article

Dissociation and hierarchy of human visual pathways for simultaneously coding facial identity and expression

• Xuetong Ding
• Hui Zhang

Humans have an extraordinary ability to recognize facial expression and identity from a single face simultaneously and effortlessly, however, the underlying neural computation is not well understood. Here, we optimized a multi-task deep neural network to classify facial expression and identity simultaneously. Under various optimization training strategies, the best-performing model consistently showed ‘share-separate’ organization. The two separate branches of the best-performing model also exhibited distinct abilities to categorize facial expression and identity, and these abilities increased along the facial expression or identity branches toward high layers. By comparing the representational similarities between the best-performing model and functional magnetic resonance imaging (fMRI) responses in the human visual cortex to the same face stimuli, the face-selective posterior superior temporal sulcus (pSTS) in the dorsal visual cortex was significantly correlated with layers in the expression branch of the model, and the anterior inferotemporal cortex (aIT) and anterior fusiform face area (aFFA) in the ventral visual cortex were significantly correlated with layers in the identity branch of the model. Besides, the aFFA and aIT better matched the high layers of the model, while the posterior FFA (pFFA) and occipital facial area (OFA) better matched the middle and early layers of the model, respectively. Overall, our study provides a task-optimization computational model to better understand the neural mechanism underlying face recognition, which suggest that similar to the best-performing model, the human visual system exhibits both dissociated and hierarchical neuroanatomical organization when simultaneously coding facial identity and expression.

JBHI Journal 2022 Journal Article

Low-Cost and Confidential ECG Acquisition Framework Using Compressed Sensing and Chaotic Systems for Wireless Body Area Network

• Hui Zhang
• Junxin Chen
• Leo Yu Zhang
• Chong Fu
• Raffaele Gravina
• Giancarlo Fortino
• Zhihan Lv

Recent years have witnessed an increasing popularity of wireless body area network (WBAN), with which continuous collection of physiological signals can be conveniently performed for healthcare monitoring. Energy consumption is a critical issue because it directly affects the duration of the equipped sensors. In this article, we propose a low-cost and confidential electrocardiogram (ECG) acquisition approach for WBAN. The compressed sensing (CS) is employed for low-cost signal acquisition, and its cryptographic features are exploited for promoting the framework's confidentiality. In particular, the RIPless measurement matrix is used to give CS the resistance against plaintext attack, while the first-order $\Sigma \Delta$ quantizer is employed to embed the cryptographic diffusion feature into the whole system. Two chaotic systems are employed for generating the required secret elements for the acquisition and encryption. Experiment results well demonstrate the signal reconstruction and security performance of the proposed framework.

JBHI Journal 2022 Journal Article

Multiple B-Value Model-Based Residual Network (MORN) for Accelerated High-Resolution Diffusion-Weighted Imaging

• Fanwen Wang
• Hui Zhang
• Fei Dai
• Weibo Chen
• Shuai Xu
• Zidong Yang
• Dinggang Shen
• Chengyan Wang

Single-Shot Echo Planar Imaging (SSEPI) based Diffusion Weighted Imaging (DWI) has shortcomings such as low resolution and severe distortions. In contrast, Multi-Shot EPI (MSEPI) provides optimal spatial resolution but increases scan time. This study proposed a Multiple b-value mOdel-based Residual Network (MORN) model to reconstruct multiple b-value high-resolution DWI from undersampled k-space data simultaneously. We incorporated Parallel Imaging (PI) into a residual U-net to reconstruct multiple b-value multi-coil data with the supervision of MUltiplexed Sensitivity-Encoding (MUSE) reconstructed Multi-Shot DWI (MSDWI). Moreover, asymmetric concatenations among different b-values and the combined loss to back propagate helped the feature transfer. After training and validation of the MORN in a dataset of 32 healthy cases, additional assessments were performed on 6 patients with different tumor types. The experimental results demonstrated that the MORN model outperformed conventional PI reconstruction (i. e. SENSE) and two state-of-the-art deep learning methods (SENSE-GAN and VSNet) in terms of PSNR (Peak Signal-to-Noise Ratio), SSIM (Structual SIMilarity) and apparent diffusion coefficient maps. In addition, using the pre-trained model under DWI, the MORN achieved consistent fractional anisotrophy and mean diffusivity reconstructed from multiple diffusion directions. Hence, the proposed method shows potential in clinical application according to the observations on tumor patients as well as images of multiple diffusion directions.

EAAI Journal 2022 Journal Article

Review on the COVID-19 pandemic prevention and control system based on AI

• Junfei Yi
• Hui Zhang
• JianXu Mao
• Yurong Chen
• Hang Zhong
• Yaonan Wang

As a new technology, artificial intelligence (AI) has recently received increasing attention from researchers and has been successfully applied to many domains. Currently, the outbreak of the COVID-19 pandemic has not only put people’s lives in jeopardy but has also interrupted social activities and stifled economic growth. Artificial intelligence, as the most cutting-edge science field, is critical in the fight against the pandemic. To respond scientifically to major emergencies like COVID-19, this article reviews the use of artificial intelligence in the combat against the pandemic from COVID-19 large data, intelligent devices and systems, and intelligent robots. This article’s primary contributions are in two aspects: (1) we summarized the applications of AI in the pandemic, including virus spreading prediction, patient diagnosis, vaccine development, excluding potential virus carriers, telemedicine service, economic recovery, material distribution, disinfection, and health care. (2) We concluded the faced challenges during the AI-based pandemic prevention process, including multidimensional data, sub-intelligent algorithms, and unsystematic, and discussed corresponding solutions, such as 5G, cloud computing, and unsupervised learning algorithms. This article systematically surveyed the applications and challenges of AI technology during the pandemic, which is of great significance to promote the development of AI technology and can serve as a new reference for future emergencies.

EAAI Journal 2022 Journal Article

Risk evaluation of information technology outsourcing project: An integrated approach considering risk interactions and hierarchies

• Wenyan Song
• Yue Zhu
• Shanshan Li
• Li Wang
• Hui Zhang

Effective risk evaluation is necessary to guarantee the successful completion of an IT outsourcing (ITO) process. However, previous methods of ITO risk assessment omit the interrelationships between the risk factors and ignore the vagueness of the evaluations. Additionally, most of the approaches fail to show the complex interactions among the risk factors with an intuitive and clear structure diagram. Thus, a new method for ITO risk assessment and visualization is developed in this paper. The proposed method integrates the advantages of improved decision-making and trial evaluation laboratories (DEMATEL) method, to incorporate the vagueness of the evaluations flexibly and evaluate the interactions and internal strengths of risk factors, and the merits of interpretative structural modeling (ISM), to clarify the risk factor structure. To illustrate the practicality and validity of this approach, an ITO case study of a mineral company is used in the implementation section to demonstrate the method.

YNIMG Journal 2021 Journal Article

Comparative analysis of signal models for microscopic fractional anisotropy estimation using q-space trajectory encoding

• Leevi Kerkelä
• Fabio Nery
• Ross Callaghan
• Fenglei Zhou
• Noemi G. Gyori
• Filip Szczepankiewicz
• Marco Palombo
• Geoff J.M. Parker

Microscopic diffusion anisotropy imaging using diffusion-weighted MRI and multidimensional diffusion encoding is a promising method for quantifying clinically and scientifically relevant microstructural properties of neural tissue. Several methods for estimating microscopic fractional anisotropy (µFA), a normalized measure of microscopic diffusion anisotropy, have been introduced but the differences between the methods have received little attention thus far. In this study, the accuracy and precision of µFA estimation using q-space trajectory encoding and different signal models were assessed using imaging experiments and simulations. Three healthy volunteers and a microfibre phantom were imaged with five non-zero b-values and gradient waveforms encoding linear and spherical b-tensors. Since the ground-truth µFA was unknown in the imaging experiments, Monte Carlo random walk simulations were performed using axon-mimicking fibres for which the ground truth was known. Furthermore, parameter bias due to time-dependent diffusion was quantified by repeating the simulations with tuned waveforms, which have similar power spectra, and with triple diffusion encoding, which, unlike q-space trajectory encoding, is not based on the assumption of time-independent diffusion. The truncated cumulant expansion of the powder-averaged signal, gamma-distributed diffusivities assumption, and q-space trajectory imaging, a generalization of the truncated cumulant expansion to individual signals, were used to estimate µFA. The gamma-distributed diffusivities assumption consistently resulted in greater µFA values than the second order cumulant expansion, 0.1 greater when averaged over the whole brain. In the simulations, the generalized cumulant expansion provided the most accurate estimates. Importantly, although time-dependent diffusion caused significant overestimation of µFA using all the studied methods, the simulations suggest that the resulting bias in µFA is less than 0.1 in human white matter.

YNIMG Journal 2021 Journal Article

Corrigendum to “SANDI: A compartment-based model for non-invasive apparent soma and neurite imaging by diffusion MRI” [Neuroimage 215 (2020), 116835]

• Marco Palombo
• Andrada Ianus
• Michele Guerreri
• Daniel Nunes
• Daniel C. Alexander
• Noam Shemesh
• Hui Zhang

YNIMG Journal 2021 Journal Article

Deep learning based multiplexed sensitivity-encoding (DL-MUSE) for high-resolution multi-shot DWI

• Hui Zhang
• Chengyan Wang
• Weibo Chen
• Fanwen Wang
• Zidong Yang
• Shuai Xu
• He Wang

PURPOSE: A phase correction method for high-resolution multi-shot (MSH) diffusion weighted imaging (DWI) is proposed. The efficacy and generalization capability of the method were validated on both healthy volunteers and patients. THEORY AND METHODS: Conventionally, inter-shot phase variations for MSH echo-planar imaging (EPI) DWI are corrected by model-based algorithms. However, many acquisition imperfections are hard to measure accurately for conventional model-based methods, making the phase estimation and artifacts suppression unreliable. We propose a deep learning multiplexed sensitivity-encoding (DL-MUSE) framework to improve the phase estimations based on convolutional neural network (CNN) reconstruction. Aliasing-free single-shot (SSH) DW images, which have been used routinely in clinical settings, were used for training before the aliasing correction of MSH-DWI images. A dual-channel U-net comprising multiple convolutional layers was used for the phase estimation of MSH-EPI. The network was trained on a dataset containing 30 healthy volunteers and tested on another dataset of 52 healthy subjects and 15 patients with lesions or tumors with different shot numbers (4, 6 and 8). To further validate the generalization capability of our network, we acquired a dataset with different numbers of shots, TEs, partial Fourier factors, resolutions, ETLs, FOVs, coil numbers, and image orientations from two sites. We also compared the reconstruction performance of our proposed method with that of the conventional MUSE and SSH-EPI qualitatively and quantitatively. RESULTS: Our results show that DL-MUSE is capable of correcting inter-shot phase errors with high and robust performance. Compared to conventional model-based MUSE, our method, by applying deep learning-based phase corrections, showed reduced distortion, noise level, and signal loss in high b-value DWIs. The improvements of image quality become more evident as the shot number increases from 4 to 8, especially in those central regions of the images, where g-factor artifacts are severe. Furthermore, the proposed method could provide the information about the orientation of the white matter with better consistency and achieve finer fibers delineation compared to the SSH-EPI method. Besides, the experiments on volunteers and patients from two different sites demonstrated the generalizability of our proposed method preliminarily. CONCLUSION: A deep learning-based reconstruction algorithm for MSH-EPI images, which helps improve image quality greatly, was proposed. Results from healthy volunteers and tumor patients demonstrated the feasibility and generalization performances of our method for high-resolution MSH-EPI DWI, which can be used for routine clinical applications as well as neuroimaging research.

YNIMG Journal 2021 Journal Article

Machine learning based white matter models with permeability: An experimental study in cuprizone treated in-vivo mouse model of axonal demyelination

• Ioana Hill
• Marco Palombo
• Mathieu Santin
• Francesca Branzoli
• Anne-Charlotte Philippe
• Demian Wassermann
• Marie-Stephane Aigrot
• Bruno Stankoff

The intra-axonal water exchange time (τi), a parameter associated with axonal permeability, could be an important biomarker for understanding and treating demyelinating pathologies such as Multiple Sclerosis. Diffusion-Weighted MRI (DW-MRI) is sensitive to changes in permeability; however, the parameter has so far remained elusive due to the lack of general biophysical models that incorporate it. Machine learning based computational models can potentially be used to estimate such parameters. Recently, for the first time, a theoretical framework using a random forest (RF) regressor suggests that this is a promising new approach for permeability estimation. In this study, we adopt such an approach and for the first time experimentally investigate it for demyelinating pathologies through direct comparison with histology. We construct a computational model using Monte Carlo simulations and an RF regressor in order to learn a mapping between features derived from DW-MRI signals and ground truth microstructure parameters. We test our model in simulations, and find strong correlations between the predicted and ground truth parameters (intra-axonal volume fraction f: R 2 =0. 99, τi: R 2 =0. 84, intrinsic diffusivity d: R2 =0. 99). We then apply the model in-vivo, on a controlled cuprizone (CPZ) mouse model of demyelination, comparing the results from two cohorts of mice, CPZ (N=8) and healthy age-matched wild-type (WT, N=8). We find that the RF model estimates sensible microstructure parameters for both groups, matching values found in literature. Furthermore, we perform histology for both groups using electron microscopy (EM), measuring the thickness of the myelin sheath as a surrogate for exchange time. Histology results show that our RF model estimates are very strongly correlated with the EM measurements (ρ = 0. 98 for f, ρ = 0. 82 for τi ). Finally, we find a statistically significant decrease in τi in all three regions of the corpus callosum (splenium/genu/body) of the CPZ cohort (<τi >=310ms/330ms/350ms) compared to the WT group (<τi>=370ms/370ms/380ms). This is in line with our expectations that τi is lower in regions where the myelin sheath is damaged, as axonal membranes become more permeable. Overall, these results demonstrate, for the first time experimentally and in vivo, that a computational model learned from simulations can reliably estimate microstructure parameters, including the axonal permeability.

YNIMG Journal 2021 Journal Article

On the generalizability of diffusion MRI signal representations across acquisition parameters, sequences and tissue types: Chronicles of the MEMENTO challenge

• Alberto de Luca
• Andrada Ianus
• Alexander Leemans
• Marco Palombo
• Noam Shemesh
• Hui Zhang
• Daniel C. Alexander
• Markus Nilsson

Diffusion MRI (dMRI) has become an invaluable tool to assess the microstructural organization of brain tissue. Depending on the specific acquisition settings, the dMRI signal encodes specific properties of the underlying diffusion process. In the last two decades, several signal representations have been proposed to fit the dMRI signal and decode such properties. Most methods, however, are tested and developed on a limited amount of data, and their applicability to other acquisition schemes remains unknown. With this work, we aimed to shed light on the generalizability of existing dMRI signal representations to different diffusion encoding parameters and brain tissue types. To this end, we organized a community challenge - named MEMENTO, making available the same datasets for fair comparisons across algorithms and techniques. We considered two state-of-the-art diffusion datasets, including single-diffusion-encoding (SDE) spin-echo data from a human brain with over 3820 unique diffusion weightings (the MASSIVE dataset), and double (oscillating) diffusion encoding data (DDE/DODE) of a mouse brain including over 2520 unique data points. A subset of the data sampled in 5 different voxels was openly distributed, and the challenge participants were asked to predict the remaining part of the data. After one year, eight participant teams submitted a total of 80 signal fits. For each submission, we evaluated the mean squared error, the variance of the prediction error and the Bayesian information criteria. The received submissions predicted either multi-shell SDE data (37%) or DODE data (22%), followed by cartesian SDE data (19%) and DDE (18%). Most submissions predicted the signals measured with SDE remarkably well, with the exception of low and very strong diffusion weightings. The prediction of DDE and DODE data seemed more challenging, likely because none of the submissions explicitly accounted for diffusion time and frequency. Next to the choice of the model, decisions on fit procedure and hyperparameters play a major role in the prediction performance, highlighting the importance of optimizing and reporting such choices. This work is a community effort to highlight strength and limitations of the field at representing dMRI acquired with trending encoding schemes, gaining insights into how different models generalize to different tissue types and fiber configurations over a large range of diffusion encodings.

AAAI Conference 2021 Conference Paper

Order Regularization on Ordinal Loss for Head Pose, Age and Gaze Estimation

• Tianchu Guo
• Hui Zhang
• ByungIn Yoo
• Yongchao Liu
• Youngjun Kwak
• Jae-Joon Han

Ordinal loss is widely used in solving regression problems with deep learning technologies. Its basic idea is to convert regression to classification while preserving the natural order. However, the order constraint is enforced only by ordinal label implicitly, leading to the real output values not strictly in order. It causes the network to learn separable feature rather than discriminative feature, and possibly overfit on training set. In this paper, we propose order regularization on ordinal loss, which makes the outputs in order by explicitly constraining the ordinal classifiers in order. The proposed method contains two parts, i. e. similar-weights constraint, which reduces the ineffective space between classifiers, and differential-bias constraint, which enforces the decision planes in order and enhances the discrimination power of the classifiers. Experimental results show that our proposed method boosts the performance of original ordinal loss on various regression problems such as head pose, age, and gaze estimation, with significant error reduction of around 5%. Furthermore, our method outperforms the state of the art on all these tasks, with the performance gain of 14. 4%, 2. 2% and 6. 5% on head pose, age and gaze estimation respectively.

YNIMG Journal 2021 Journal Article

Ventralis intermedius nucleus anatomical variability assessment by MRI structural connectivity

• Francisca Ferreira
• Harith Akram
• John Ashburner
• Ludvic Zrinzo
• Hui Zhang
• Christian Lambert

The ventralis intermedius nucleus (Vim) is centrally placed in the dentato-thalamo-cortical pathway (DTCp) and is a key surgical target in the treatment of severe medically refractory tremor. It is not visible on conventional MRI sequences; consequently, stereotactic targeting currently relies on atlas-based coordinates. This fails to capture individual anatomical variability, which may lead to poor long-term clinical efficacy. Probabilistic tractography, combined with known anatomical connectivity, enables localisation of thalamic nuclei at an individual subject level. There are, however, a number of confounds associated with this technique that may influence results. Here we focused on an established method, using probabilistic tractography to reconstruct the DTCp, to identify the connectivity-defined Vim (cd-Vim) in vivo. Using 100 healthy individuals from the Human Connectome Project, our aim was to quantify cd-Vim variability across this population, measure the discrepancy with atlas-defined Vim (ad-Vim), and assess the influence of potential methodological confounds. We found no significant effect of any of the confounds. The mean cd-Vim coordinate was located within 1.88 mm (left) and 2.12 mm (right) of the average midpoint and 3.98 mm (left) and 5.41 mm (right) from the ad-Vim coordinates. cd-Vim location was more variable on the right, which reflects hemispheric asymmetries in the probabilistic DTC reconstructed. The method was reproducible, with no significant cd-Vim location differences in a separate test-retest cohort. The superior cerebellar peduncle was identified as a potential source of artificial variance. This work demonstrates significant individual anatomical variability of the cd-Vim that atlas-based coordinate targeting fails to capture. This variability was not related to any methodological confound tested. Lateralisation of cerebellar functions, such as speech, may contribute to the observed asymmetry. Tractography-based methods seem sensitive to individual anatomical variability that is missed by conventional neurosurgical targeting; these findings may form the basis for translational tools to improve efficacy and reduce side-effects of thalamic surgery for tremor.

AAAI Conference 2020 Conference Paper

All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting

• Hao Wang
• Pu Lu
• Hui Zhang
• Mingkun Yang
• Xiang Bai
• Yongchao Xu
• Mengchao He
• Yongpan Wang

Recently, end-to-end text spotting that aims to detect and recognize text from cluttered images simultaneously has received particularly growing interest in computer vision. Different from the existing approaches that formulate text detection as bounding box extraction or instance segmentation, we localize a set of points on the boundary of each text instance. With the representation of such boundary points, we establish a simple yet effective scheme for end-to-end text spotting, which can read the text of arbitrary shapes. Experiments on three challenging datasets, including ICDAR2015, Total- Text and COCO-Text demonstrate that the proposed method consistently surpasses the state-of-the-art in both scene text detection and end-to-end text recognition tasks.

YNIMG Journal 2020 Journal Article

Anterior superior temporal sulcus is specialized for non-rigid facial motion in both monkeys and humans

• Hui Zhang
• Shruti Japee
• Andrea Stacy
• Molly Flessert
• Leslie G. Ungerleider

Facial motion plays a fundamental role in the recognition of facial expressions in primates, but the neural substrates underlying this special type of biological motion are not well understood. Here, we used fMRI to investigate the extent to which the specialization for facial motion is represented in the visual system and compared the neural mechanisms for the processing of non-rigid facial motion in macaque monkeys and humans. We defined the areas specialized for facial motion as those significantly more activated when subjects perceived the motion caused by dynamic faces (dynamic faces ​> ​static faces) than when they perceived the motion caused by dynamic non-face objects (dynamic objects ​> ​static objects). We found that, in monkeys, significant activations evoked by facial motion were in the fundus of anterior superior temporal sulcus (STS), which overlapped the anterior fundus face patch. In humans, facial motion activated three separate foci in the right STS: posterior, middle, and anterior STS, with the anterior STS location showing the most selectivity for facial motion compared with other facial motion areas. In both monkeys and humans, facial motion shows a gradient preference as one progresses anteriorly along the STS. Taken together, our results indicate that monkeys and humans share similar neural substrates within the anterior temporal lobe specialized for the processing of non-rigid facial motion.

YNIMG Journal 2020 Journal Article

ConFiG: Contextual Fibre Growth to generate realistic axonal packing for diffusion MRI simulation

• Ross Callaghan
• Daniel C. Alexander
• Marco Palombo
• Hui Zhang

This paper presents Contextual Fibre Growth (ConFiG), an approach to generate white matter numerical phantoms by mimicking natural fibre genesis. ConFiG grows fibres one-by-one, following simple rules motivated by real axonal guidance mechanisms. These simple rules enable ConFiG to generate phantoms with tuneable microstructural features by growing fibres while attempting to meet morphological targets such as user-specified density and orientation distribution. We compare ConFiG to the state-of-the-art approach based on packing fibres together by generating phantoms in a range of fibre configurations including crossing fibre bundles and orientation dispersion. Results demonstrate that ConFiG produces phantoms with up to 20% higher densities than the state-of-the-art, particularly in complex configurations with crossing fibres. We additionally show that the microstructural morphology of ConFiG phantoms is comparable to real tissue, producing diameter and orientation distributions close to electron microscopy estimates from real tissue as well as capturing complex fibre cross sections. Signals simulated from ConFiG phantoms match real diffusion MRI data well, showing that ConFiG phantoms can be used to generate realistic diffusion MRI data. This demonstrates the feasibility of ConFiG to generate realistic synthetic diffusion MRI data for developing and validating microstructure modelling approaches.

YNIMG Journal 2020 Journal Article

MTE-NODDI: Multi-TE NODDI for disentangling non-T2-weighted signal fractions from compartment-specific T2 relaxation times

• Ting Gong
• Qiqi Tong
• Hongjian He
• Yi Sun
• Jianhui Zhong
• Hui Zhang

Neurite orientation dispersion and density imaging (NODDI) has become a popular diffusion MRI technique for investigating microstructural alternations during brain development, maturation and aging in health and disease. However, the NODDI model of diffusion does not explicitly account for compartment-specific T2 relaxation and its model parameters are usually estimated from data acquired with a single echo time (TE). Thus, the NODDI-derived measures, such as the intra-neurite signal fraction, also known as the neurite density index, could be T2-weighted and TE-dependent. This may confound the interpretation of studies as one cannot disentangle differences in diffusion from those in T2 relaxation. To address this challenge, we propose a multi-TE NODDI (MTE-NODDI) technique, inspired by recent studies exploiting the synergy between diffusion and T2 relaxation. MTE-NODDI could give robust estimates of the non-T2-weighted signal fractions and compartment-specific T2 values, as demonstrated by both simulation and in vivo data experiments. Results showed that the estimated non-T2 weighted intra-neurite fraction and compartment-specific T2 values in white matter were consistent with previous studies. The T2-weighted intra-neurite fractions from the original NODDI were found to be overestimated compared to their non-T2-weighted estimates; the overestimation increases with TE, consistent with the reported intra-neurite T2 being larger than extra-neurite T2. Finally, the inclusion of the free water compartment reduces the estimation error in intra-neurite T2 in the presence of cerebrospinal fluid contamination. With the ability to disentangle non-T2-weighted signal fractions from compartment-specific T2 relaxation, MTE-NODDI could help improve the interpretability of future neuroimaging studies, especially those in brain development, maturation and aging.

YNIMG Journal 2020 Journal Article

SANDI: A compartment-based model for non-invasive apparent soma and neurite imaging by diffusion MRI

• Marco Palombo
• Andrada Ianus
• Michele Guerreri
• Daniel Nunes
• Daniel C. Alexander
• Noam Shemesh
• Hui Zhang

This work introduces a compartment-based model for apparent cell body (namely soma) and neurite density imaging (SANDI) using non-invasive diffusion-weighted MRI (DW-MRI). The existing conjecture in brain microstructure imaging through DW-MRI presents water diffusion in white (WM) and gray (GM) matter as restricted diffusion in neurites, modelled by infinite cylinders of null radius embedded in the hindered extra-neurite water. The extra-neurite pool in WM corresponds to water in the extra-axonal space, but in GM it combines water in the extra-cellular space with water in soma. While several studies showed that this microstructure model successfully describe DW-MRI data in WM and GM at b ​≤ ​3, 000 ​s/mm2 (or 3 ​ms/μm2), it has been also shown to fail in GM at high b values (b≫3, 000 ​s/mm2 or 3 ​ms/μm2). Here we hypothesise that the unmodelled soma compartment (i. e. cell body of any brain cell type: from neuroglia to neurons) may be responsible for this failure and propose SANDI as a new model of brain microstructure where soma of any brain cell type is explicitly included. We assess the effects of size and density of soma on the direction-averaged DW-MRI signal at high b values and the regime of validity of the model using numerical simulations and comparison with experimental data from mouse (bmax ​= ​40, 000 ​s/mm2, or 40 ​ms/μm2) and human (bmax ​= ​10, 000 ​s/mm2, or 10 ​ms/μm2) brain. We show that SANDI defines new contrasts representing complementary information on the brain cyto- and myelo-architecture. Indeed, we show maps from 25 healthy human subjects of MR soma and neurite signal fractions, that remarkably mirror contrasts of histological images of brain cyto- and myelo-architecture. Although still under validation, SANDI might provide new insight into tissue architecture by introducing a new set of biomarkers of potential great value for biomedical applications and pure neuroscience.

YNIMG Journal 2019 Journal Article

A generative model of realistic brain cells with application to numerical simulation of the diffusion-weighted MR signal

• Marco Palombo
• Daniel C. Alexander
• Hui Zhang

To date, numerical simulations of the brain tissue have been limited by their lack of realism and flexibility. The purpose of this work is to propose a controlled and flexible generative model for brain cell morphology and an efficient computational pipeline for the reliable and robust simulation of realistic cellular structures with application to numerical simulation of intra-cellular diffusion-weighted MR (DW-MR) signal features. Inspired by the advances in computational neuroscience for modelling brain cells, we propose a generative model that enables users to simulate molecular diffusion within realistic digital brain cells, such as neurons, in a completely controlled and flexible fashion. We validate our new approach by showing an excellent match between the morphology (no statistically different 3D Sholl metrics, P > 0. 05) and simulated intra-cellular DW-MR signal (mean relative difference < 2%) of the generated digital model of brain cells and those of digital reconstruction of real brain cells from available open-access databases. We demonstrate the versatility and potential of the framework by showing a select set of examples of relevance for the DW-MR community. The computational models introduced here are useful for synthesizing intra-cellular DW-MR signals, similar to those one might measure from brain metabolites DW-MRS experiments. They also provide the foundation for a more complete simulation system that will potentially include signals from extra-cellular compartments and exchange processes, necessary for synthesizing DW-MR signals of relevance for DW-MRI experiments.

YNIMG Journal 2019 Journal Article

Different patterns of cortical maturation before and after 38 weeks gestational age demonstrated by diffusion MRI in vivo

• Dafnis Batalle
• Jonathan O'Muircheartaigh
• Antonios Makropoulos
• Christopher J. Kelly
• Ralica Dimitrova
• Emer J. Hughes
• Joseph V. Hajnal
• Hui Zhang

Human cortical development during the third trimester is characterised by macro- and microstructural changes which are reflected in alterations in diffusion MRI (dMRI) measures, with significant decreases in cortical mean diffusivity (MD) and fractional anisotropy (FA). This has been interpreted as reflecting increased cellular density and dendritic arborisation. However, the fall in FA stops abruptly at 38 weeks post-menstrual age (PMA), and then tends to plateau, while MD continues to fall, suggesting a more complex picture and raising the hypothesis that after this age development is dominated by continuing increase in neural and organelle density rather than alterations in the geometry of dendritic trees. To test this, we used neurite orientation dispersion and density imaging (NODDI), acquiring multi-shell, high angular resolution dMRI and measures of cortical volume and mean curvature in 99 preterm infants scanned between 25 and 47 weeks PMA. We predicted that increased neurite and organelle density would be reflected in increases in neurite density index (NDI), while a relatively unchanging geometrical structure would be associated with constant orientation dispersion index (ODI). As dendritic arborisation is likely to be one of the drivers of gyrification, we also predicted that measures of cortical volume and curvature would correlate with ODI and show slower growth after 38 weeks. We observed a decrease of MD throughout the period, while cortical FA decreased from 25 to 38 weeks PMA and then increased. ODI increased up to 38 weeks and then plateaued, while NDI rose after 38 weeks. The evolution of ODI correlated with cortical volume and curvature. Regional analysis of cortical microstructure revealed a heterogenous pattern with increases in FA and NDI after 38 weeks confined to primary motor and sensory regions. These results support the interpretation that cortical development between 25 and 38 weeks PMA shows a predominant increase in dendritic arborisation and neurite growth, while between 38 and 47 weeks PMA it is dominated by increasing cellular and organelle density.

YNICL Journal 2019 Journal Article

Fixel-based analysis of the preterm brain: Disentangling bundle-specific white matter microstructural and macrostructural changes in relation to clinical risk factors

• Diliana Pecheva
• J-Donald Tournier
• Maximilian Pietsch
• Daan Christiaens
• Dafnis Batalle
• Daniel C. Alexander
• Joseph V. Hajnal
• A. David Edwards

Diffusion MRI (dMRI) studies using the tensor model have identified abnormal white matter development associated with perinatal risk factors in preterm infants studied at term equivalent age (TEA). However, this model is an oversimplification of the underlying neuroanatomy. Fixel-based analysis (FBA) is a novel quantitative framework, which identifies microstructural and macrostructural changes in individual fibre populations within voxels containing crossing fibres. The aim of this study was to apply FBA to investigate the relationship between fixel-based measures of apparent fibre density (FD), fibre bundle cross-section (FC), and fibre density and cross-section (FDC) and perinatal risk factors in preterm infants at TEA. We studied 50 infants (28 male) born at 24. 0–32. 9 (median 30. 4) weeks gestational age (GA) and imaged at 38. 6–47. 1 (median 42. 1) weeks postmenstrual age (PMA). dMRI data were acquired in non-collinear directions with b-value 2500 s/mm2 on a 3 Tesla system sited on the neonatal intensive care unit. FBA was performed to assess the relationship between FD, FC, FDC and PMA at scan, GA at birth, days on mechanical ventilation, days on total parenteral nutrition (TPN), birthweight z-score, and sex. FBA reveals fibre population-specific alterations in FD, FC and FDC associated with clinical risk factors. FD was positively correlated with GA at birth and was negatively correlated with number of days requiring ventilation. FC was positively correlated with GA at birth, birthweight z-scores and was higher in males. FC was negatively correlated with number of days on ventilation and days on TPN. FDC was positively correlated with GA at birth and birthweight z-scores, negatively correlated with days on ventilation and days on TPN and higher in males. We demonstrate that these relationships are fibre-specific even within regions of crossing fibres. These results show that aberrant white matter development involves both microstructural changes and macrostructural alterations.

YNIMG Journal 2018 Journal Article

A supervised learning approach for diffusion MRI quality control with minimal training data

• Mark S. Graham
• Ivana Drobnjak
• Hui Zhang

Quality control (QC) is a fundamental component of any study. Diffusion MRI has unique challenges that make manual QC particularly difficult, including a greater number of artefacts than other MR modalities and a greater volume of data. The gold standard is manual inspection of the data, but this process is time-consuming and subjective. Recently supervised learning approaches based on convolutional neural networks have been shown to be competitive with manual inspection. A drawback of these approaches is they still require a manually labelled dataset for training, which is itself time-consuming to produce and still introduces an element of subjectivity. In this work we demonstrate the need for manual labelling can be greatly reduced by training on simulated data, and using a small amount of labelled data for a final calibration step. We demonstrate its potential for the detection of severe movement artefacts, and compare performance to a classifier trained on manually-labelled real data.

YNIMG Journal 2018 Journal Article

Image processing and Quality Control for the first 10,000 brain imaging datasets from UK Biobank

• Fidel Alfaro-Almagro
• Mark Jenkinson
• Neal K. Bangerter
• Jesper L.R. Andersson
• Ludovica Griffanti
• Gwenaëlle Douaud
• Stamatios N. Sotiropoulos
• Saad Jbabdi

UK Biobank is a large-scale prospective epidemiological study with all data accessible to researchers worldwide. It is currently in the process of bringing back 100, 000 of the original participants for brain, heart and body MRI, carotid ultrasound and low-dose bone/fat x-ray. The brain imaging component covers 6 modalities (T1, T2 FLAIR, susceptibility weighted MRI, Resting fMRI, Task fMRI and Diffusion MRI). Raw and processed data from the first 10, 000 imaged subjects has recently been released for general research access. To help convert this data into useful summary information we have developed an automated processing and QC (Quality Control) pipeline that is available for use by other researchers. In this paper we describe the pipeline in detail, following a brief overview of UK Biobank brain imaging and the acquisition protocol. We also describe several quantitative investigations carried out as part of the development of both the imaging protocol and the processing pipeline.

YNIMG Journal 2018 Journal Article

Neurite imaging reveals microstructural variations in human cerebral cortical gray matter

• Hikaru Fukutomi
• Matthew F. Glasser
• Hui Zhang
• Joonas A. Autio
• Timothy S. Coalson
• Tomohisa Okada
• Kaori Togashi
• David C. Van Essen

We present distinct patterns of neurite distribution in the human cerebral cortex using diffusion magnetic resonance imaging (MRI). We analyzed both high-resolution structural (T1w and T2w images) and diffusion MRI data in 505 subjects from the Human Connectome Project. Neurite distributions were evaluated using the neurite orientation dispersion and density imaging (NODDI) model, optimized for gray matter, and mapped onto the cortical surface using a method weighted towards the cortical mid-thickness to reduce partial volume effects. The estimated neurite density was high in both somatosensory and motor areas, early visual and auditory areas, and middle temporal area (MT), showing a strikingly similar distribution to myelin maps estimated from the T1w/T2w ratio. The estimated neurite orientation dispersion was particularly high in early sensory areas, which are known for dense tangential fibers and are classified as granular cortex by classical anatomists. Spatial gradients of these cortical neurite properties revealed transitions that colocalize with some areal boundaries in a recent multi-modal parcellation of the human cerebral cortex, providing mutually supportive evidence. Our findings indicate that analyzing the cortical gray matter neurite morphology using diffusion MRI and NODDI provides valuable information regarding cortical microstructure that is related to but complementary to myeloarchitecture.

AAAI Conference 2018 Conference Paper

Residual Encoder Decoder Network and Adaptive Prior for Face Parsing

• Tianchu Guo
• Youngsung Kim
• Hui Zhang
• Deheng Qian
• ByungIn Yoo
• Jingtao Xu
• Dongqing Zou
• Jae-Joon Han

Face parsing assigns every pixel in a facial image with a semantic label, which could be applied in various applications including face expression recognition, facial beautification, affective computing and animation. While lots of progress have been made in this field, current state-of-the-art methods still fail to extract real effective feature and restore accurate score map, especially for those facial parts which have large variations of deformation and fairly similar appearance, e. g. mouth, eyes and thin eyebrows. In this paper, we propose a novel pixel-wise face parsing method called Residual Encoder Decoder Network (RED-Net), which combines a feature-rich encoder-decoder framework with adaptive prior mechanism. Our encoder-decoder framework extracts feature with ResNet and decodes the feature by elaborately fusing the residual architectures into deconvolution. This framework learns more effective feature comparing to that learnt by decoding with interpolation or classic deconvolution operations. To overcome the appearance ambiguity between facial parts, an adaptive prior mechanism is proposed in term of the decoder prediction confidence, allowing refining the final result. The experimental results on two public databases demonstrate that our method outperforms the state-of-thearts significantly, achieving improvements of F-measure from 0. 854 to 0. 905 on the Helen dataset, and pixel accuracy from 95. 12% to 97. 59% on the LFW dataset. In particular, convincing qualitative examples show that our method parses eye, eyebrow and lip regions more accurately.

YNIMG Journal 2018 Journal Article

Susceptibility-induced distortion that varies due to motion: Correction in diffusion MR without acquiring additional data

• Jesper L.R. Andersson
• Mark S. Graham
• Ivana Drobnjak
• Hui Zhang
• Jon Campbell

Because of their low bandwidth in the phase-encode (PE) direction, the susceptibility-induced off-resonance field causes distortions in echo planar imaging (EPI) images. It is therefore crucial to correct for susceptibility-induced distortions when performing diffusion studies using EPI. The susceptibility-induced field is caused by the object (head) disrupting the field and it is typically assumed that it remains constant within a framework defined by the object, (i. e. it follows the object as it moves in the scanner). However, this is only approximately true. When a non-spherical object rotates around an axis other than that parallel with the magnetic flux (the z-axis) it changes the way it disrupts the field, leading to different distortions. Hence, if using a single field to correct for distortions there will be residual distortions in the volumes where the object orientation is substantially different to that when the field was measured. In this paper we present a post-processing method for estimating the field as it changes with motion during the course of an experiment. It only requires a single measured field and knowledge of the orientation of the subject when that field was acquired. The volume-to-volume changes of the field as a consequence of subject movement are estimated directly from the diffusion data without the need for any additional or special acquisitions. It uses a generative model that predicts how each volume would look predicated on field change and inverts that model to yield an estimate of the field changes. It has been validated on both simulations and experimental data. The results show that we are able to track the field with high accuracy and that we are able to correct the data for the adverse effects of the changing field.

YNIMG Journal 2018 Journal Article

Whole brain g-ratio mapping using myelin water imaging (MWI) and neurite orientation dispersion and density imaging (NODDI)

• Woojin Jung
• Jingu Lee
• Hyeong-Geol Shin
• Yoonho Nam
• Hui Zhang
• Se-Hong Oh
• Jongho Lee

MR g-ratio, which measures the ratio of the aggregate volume of axons to that of fibers in a voxel, is a potential biomarker for white matter microstructures. In this study, a new approach for acquiring an in-vivo whole human brain g-ratio map is proposed. To estimate the g-ratio, myelin volume fraction and axonal volume fraction are acquired using multi-echo gradient echo myelin water imaging (GRE-MWI) and neurite orientation dispersion and density imaging (NODDI), respectively. In order to translate myelin water fraction measured in GRE-MWI into myelin volume fraction, a new scaling procedure is proposed and validated. This scaling approach utilizes geometric measures of myelin structure and, therefore, provides robustness over previous methods. The resulting g-ratio map reveals an expected range of g-ratios (0. 71–0. 85 in major fiber bundles) with a small inter-subject coefficient of variance (less than 2%). Additionally, a few fiber bundles (e. g. cortico-spinal tract and optic radiation) show different constituents of myelin volume fraction and axonal volume fraction, indicating potentials to utilize the measures for deciphering fiber tracking.

YNIMG Journal 2017 Journal Article

A tract-specific approach to assessing white matter in preterm infants

• Diliana Pecheva
• Paul Yushkevich
• Dafnis Batalle
• Emer Hughes
• Paul Aljabar
• Julia Wurie
• Joseph V. Hajnal
• A. David Edwards

Diffusion-weighted imaging (DWI) is becoming an increasingly important tool for studying brain development. DWI analyses relying on manually-drawn regions of interest and tractography using manually-placed waypoints are considered to provide the most accurate characterisation of the underlying brain structure. However, these methods are labour-intensive and become impractical for studies with large cohorts and numerous white matter (WM) tracts. Tract-specific analysis (TSA) is an alternative WM analysis method applicable to large-scale studies that offers potential benefits. TSA produces a skeleton representation of WM tracts and projects the group's diffusion data onto the skeleton for statistical analysis. In this work we evaluate the performance of TSA in analysing preterm infant data against results obtained from native space tractography and tract-based spatial statistics. We evaluate TSA's registration accuracy of WM tracts and assess the agreement between native space data and template space data projected onto WM skeletons, in 12 tracts across 48 preterm neonates. We show that TSA registration provides better WM tract alignment than a previous protocol optimised for neonatal spatial normalisation, and that TSA projects FA values that match well with values derived from native space tractography. We apply TSA for the first time to a preterm neonatal population to study the effects of age at scan on WM tracts around term equivalent age. We demonstrate the effects of age at scan on DTI metrics in commissural, projection and association fibres. We demonstrate the potential of TSA for WM analysis and its suitability for infant studies involving multiple tracts.

IJCAI Conference 2017 Conference Paper

DRLnet: Deep Difference Representation Learning Network and An Unsupervised Optimization Framework

• Puzhao Zhang
• Maoguo Gong
• Hui Zhang
• Jia Liu

Change detection and analysis (CDA) is an important research topic in the joint interpretation of spatial-temporal remote sensing images. The core of CDA is to effectively represent the difference and measure the difference degree between bi-temporal images. In this paper, we propose a novel difference representation learning network (DRLnet) and an effective optimization framework without any supervision. Difference measurement, difference representation learning and unsupervised clustering are combined as a single model, i. e. , DRLnet, which is driven to learn clustering-friendly and discriminative difference representations (DRs) for different types of changes. Further, DRLnet is extended into a recurrent learning framework to update and reuse limited training samples and prevent the semantic gaps caused by the saltation in the number of change types from over-clustering stage to the desired one. Experimental results identify the effectiveness of the proposed framework.

YNIMG Journal 2017 Journal Article

Early development of structural networks and the impact of prematurity on brain connectivity

• Dafnis Batalle
• Emer J. Hughes
• Hui Zhang
• J.-Donald Tournier
• Nora Tusor
• Paul Aljabar
• Luqman Wali
• Daniel C. Alexander

Preterm infants are at high risk of neurodevelopmental impairment, which may be due to altered development of brain connectivity. We aimed to (i) assess structural brain development from 25 to 45 weeks gestational age (GA) using graph theoretical approaches and (ii) test the hypothesis that preterm birth results in altered white matter network topology. Sixty-five infants underwent MRI between 25+3 and 45+6 weeks GA. Structural networks were constructed using constrained spherical deconvolution tractography and were weighted by measures of white matter microstructure (fractional anisotropy, neurite density and orientation dispersion index). We observed regional differences in brain maturation, with connections to and from deep grey matter showing most rapid developmental changes during this period. Intra-frontal, frontal to cingulate, frontal to caudate and inter-hemispheric connections matured more slowly. We demonstrated a core of key connections that was not affected by GA at birth. However, local connectivity involving thalamus, cerebellum, superior frontal lobe, cingulate gyrus and short range cortico-cortical connections was related to the degree of prematurity and contributed to altered global topology of the structural brain network. The relative preservation of core connections at the expense of local connections may support more effective use of impaired white matter reserve following preterm birth.

YNIMG Journal 2017 Journal Article

Image quality transfer and applications in diffusion MRI

• Daniel C. Alexander
• Darko Zikic
• Aurobrata Ghosh
• Ryutaro Tanno
• Viktor Wottschel
• Jiaying Zhang
• Enrico Kaden
• Tim B. Dyrby

This paper introduces a new computational imaging technique called image quality transfer (IQT). IQT uses machine learning to transfer the rich information available from one-off experimental medical imaging devices to the abundant but lower-quality data from routine acquisitions. The procedure uses matched pairs to learn mappings from low-quality to corresponding high-quality images. Once learned, these mappings then augment unseen low quality images, for example by enhancing image resolution or information content. Here, we demonstrate IQT using a simple patch-regression implementation and the uniquely rich diffusion MRI data set from the human connectome project (HCP). Results highlight potential benefits of IQT in both brain connectivity mapping and microstructure imaging. In brain connectivity mapping, IQT reveals, from standard data sets, thin connection pathways that tractography normally requires specialised data to reconstruct. In microstructure imaging, IQT shows potential in estimating, from standard “single-shell” data (one non-zero b-value), maps of microstructural parameters that normally require specialised multi-shell data. Further experiments show strong generalisability, highlighting IQT's benefits even when the training set does not directly represent the application domain. The concept extends naturally to many other imaging modalities and reconstruction problems.

YNIMG Journal 2017 Journal Article

Improved tractography using asymmetric fibre orientation distributions

• Matteo Bastiani
• Michiel Cottaar
• Krikor Dikranian
• Aurobrata Ghosh
• Hui Zhang
• Daniel C. Alexander
• Timothy E. Behrens
• Saad Jbabdi

Diffusion MRI allows us to make inferences on the structural organisation of the brain by mapping water diffusion to white matter microstructure. However, such a mapping is generally ill-defined; for instance, diffusion measurements are antipodally symmetric (diffusion along x and –x are equal), whereas the distribution of fibre orientations within a voxel is generally not symmetric. Therefore, different sub-voxel patterns such as crossing, fanning, or sharp bending, cannot be distinguished by fitting a voxel-wise model to the signal. However, asymmetric fibre patterns can potentially be distinguished once spatial information from neighbouring voxels is taken into account. We propose a neighbourhood-constrained spherical deconvolution approach that is capable of inferring asymmetric fibre orientation distributions (A-fods). Importantly, we further design and implement a tractography algorithm that utilises the estimated A-fods, since the commonly used streamline tractography paradigm cannot directly take advantage of the new information. We assess performance using ultra-high resolution histology data where we can compare true orientation distributions against sub-voxel fibre patterns estimated from down-sampled data. Finally, we explore the benefits of A-fods-based tractography using in vivo data by evaluating agreement of tractography predictions with connectivity estimates made using different in-vivo modalities. The proposed approach can reliably estimate complex fibre patterns such as sharp bending and fanning, which voxel-wise approaches cannot estimate. Moreover, histology-based and in-vivo results show that the new framework allows more accurate tractography and reconstruction of maps quantifying (symmetric and asymmetric) fibre complexity.

YNIMG Journal 2017 Journal Article

Towards a comprehensive framework for movement and distortion correction of diffusion MR images: Within volume movement

• Jesper L.R. Andersson
• Mark S. Graham
• Ivana Drobnjak
• Hui Zhang
• Nicola Filippini
• Matteo Bastiani

Most motion correction methods work by aligning a set of volumes together, or to a volume that represents a reference location. These are based on an implicit assumption that the subject remains motionless during the several seconds it takes to acquire all slices in a volume, and that any movement occurs in the brief moment between acquiring the last slice of one volume and the first slice of the next. This is clearly an approximation that can be more or less good depending on how long it takes to acquire one volume and in how rapidly the subject moves. In this paper we present a method that increases the temporal resolution of the motion correction by modelling movement as a piecewise continous function over time. This intra-volume movement correction is implemented within a previously presented framework that simultaneously estimates distortions, movement and movement-induced signal dropout. We validate the method on highly realistic simulated data containing all of these effects. It is demonstrated that we can estimate the true movement with high accuracy, and that scalar parameters derived from the data, such as fractional anisotropy, are estimated with greater fidelity when data has been corrected for intra-volume movement. Importantly, we also show that the difference in fidelity between data affected by different amounts of movement is much reduced when taking intra-volume movement into account. Additional validation was performed on data from a healthy volunteer scanned when lying still and when performing deliberate movements. We show an increased correspondence between the “still” and the “movement” data when the latter is corrected for intra-volume movement. Finally we demonstrate a big reduction in the telltale signs of intra-volume movement in data acquired on elderly subjects.

YNIMG Journal 2016 Journal Article

Bingham–NODDI: Mapping anisotropic orientation dispersion of neurites using diffusion MRI

• Maira Tariq
• Torben Schneider
• Daniel C. Alexander
• Claudia A. Gandini Wheeler-Kingshott
• Hui Zhang

This paper presents Bingham–NODDI, a clinically-feasible technique for estimating the anisotropic orientation dispersion of neurites. Direct quantification of neurite morphology on clinical scanners was recently realised by a diffusion MRI technique known as neurite orientation dispersion and density imaging (NODDI). However in its current form NODDI cannot estimate anisotropic orientation dispersion, which is widespread in the brain due to common fanning and bending of neurites. This work proposes Bingham–NODDI that extends the NODDI formalism to address this limitation. Bingham–NODDI characterises anisotropic orientation dispersion by utilising the Bingham distribution to model neurite orientation distribution. The new model estimates the extent of dispersion about the dominant orientation, separately along the primary and secondary dispersion orientations. These estimates are subsequently used to estimate the overall dispersion about the dominant orientation and the dispersion anisotropy. We systematically evaluate the ability of the new model to recover these key parameters of anisotropic orientation dispersion with standard NODDI protocol, both in silico and in vivo. The results demonstrate that the parameters of the proposed model can be estimated without additional acquisition requirements over the standard NODDI protocol. Thus anisotropic dispersion can be determined and has the potential to be used as a marker for normal brain development and ageing or in pathology. We additionally find that the original NODDI model is robust to the effects of anisotropic orientation dispersion, when the quantification of anisotropic dispersion is not of interest.

YNIMG Journal 2016 Journal Article

Face-selective regions differ in their ability to classify facial expressions

• Hui Zhang
• Shruti Japee
• Rachel Nolan
• Carlton Chu
• Ning Liu
• Leslie G. Ungerleider

Recognition of facial expressions is crucial for effective social interactions. Yet, the extent to which the various face-selective regions in the human brain classify different facial expressions remains unclear. We used functional magnetic resonance imaging (fMRI) and support vector machine pattern classification analysis to determine how well face-selective brain regions are able to decode different categories of facial expression. Subjects participated in a slow event-related fMRI experiment in which they were shown 32 face pictures, portraying four different expressions: neutral, fearful, angry, and happy and belonging to eight different identities. Our results showed that only the amygdala and the posterior superior temporal sulcus (STS) were able to accurately discriminate between these expressions, albeit in different ways: the amygdala discriminated fearful faces from non-fearful faces, whereas STS discriminated neutral from emotional (fearful, angry and happy) faces. In contrast to these findings on the classification of emotional expression, only the fusiform face area (FFA) and anterior inferior temporal cortex (aIT) could discriminate among the various facial identities. Further, the amygdala and STS were better than FFA and aIT at classifying expression, while FFA and aIT were better than the amygdala and STS at classifying identity. Taken together, our findings indicate that the decoding of facial emotion and facial identity occurs in different neural substrates: the amygdala and STS for the former and FFA and aIT for the latter.

YNIMG Journal 2016 Journal Article

Realistic simulation of artefacts in diffusion MRI for validating post-processing correction techniques

• Mark S. Graham
• Ivana Drobnjak
• Hui Zhang

In this paper we demonstrate a simulation framework that enables the direct and quantitative comparison of post-processing methods for diffusion weighted magnetic resonance (DW-MR) images. DW-MR datasets are employed in a range of techniques that enable estimates of local microstructure and global connectivity in the brain. These techniques require full alignment of images across the dataset, but this is rarely the case. Artefacts such as eddy-current (EC) distortion and motion lead to misalignment between images, which compromise the quality of the microstructural measures obtained from them. Numerous methods and software packages exist to correct these artefacts, some of which have become de-facto standards, but none have been subject to rigorous validation. In the literature, improved alignment is assessed using either qualitative visual measures or quantitative surrogate metrics. Here we introduce a simulation framework that allows for the direct, quantitative assessment of techniques, enabling objective comparisons of existing and future methods. DW-MR datasets are generated using a process that is based on the physics of MRI acquisition, which allows for the salient features of the images and their artefacts to be reproduced. We apply this framework in three ways. Firstly we assess the most commonly used method for artefact correction, FSL's eddy_correct, and compare it to a recently proposed alternative, eddy. We demonstrate quantitatively that using eddy_correct leads to significant errors in the corrected data, whilst eddy is able to provide much improved correction. Secondly we investigate the datasets required to achieve good correction with eddy, by looking at the minimum number of directions required and comparing the recommended full-sphere acquisitions to equivalent half-sphere protocols. Finally, we investigate the impact of correction quality by examining the fits from microstructure models to real and simulated data.

YNIMG Journal 2015 Journal Article

Accelerated Microstructure Imaging via Convex Optimization (AMICO) from diffusion MRI data

• Alessandro Daducci
• Erick J. Canales-Rodríguez
• Hui Zhang
• Tim B. Dyrby
• Daniel C. Alexander
• Jean-Philippe Thiran

Microstructure imaging from diffusion magnetic resonance (MR) data represents an invaluable tool to study non-invasively the morphology of tissues and to provide a biological insight into their microstructural organization. In recent years, a variety of biophysical models have been proposed to associate particular patterns observed in the measured signal with specific microstructural properties of the neuronal tissue, such as axon diameter and fiber density. Despite very appealing results showing that the estimated microstructure indices agree very well with histological examinations, existing techniques require computationally very expensive non-linear procedures to fit the models to the data which, in practice, demand the use of powerful computer clusters for large-scale applications. In this work, we present a general framework for Accelerated Microstructure Imaging via Convex Optimization (AMICO) and show how to re-formulate this class of techniques as convenient linear systems which, then, can be efficiently solved using very fast algorithms. We demonstrate this linearization of the fitting problem for two specific models, i. e. ActiveAx and NODDI, providing a very attractive alternative for parameter estimation in those techniques; however, the AMICO framework is general and flexible enough to work also for the wider space of microstructure imaging methods. Results demonstrate that AMICO represents an effective means to accelerate the fit of existing techniques drastically (up to four orders of magnitude faster) while preserving accuracy and precision in the estimated model parameters (correlation above 0. 9). We believe that the availability of such ultrafast algorithms will help to accelerate the spread of microstructure imaging to larger cohorts of patients and to study a wider spectrum of neurological disorders.

YNIMG Journal 2015 Journal Article

Neurite orientation dispersion and density imaging of the healthy cervical spinal cord in vivo

• Francesco Grussu
• Torben Schneider
• Hui Zhang
• Daniel C. Alexander
• Claudia A.M. Wheeler–Kingshott

Here we present the application of neurite orientation dispersion and density imaging (NODDI) to the healthy spinal cord in vivo. NODDI provides maps such as the intra-neurite tissue volume fraction (v in ), the orientation dispersion index (ODI) and the isotropic volume fraction (v iso ), and here we investigate their potential for spinal cord imaging. We scanned five healthy volunteers, four of whom twice, on a 3T MRI system with a ZOOM-EPI sequence. In accordance to the published NODDI protocol, multiple b-shells were acquired at cervical level and both NODDI and diffusion tensor imaging (DTI) metrics were obtained and analysed to: i) characterise differences in grey and white matter (GM/WM); ii) assess the scan–rescan reproducibility of NODDI; iii) investigate the relationship between NODDI and DTI; and iv) compare the quality of fit of NODDI and DTI. Our results demonstrated that: i) anatomical features can be identified in NODDI maps, such as clear contrast between GM and WM in ODI; ii) the variabilities of v in and ODI are comparable to that of DTI and are driven by biological differences between subjects for ODI, have similar contribution from measurement errors and biological variation for v in, whereas v iso shows higher variability, driven by measurement errors; iii) NODDI identifies potential sources contributing to DTI indices, as in the brain; and iv) NODDI outperforms DTI in terms of quality of fit. In conclusion, this work shows that NODDI is a useful model for in vivo diffusion MRI of the spinal cord, providing metrics closely related to tissue microstructure, in line with findings in the brain.

YNIMG Journal 2015 Journal Article

White matter compartment models for in vivo diffusion MRI at 300 mT/m

• Uran Ferizi
• Torben Schneider
• Thomas Witzel
• Lawrence L. Wald
• Hui Zhang
• Claudia A.M. Wheeler-Kingshott
• Daniel C. Alexander

This paper compares a range of compartment models for diffusion MRI data on in vivo human acquisitions from a standard 60mT/m system (Philips 3T Achieva) and a unique 300mT/m system (Siemens Connectom). The key aim is to determine whether both systems support broadly the same models or whether the Connectom higher gradient system supports significantly more complex models. A single volunteer underwent 8h of acquisition on each system to provide uniquely wide and dense sampling of the available space of pulsed-gradient spin-echo (PGSE) measurements. We select a set of promising models from the wide set of possible three-compartment models for in vivo white matter (WM) that previous work and preliminary experiments suggest as strong candidates, but extend them to fit for compartmental T2 and diffusivity. We focus on the corpus callosum where the WM fibre architecture is simplest and compare their ability to explain the measured data, using Akaike's information criterion (AIC), and to predict unseen data, using cross-validation. We also compare the stability of parameter estimates in the presence of i) noise, using bootstrapping, and ii) spatial variation, using visual assessment and comparison with anatomical knowledge. Broadly similar models emerge from the AIC and cross-validation experiments in both data sets. Specifically, a three-compartment model consisting of either a Bingham distribution of sticks or a Cylinder for the intracellular compartment, an anisotropic diffusion tensor (DT) model for the extracellular compartment, as well as an isotropic CSF compartment, performs consistently well. However, various other models also perform well and no single model emerges as clear winner. The WM data (with virtually no CSF contamination) do not support compartmental T2 but partially support compartmental diffusivity. Evaluation of parameter stability favours simpler models than those identified by AIC or cross-validation. They suggest that the level of complexity in models underpinning currently popular microstructure imaging techniques such as NODDI, CHARMED, or ActiveAx, where the number of free parameters is about 4 or 5 rather than 10 or 11, may reflect the level of complexity achievable for a useful technique on current systems, although the 300mT/m data may support more complex models.

JBHI Journal 2014 Journal Article

A Bayesian Bounded Asymmetric Mixture Model With Segmentation Application

• Thanh Minh Nguyen
• Q. M. Jonathan Wu
• Dibyendu Mukherjee
• Hui Zhang

Segmentation of a medical image based on the modeling and estimation of the tissue intensity probability density functions via a Gaussian mixture model has recently received great attention. However, the Gaussian distribution is unbounded and symmetrical around its mean. This study presents a new bounded asymmetric mixture model for analyzing both univariate and multivariate data. The advantage of the proposed model is that it has the flexibility to fit different shapes of observed data such as non-Gaussian, nonsymmetric, and bounded support data. Another advantage is that each component of the proposed model has the ability to model the observed data with different bounded support regions, which is suitable for application on image segmentation. Our method is intuitively appealing, simple, and easy to implement. We also propose a new method to estimate the model parameters in order to minimize the higher bound on the data negative log-likelihood function. Numerical experiments are presented where the proposed model is tested in various images from simulated to real 3- $\hbox{D}$ medical ones.

YNIMG Journal 2014 Journal Article

Assessing white matter microstructure of the newborn with multi-shell diffusion MRI and biophysical compartment models

• Nicolas Kunz
• Hui Zhang
• Lana Vasung
• Kieran R. O'Brien
• Yaniv Assaf
• François Lazeyras
• Daniel C. Alexander
• Petra S. Hüppi

Brain white matter connections have become a focus of major interest with important maturational processes occurring in newborns. To study the complex microstructural developmental changes in-vivo, it is imperative that non-invasive neuroimaging approaches are developed for this age-group. Multi-b-value diffusion weighted imaging data were acquired in 13 newborns, and the biophysical compartment diffusion models CHARMED-light and NODDI, providing new microstructural parameters such as intra-neurite volume fraction (ν in ) and neurite orientation dispersion index (ODI), were developed for newborn data. Comparative analysis was performed and twenty ROIs in the white matter were investigated. Diffusion tensor imaging and both biophysical compartment models highlighted the compact and oriented structure of the corpus-callosum with the highest FA and ν in values and the smallest ODI values. We could clearly differentiate, using the FA, ν in and ODI, the posterior and anterior internal capsule representing similar cellular structure but with different maturation (i. e. partially myelinated and absence of myelin, respectively). Late maturing regions (external capsule and periventricular crossroads of pathways) had lower ν in values, but displayed significant differences in ODI. The compartmented models CHARMED-light and NODDI bring new indices corroborating the cellular architectures, with the lowest ν in, reflecting the late maturation of areas with thin non-myelinated fibers, and with highest ODI indicating the presence of fiber crossings and fanning. The application of biophysical compartment diffusion models adds new insights to the brain white matter development in vivo.

YNICL Journal 2014 Journal Article

Characterizing the microstructural basis of “unidentified bright objects” in neurofibromatosis type 1: A combined in vivo multicomponent T2 relaxation and multi-shell diffusion MRI analysis

• Thibo Billiet
• Burkhard Mädler
• Felice D'Arco
• Ronald Peeters
• Sabine Deprez
• Ellen Plasschaert
• Alexander Leemans
• Hui Zhang

INTRODUCTION: The histopathological basis of "unidentified bright objects" (UBOs) (hyperintense regions seen on T2-weighted magnetic resonance (MR) brain scans in neurofibromatosis-1 (NF1)) remains unclear. New in vivo MRI-based techniques (multi-exponential T2 relaxation (MET2) and diffusion MR imaging (dMRI)) provide measures relating to microstructural change. We combined these methods and present previously unreported data on in vivo UBO microstructure in NF1. METHODS: 3-Tesla dMRI data were acquired on 17 NF1 patients, covering 30 white matter UBOs. Diffusion tensor, kurtosis and neurite orientation and dispersion density imaging parameters were calculated within UBO sites and in contralateral normal appearing white matter (cNAWM). Analysis of MET2 parameters was performed on 24 UBO-cNAWM pairs. RESULTS: No significant alterations in the myelin water fraction and intra- and extracellular (IE) water fraction were found. Mean T2 time of IE water was significantly higher in UBOs. UBOs furthermore showed increased axial, radial and mean diffusivity, and decreased fractional anisotropy, mean kurtosis and neurite density index compared to cNAWM. Neurite orientation dispersion and isotropic fluid fraction were unaltered. CONCLUSION: Our results suggest that demyelination and axonal degeneration are unlikely to be present in UBOs, which appear to be mainly caused by a shift towards a higher T2-value of the intra- and extracellular water pool. This may arise from altered microstructural compartmentalization, and an increase in 'extracellular-like', intracellular water, possibly due to intramyelinic edema. These findings confirm the added value of combining dMRI and MET2 to characterize the microstructural basis of T2 hyperintensities in vivo.

YNIMG Journal 2013 Journal Article

An unbiased longitudinal analysis framework for tracking white matter changes using diffusion tensor imaging with application to Alzheimer's disease

• Shiva Keihaninejad
• Hui Zhang
• Natalie S. Ryan
• Ian B. Malone
• Marc Modat
• M. Jorge Cardoso
• David M. Cash
• Nick C. Fox

We introduce a novel image-processing framework for tracking longitudinal changes in white matter microstructure using diffusion tensor imaging (DTI). Charting the trajectory of such temporal changes offers new insight into disease progression but to do so accurately faces a number of challenges. Recent developments have highlighted the importance of processing each subject's data at multiple time points in an unbiased way. In this paper, we aim to highlight a different challenge critical to the processing of longitudinal DTI data, namely the approach to image alignment. Standard approaches in the literature align DTI data by registering the corresponding scalar-valued fractional anisotropy (FA) maps. We propose instead a DTI registration algorithm that leverages full tensor information to drive improved alignment. This proposed pipeline is evaluated against the standard FA-based approach using a DTI dataset from an ongoing study of Alzheimer's disease (AD). The dataset consists of subjects scanned at two time points and at each time point the DTI acquisition consists of two back-to-back repeats in the same scanning session. The repeated scans allow us to evaluate the specificity of each pipeline, using a test–retest design, and assess precision, using bootstrap-based method. The results show that the tensor-based pipeline achieves both higher specificity and precision than the standard FA-based approach. Tensor-based registration for longitudinal processing of DTI data in clinical studies may be of particular value in studies assessing disease progression.

YNIMG Journal 2012 Journal Article

A diffusion tensor brain template for Rhesus Macaques

• Nagesh Adluru
• Hui Zhang
• Andrew S. Fox
• Steven E. Shelton
• Chad M. Ennis
• Anne M. Bartosic
• Jonathan A. Oler
• Do P.M. Tromp

Diffusion tensor imaging (DTI) is a powerful and noninvasive imaging method for characterizing tissue microstructure and white matter organization in the brain. While it has been applied extensively in research studies of the human brain, DTI studies of non-human primates have been performed only recently. The growing application of DTI in rhesus monkey studies would significantly benefit from a standardized framework to compare findings across different studies. A very common strategy for image analysis is to spatially normalize (co-register) the individual scans to a representative template space. This paper presents the development of a DTI brain template, UWRMAC-DTI271, for adolescent Rhesus Macaque (Macaca mulatta) monkeys. The template was generated from 271 rhesus monkeys, collected as part of a unique brain imaging genetics study. It is the largest number of animals ever used to generate a computational brain template, which enables the generation of a template that has high image quality and accounts for variability in the species. The quality of the template is further ensured with the use of DTI-TK, a well-tested and high-performance DTI spatial normalization method in human studies. We demonstrated its efficacy in monkey studies for the first time by comparing it to other commonly used scalar-methods for DTI normalization. It is anticipated that this template will play an important role in facilitating cross-site voxelwise DTI analyses in Rhesus Macaques. Such analyses are crucial in investigating the role of white matter structure in brain function, development, and other psychopathological disorders for which there are well-validated non-human primate models.

YNIMG Journal 2012 Journal Article

NODDI: Practical in vivo neurite orientation dispersion and density imaging of the human brain

• Hui Zhang
• Torben Schneider
• Claudia A. Wheeler-Kingshott
• Daniel C. Alexander

This paper introduces neurite orientation dispersion and density imaging (NODDI), a practical diffusion MRI technique for estimating the microstructural complexity of dendrites and axons in vivo on clinical MRI scanners. Such indices of neurites relate more directly to and provide more specific markers of brain tissue microstructure than standard indices from diffusion tensor imaging, such as fractional anisotropy (FA). Mapping these indices over the whole brain on clinical scanners presents new opportunities for understanding brain development and disorders. The proposed technique enables such mapping by combining a three-compartment tissue model with a two-shell high-angular-resolution diffusion imaging (HARDI) protocol optimized for clinical feasibility. An index of orientation dispersion is defined to characterize angular variation of neurites. We evaluate the method both in simulation and on a live human brain using a clinical 3T scanner. Results demonstrate that NODDI provides sensible neurite density and orientation dispersion estimates, thereby disentangling two key contributing factors to FA and enabling the analysis of each factor individually. We additionally show that while orientation dispersion can be estimated with just a single HARDI shell, neurite density requires at least two shells and can be estimated more accurately with the optimized two-shell protocol than with alternative two-shell protocols. The optimized protocol takes about 30min to acquire, making it feasible for inclusion in a typical clinical setting. We further show that sampling fewer orientations in each shell can reduce the acquisition time to just 10min with minimal impact on the accuracy of the estimates. This demonstrates the feasibility of NODDI even for the most time-sensitive clinical applications, such as neonatal and dementia imaging.

YNIMG Journal 2011 Journal Article

A weighted-RV method to detect fine-scale functional connectivity during resting state

• Hui Zhang
• Xiaopeng Zhang
• Yingshi Sun
• Jiangang Liu
• Wu Li
• Jie Tian

During the resting state, in the absence of external stimuli or goal-directed mental tasks, some functionally related discrete regions of the brain show complex low-frequency fluctuations in the blood oxygenation level dependent signal. Here we developed a novel ROI-based multivariate statistical framework to obtain the fine-grained patterns of functionally specialized brain networks in the resting state. Under this framework, the weighted-RV method is proposed and used to detect the spatial fine-scale patterns of functional connectivity. This approach overcomes several major problems of the traditional resting-state data analysis methods such as Pearson correlation and linear regression analysis. By using simulation and real fMRI experiment, we have found that the weighted-RV method is shown to be more sensitive in detecting the fine-scale based low-frequency connectivity even at a very low functional contrast-to-noise ratio (CNR), and this method can achieve much better performance in mapping the fine-grained patterns of functionally specialized brain networks compared to the traditional methods.

YNIMG Journal 2011 Journal Article

Axon diameter mapping in the presence of orientation dispersion with diffusion MRI

• Hui Zhang
• Penny L. Hubbard
• Geoff J.M. Parker
• Daniel C. Alexander

Direct measurement of tissue microstructure with diffusion MRI offers a new class of markers, such as axon diameters, that give more specific information about tissue than measures derived from diffusion tensor imaging. The existing techniques of this kind assume a single axon orientation in the tissue model, which may be a reasonable approximation only for the most coherently oriented brain white matter, such as the corpus callosum. For most other areas, orientation dispersion is not negligible and, if unaccounted for, leads to overestimation of the axon diameters, prohibiting their accurate mapping over the whole brain. Here we propose a new model that captures the effect of orientation dispersion explicitly. A numerical scheme is developed to compute the diffusion signal prescribed by the proposed model efficiently, which supports the simultaneous estimation of the axon diameter and orientation dispersion. Synthetic data experiments demonstrate that the new model provides an axon diameter index that is robust to the presence of orientation dispersion. Results on in vivo human data show reduced axon diameter index and better agreement with histology compared to previous methods suggesting improvements in the axon diameter estimate.

YNIMG Journal 2011 Journal Article

DTI registration in atlas based fiber analysis of infantile Krabbe disease

• Yi Wang
• Aditya Gupta
• Zhexing Liu
• Hui Zhang
• Maria L. Escolar
• John H. Gilmore
• Sylvain Gouttard
• Pierre Fillard

In recent years, diffusion tensor imaging (DTI) has become the modality of choice to investigate white matter pathology in the developing brain. To study neonate Krabbe disease with DTI, we evaluate the performance of linear and non-linear DTI registration algorithms for atlas based fiber tract analysis. The DTI scans of 10 age-matched neonates with infantile Krabbe disease are mapped into an atlas for the analysis of major fiber tracts — the genu and splenium of the corpus callosum, the internal capsules tracts and the uncinate fasciculi. The neonate atlas is based on 377 healthy control subjects, generated using an unbiased diffeomorphic atlas building method. To evaluate the performance of one linear and seven nonlinear commonly used registration algorithms for DTI we propose the use of two novel evaluation metrics: a regional matching quality criterion incorporating the local tensor orientation similarity, and a fiber property profile based metric using normative correlation. Our experimental results indicate that the whole tensor based registration method within the DTI-ToolKit (DTI-TK) shows the best performance for our application.

EAAI Journal 2011 Journal Article

Intelligent injection liquid particle inspection machine based on two-dimensional Tsallis Entropy with modified pulse-coupled neural networks

• Yaonan Wang
• Ji Ge
• Hui Zhang
• Bowen Zhou

The Automatic Liquid Particle Inspection Machine (AIM) using 2-D Tsallis Entropy with modified pulse-coupled neural networks (PCNN) is used in order to detect visible foreign particles within injection fluids. According to the motion of the particles in liquid, appropriate mechanisms are utilized which guarantees that the inspection machine will follow detection procedures: “Rotation, Abruptly Braking, Video Tracking” to extract tiny objects from complicated sequential images. In order to reduce the influence derived from air bubbles, improved spin/stop techniques are applied. The external capture mode of CCD cameras is used to avoid the possibility of omitting certain particles by trivial displacement. 2-D Tsallis Entropy with modified PCNN is applied in order to segment the difference images, and then to judge the existence of foreign particles according to the continuity and smoothness of their traces. Preliminary experimental results (125ml 0. 9% sodium chloride solution and 10% glucose as the samples) indicate that the inspection machine, which is superior to proficient inspectors, can detect the visible foreign particles effectively and that this detection speed and accuracy, as well as the correct detection rate can also facilitate the medicinal construction.

ICRA Conference 2011 Conference Paper

Software, electronics and mechanical components co-simulation for efficient design

• Yicheng Zhang 0001
• Nuo Li
• Said Zahrai
• Hui Zhang

A method and a tool for simulation of a control system are presented. The tool allows integration of software components, electronics and mechanical devices into the same package and makes it possible to simulate the complete system accounting for all time-discretizations and physical delays in an accurate way. The software used for control of the virtual system is exactly the same as that used in the final product. The complete system can be prototyped in a virtual world, be tested and optimized long before a physical prototype is built.

ICRA Conference 2011 Conference Paper

Virtual prototyping for drive chain optimization in an industrial robot

• Bojun Ma
• Hao Li
• Said Zahrai
• Hui Zhang

Cost, performance and efficiency of energy usage of a robot system is strongly dependent on its drive chain, i. e. combination of the drive, the motors and the gears. A model is presented that allows accurate simulation of the drive chain in an industrial robot to offer a high degree of optimization in the design process. Simulation results are compared to final data from the developed units and excellent agreements are found.

AIIM Journal 2009 Journal Article

An integrated scheme for feature selection and parameter setting in the support vector machine modeling and its application to the prediction of pharmacokinetic properties of drugs

• Sheng-Yong Yang
• Qi Huang
• Lin-Li Li
• Chang-Ying Ma
• Hui Zhang
• Ru Bai
• Qi-Zhi Teng
• Ming-Li Xiang

Objective Support vector machine (SVM), a statistical learning method, has recently been evaluated in the prediction of absorption, distribution, metabolism, and excretion properties, as well as toxicity (ADMET) of new drugs. However, two problems still remain in SVM modeling, namely feature selection and parameter setting. The two problems have been shown to have an important impact on the efficiency and accuracy of SVM classification. In particular, the feature subset choice and optimal SVM parameter settings influence each other; this suggested that they should be dealt with simultaneously. In this paper, we propose an integrated scheme to account for both feature subset choice and SVM parameter settings in concert. Method In the proposed scheme, a genetic algorithm (GA) is used for the feature selection and the conjugate gradient (CG) method for the parameter optimization. Several classification models of ADMET related properties have been built for assessing and testing the integrated GA–CG-SVM scheme. They include: (1) identification of P-glycoprotein substrates and nonsubstrates, (2) prediction of human intestinal absorption, (3) prediction of compounds inducing torsades de pointes, and (4) prediction of blood–brain barrier penetration. Results Compared with the results of previous SVM studies, our GA–CG-SVM approach significantly improves the overall prediction accuracy and has fewer input features. Conclusions Our results indicate that considering feature selection and parameter optimization simultaneously, in SVM modeling, can help to develop better predictive models for the ADMET properties of drugs.

IROS Conference 2009 Conference Paper

Improving machining accuracy with robot deformation compensation

• Jianjun Wang 0001
• Hui Zhang
• Thomas A. Fuhlbrigge

Industrial robots offer a cheaper yet more flexible alternative to the CNC machines in the cleaning and pre-machining applications of automotive aluminum castings. But the low stiffness has limited the application of industrial robots to the machining tasks with very low precision requirement. This paper presents a practical method to compensate the robot deformation caused by the machining force. A constant joint stiffness model based feed forward compensation scheme is implemented in the robot controller. The compensation scheme is shown to be able to reduce the position error by more than 60%. Application test in milling a standard aluminum block has demonstrated the effectiveness of the proposed deformation compensation method. The surface error is reduced from 0. 5 mm to 0. 1 mm.

TCS Journal 2008 Journal Article

Property matching and weighted matching

• Amihood Amir
• Eran Chencinski
• Costas Iliopoulos
• Tsvi Kopelowitz
• Hui Zhang

In many pattern matching applications the text has some properties attached to its various parts. Pattern Matching with Properties (Property Matching, for short), involves a string matching between the pattern and the text, and the requirement that the text part satisfies some property. Some immediate examples come from molecular biology where it has long been a practice to consider special areas in the genome by their structures. It is straightforward to do sequential matching in a text with properties. However, indexing in a text with properties becomes difficult if we desire the time to be output dependent. We present an algorithm for indexing a text with properties in O ( n log | Σ | + n log log n ) time for preprocessing and O ( | P | log | Σ | + tocc π ) per query, where n is the length of the text, P is the sought pattern, Σ is the alphabet, and tocc π is the number of occurrences of the pattern that satisfy some property π. As a practical use of Property Matching we show how to solve Weighted Matching problems using techniques from Property Matching. Weighted sequences have recently been introduced as a tool to handle a set of sequences that are not identical but have many local similarities. The weighted sequence is a “statistical image” of this set, where we are given the probability of every symbol’s occurrence at every text location. Weighted matching problems are pattern matching problems where the given text is weighted. We present a reduction from Weighted Matching to Property Matching that allows off-the-shelf solutions to numerous weighted matching problems including indexing, swapped matching, parameterized matching, approximate matching, and many more. Assuming that one seeks the occurrence of pattern P with probability ϵ in weighted text T of length n, we reduce the problem to a property matching problem of pattern P in text T ′ of length O ( n ( 1 ϵ ) 2 log 1 ϵ ).

YNIMG Journal 2008 Journal Article

Structure-specific statistical mapping of white matter tracts

• Paul A. Yushkevich
• Hui Zhang
• Tony J. Simon
• James C. Gee

We present a new model-based framework for the statistical analysis of diffusion imaging data associated with specific white matter tracts. The framework takes advantage of the fact that several of the major white matter tracts are thin sheet-like structures that can be effectively modeled by medial representations. The approach involves segmenting major tracts and fitting them with deformable geometric medial models. The medial representation makes it possible to average and combine tensor-based features along directions locally perpendicular to the tracts, thus reducing data dimensionality and accounting for errors in normalization. The framework enables the analysis of individual white matter structures, and provides a range of possibilities for computing statistics and visualizing differences between cohorts. The framework is demonstrated in a study of white matter differences in pediatric chromosome 22q11. 2 deletion syndrome.

YNIMG Journal 2007 Journal Article

Hippocampus-specific fMRI group activation analysis using the continuous medial representation

• Paul A. Yushkevich
• John A. Detre
• Dawn Mechanic-Hamilton
• María A. Fernández-Seara
• Kathy Z. Tang
• Angela Hoang
• Marc Korczykowski
• Hui Zhang

We present a new shape-based approach for regional group activation analysis in fMRI studies. The method restricts anatomical normalization, spatial smoothing and random effects statistical analysis to the space inside and around a structure of interest. Normalization involves finding intersubject correspondences between manually outlined masks, and it leverages the continuous medial representation, which makes it possible to extend surface-based shape correspondences to the space inside and outside of structures. Our approach is an alternative to whole-brain normalization in cases where the latter may fail due to anatomical variability or pathology. It also provides an opportunity to analyze the shape and thickness of structures concurrently with functional activation. We apply the technique to the hippocampus and evaluate it using data from a visual scene encoding fMRI study, where activation in the hippocampus is expected. We produce detailed statistical maps of hippocampal activation, as well as maps comparing activation inside and outside of the hippocampus. We find that random effects statistics computed by the new approach are more significant than those produced using the Statistical Parametric Mapping framework (Friston, K. J. , Holmes, A. P. , Worsley, K. J. , Poline, J. -P. , Firth, C. D. , Frackowiak, R. S. J. 1994, Statistical parametric maps in functional imaging: a general linear approach. Human Brain Mapping, 2(4): 189–210) at low levels of smoothing, suggesting that greater specificity can be achieved by the new method without a severe tradeoff in sensitivity.

IROS Conference 2006 Conference Paper

On-Line Path Generation for Robotic Deburring of Cast Aluminum Wheels

• Hui Zhang
• Heping Chen
• Ning Xi 0001
• George Zhang 0001
• Jianmin He

Cast aluminum wheels must be deburred and polished before chrome plating operation. Manual deburring and polishing is tedious and monotonous. Industrial robots are attracting more and more attention for the deburring applications. However, Each wheel path program was taking eight to ten weeks to create because the position and orientation of the deburring tool must be accurately identified based on the curvature of the wheel. To solve this problem, we developed a practical 6 DOF robot path generation method using hybrid force and visual servoing methodology. The force servoing keeps the robot tool continuously contacting with the wheel surface and the visual servoing controls the robot tool to follow a marked tool path on the wheel while the position and orientation are controlled and recorded. A robot path is then generated from the recorded data. Experiments are performed and the experimental results demonstrate that the developed algorithm can be used to automatically generate accurate 6 DOF robot paths for deburring aluminum wheels in less than an hour. This significantly reduces the robot programming time. The developed technology can also be used for robot path generation in many other manufacturing applications, such as welding and strip painting

ICRA Conference 2004 Conference Paper

On Cutting and Dissection of Virtual Deformable Objects

• Hui Zhang
• Shahram Payandeh
• John Dill

Tissue dissection is an important procedure in surgical simulation systems. Dissection involves cutting through and separating the tissue after a cut. In this paper, we use a surface mass-spring model to simulate virtual dissection by progressive subdivision and re-meshing. We introduce novel algorithms to generate interior structures that show the cutting result generated by the interaction between instrument and model. In addition, a novel data structure for object representation after the cutting action is proposed which allows the original soft object to be divided and a portion manipulated away. The dissection environment can support a number of user interface devices which can manipulate different representation of virtual instruments. These techniques are being integrated into a training environment for both open and minimally invasive surgery.