Hao Huang

EAAI Journal 2026 Journal Article

A symbolic node-priority ranker driven by deep reinforcement learning for distributed traffic signal control

• Guoqiang Chen
• Lan Liu
• Jiannan Mao
• Weike Lu
• Guojing Hu
• Hao Huang

In distributed traffic signal control (DTSC) systems, properly prioritizing intersections is crucial for improving network-wide traffic efficiency. However, existing node-priority ranking methods often rely on empirical rules or black-box models, leading to either limited performance or poor interpretability. To address this challenge, we propose SymRanker, a deep reinforcement learning-driven symbolic ranker for node prioritization. From the AI perspective, SymRanker is built on Proximal Policy Optimization (PPO) and consists of two key neural components: an Actor policy network and a Critic network. The Actor is implemented as a Recurrent Neural Network (RNN) and uses a binary-tree representation to efficiently search for interpretable node-ranking formulas. The Critic provides value estimates to stabilize policy optimization, reduce variance, and improve convergence during training. From the engineering perspective, SymRanker is tailored to DTSC by integrating a multi-penetration-rate mechanism into policy updates, ensuring consistent performance across different network penetration rates. Experiments on six benchmark networks show that SymRanker uncovers latent regularities and expresses them as concise symbolic formulas. Ablation studies demonstrate a 90% gain in formula reproduction accuracy when structure learning is decoupled from constant estimation. Further studies on two DTSC systems demonstrate that controlling only critical intersections can achieve performance comparable to full-node control. Across four settings, precision control achieves the same performance as 100% deployment, with distributed controllers installed on only 45% of the nodes. Overall, these results confirm the effectiveness of SymRanker and offer a practical solution to intersection prioritization in DTSC.

EAAI Journal 2026 Journal Article

Adaptive spatial–temporal graph attention network for real-time traffic forecasting

• Hao Huang
• Jee-Hyong Lee
• Yanling Ge
• Seok-Beom Roh
• Xue Zhao

Accurate and efficient Multivariate Time Series Forecasting (MTSF) plays a critical role in intelligent transportation systems by supporting real-time traffic management. However, achieving reliable forecasting remains challenging due to complex and dynamically evolving spatial–temporal patterns. Existing forecasting methods often fail to adapt effectively to these dynamic traffic conditions and typically incur high computational costs, significantly limiting their deployment in real-time traffic management scenarios. To address these engineering challenges, this study proposes a novel Attention-based Spatial-Temporal Network (ASTNet), explicitly designed for adaptive and efficient real-time traffic forecasting. ASTNet introduces two innovative Artificial Intelligence (AI)-driven modules: an Adaptive Spatial Graph Encoder (ASGE), which dynamically models evolving spatial dependencies from real-time traffic data, thus overcoming the limitations of static graph structures; and a Temporal Attention-Gated Unit (TAGU), which efficiently captures critical temporal dependencies through the integration of recurrent gating mechanisms and self-attention techniques. Extensive evaluations conducted on widely-used traffic benchmark datasets (PEMS04, METR-LA, etc.) confirm that ASTNet achieves superior predictive accuracy and robustness compared to state-of-the-art methods, while significantly reducing inference latency. Ablation studies further validate that the combined innovations of ASGE and TAGU are crucial for ASTNet’s outstanding performance, highlighting its practical suitability and strong potential for deployment in real-time intelligent transportation applications.

EAAI Journal 2026 Journal Article

Distribution-guided and perturbation based contrastive clustering for specific emitter identification

• Ke Wang
• Yiting Gao
• Hao Huang
• Jiao Wang
• Jiaxu Liu
• Yao Zheng
• Jianqing Li

Specific Emitter Identification (SEI) authenticates devices from Radio Frequency (RF) hardware fingerprints and is crucial for large, label-scarce Internet of Things (IoT) deployments. While recent label-free methods such as Deep Transfer Clustering (DTC) and Signal Contrastive Self-Supervised Clustering (SCSC) reduce annotation needs, they typically require the true number of emitters and optimize with augmentation or transfer-driven objectives, limiting applicability when the emitter number is unknown or dynamic. To address these limitations, we propose an innovative Distribution-guided and Perturbation based Contrastive Clustering framework (DPCC) for unsupervised SEI, which differs from DTC and SCSC by not assuming a predefined emitter number — the effective cluster count emerges from active logits at convergence — by using physically grounded contrastive pairs (same-receiver slicing and cross-receiver co-occurrence) instead of generic augmentations, and by applying distribution-guided strong–weak initialization with a confidence-triggered dynamic perturbation to prevent premature collapse and escape local optima. On a public real-world long-range (LoRa) fingerprint corpus, DPCC improves accuracy by 20. 08% over SCSC and 58. 13% over DTC; on the public automatic dependent surveillance-broadcast (ADS-B) Top-10 dataset, it also surpasses other unsupervised baselines across all primary metrics. Comprehensive ablation studies corroborate the contribution of each component, while confirming strong generalization and validating DPCC’s robustness and practicality in realistic wireless environments.

AAAI Conference 2026 Conference Paper

Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding

• Di Wu
• Liting Jiang
• Ruiyu Fang
• Bianjing
• Hongyan Xie
• Haoxiang Su
• Hao Huang
• Zhongjiang He

Spoken Language Understanding (SLU) consists of two sub-tasks: intent detection (ID) and slot filling (SF). Given its broad range of real-world applications, enhancing SLU for practical deployment is increasingly critical. Profile-based SLU addresses ambiguous user utterances by incorporating context awareness (CA), user profiles (UP), and knowledge graphs (KG) to support disambiguation, thereby advancing SLU research toward real-world applicability. However, existing SLU datasets still fall short in representing real-world scenarios. Specifically, (1) CA uses one-hot vectors for representation, which is overly idealized, and (2) models typically focuses solely on predicting intents and slot labels, neglecting the reasoning process that could enhance performance and interpretability. To overcome these limitations, we introduce VRSLU, a novel SLU dataset that integrates both Visual images and explicit Reasoning. For over-idealized CA, we use GPT-4o and FLUX.1-dev to generate images reflecting users’ environments and statuses, followed by human verification to ensure quality. For reasoning, GPT-4o is employed to generate explanations for predicted labels, which are then refined by human annotators to ensure accuracy and coherence. Additionally, we propose an instructional template, LR-Instruct, which first predicts labels and then generates corresponding reasoning. This two-step approach helps mitigate the influence of reasoning bias on label prediction. Experimental results confirm the effectiveness of incorporating visual information and highlight the promise of explicit reasoning in advancing SLU.

AAAI Conference 2026 Conference Paper

MVGD-Net: A Novel Motion-aware Video Glass Surface Detection Method

• Yiwei Lu
• Hao Huang
• Tao Yan

Glass surface ubiquitous in both daily life and professional environments presents a potential threat to vision-based systems, such as robot and drone navigation. To solve this challenge, most recent studies have shown significant interest in Video Glass Surface Detection (VGSD). We observe that objects in the reflection (or transmission) layer appear farther from the glass surfaces. Consequently, in video motion scenarios, the notable reflected (or transmitted) objects on the glass surface move slower than objects in non-glass regions within the same spatial plane, and this motion inconsistency can effectively reveal the presence of glass surfaces. Based on this observation, we propose a novel network, named MVGD-Net, for detecting glass surfaces in videos by leveraging motion inconsistency cues. Our MVGD-Net features three novel modules: the Cross-scale Multimodal Fusion Module (CMFM) that integrates extracted spatial features and estimated optical flow maps, the History Guided Attention Module (HGAM) and Temporal Cross Attention Module (TCAM), both of which further enhances temporal features. A Temporal-Spatial Decoder (TSD) is also introduced to fuse the spatial and temporal features for generating the glass region mask. Furthermore, for learning our network, we also propose a large-scale dataset, which comprises 312 diverse glass scenarios with a total of 19,268 frames. Extensive experiments demonstrate that our MVGD-Net outperforms relevant state-of-the-art methods. We will release our code and dataset.

AAAI Conference 2026 Conference Paper

Vision-Only Gaussian Splatting for Collaborative Semantic Occupancy Prediction

• Cheng Chen
• Hao Huang
• Saurabh Bagchi

Collaborative perception enables connected vehicles to share information, overcoming occlusions and extending the limited sensing range inherent in single-agent (non-collaborative) systems. Existing vision-only methods for 3D semantic occupancy prediction commonly rely on dense 3D voxels, which incur high communication costs, or 2D planar features, which require accurate depth estimation or additional supervision, limiting their applicability to collaborative scenarios. To address these challenges, we propose the first approach leveraging sparse 3D semantic Gaussian splatting for collaborative 3D semantic occupancy prediction. By sharing and fusing intermediate Gaussian primitives, our method provides three benefits: a neighborhood-based cross-agent fusion that removes duplicates and suppresses noisy or inconsistent Gaussians; a joint encoding of geometry and semantics in each primitive, which reduces reliance on depth supervision and allows simple rigid alignment; and sparse, object-centric messages that preserve structural information while reducing communication volume. Extensive experiments demonstrate that our approach outperforms single-agent perception and baseline collaborative methods by +8.42 and +3.28 points in mIoU, and +5.11 and +22.41 points in IoU, respectively. When further reducing the number of transmitted Gaussians, our method still achieves a +1.9 improvement in mIoU, using only 34.6% communication volume, highlighting robust performance under limited communication budgets.

JBHI Journal 2025 Journal Article

A Graph-based Multi-dimensional Interaction Network for Drug-Drug Interaction Prediction

• Lejun Gong
• Xinyi Wei
• Hongqin Ji
• Hao Huang
• Yimu Ji

In the treatment of complex diseases, drug combination therapy is common, but drug-drug interactions (DDI) can cause severe side effects, threaten patient safety, and increase healthcare costs. Existing DDI prediction methods often focus on drug substructure features but overlook the complex interactions between them. To address this, this paper proposes the Multi-dimensional Interaction Graph Neural Network (MDI-DDI). The model combines four GraphSAGE convolution layers with a Tri-Co Attention Module. It first calculates interaction strength at the 2D level using a co- attention mechanism, then captures deeper interactions at the 3D level using a triplet structure. Experimental results show that MDI-DDI outperforms existing methods, achieving ACC, AUPRC, and AUROC of 0. 9613, 0. 9901, and 0. 9871, respectively, on the DrugBank dataset. Additionally, the risk analysis of nitrate and nitrite drugs demonstrates the model's ability to accurately identify key functional groups, further validating its interpretability.

TMLR Journal 2025 Journal Article

Curvature Diversity-Driven Deformation and Domain Alignment for Point Cloud

• Mengxi Wu
• Hao Huang
• Yi Fang
• Mohammad Rostami

Unsupervised Domain Adaptation is crucial for point cloud learning due to geometric variations across different generation methods and sensors. To tackle this challenge, we propose Curvature Diversity-Driven Nuclear-Norm Wasserstein Domain Alignment (CDND). We first introduce a Curvature Diversity-driven Deformation Reconstruction (CurvRec) task, enabling the model to extract salient features from semantically rich regions of a given point cloud. We then propose a theoretical framework for Deformation-based Nuclear-norm Wasserstein Discrepancy (D-NWD), extending the Nuclear-norm Wasserstein Discrepancy to original and deformed samples. Our theoretical analysis demonstrates that D-NWD is effective for any deformation method. Empirical experiment results show that our CDND achieves state-of-the-art performance by a noticeable margin over existing approaches.

AAAI Conference 2025 Conference Paper

OpenVIS: Open-vocabulary Video Instance Segmentation

• Pinxue Guo
• Hao Huang
• Peiyang He
• Xuefeng Liu
• Tianjun Xiao
• Wenqiang Zhang

Open-vocabulary Video Instance Segmentation (OpenVIS) can simultaneously detect, segment, and track arbitrary object categories in a video, without being constrained to categories seen during training. In this work, we propose InstFormer, a carefully designed framework for the OpenVIS task that achieves powerful open-vocabulary capabilities through lightweight fine-tuning with limited-category data. InstFormer begins with the open-world mask proposal network, encouraged to propose all potential instance class-agnostic masks by the contrastive instance margin loss. Next, we introduce InstCLIP, adapted from pre-trained CLIP with Instance Guidance Attention, which encodes open-vocabulary instance tokens efficiently. These instance tokens not only enable open-vocabulary classification but also offer strong universal tracking capabilities. Furthermore, to prevent the tracking module from being constrained by the training data with limited categories, we propose the universal rollout association, which transforms the tracking problem into predicting the next frame’s instance tracking token. The experimental results demonstrate the proposed InstFormer achieve state-of-the-art capabilities on a comprehensive OpenVIS evaluation benchmark, while also achieves competitive performance in fully supervised VIS task.

EAAI Journal 2025 Journal Article

Progressive semi-supervised learning for specific emitter identification: An iterative clustering and pseudo-label refinement approach

• Yiting Gao
• Ke Wang
• Hao Huang
• Jiao Wang
• Jiaxu Liu
• Yao Zheng
• Jianqing Li

Specific Emitter Identification (SEI) distinguishes radio-frequency (RF) devices by exploiting hardware-induced signal fingerprints, thereby strengthening wireless-layer security. Existing deep learning-based SEI methods depend heavily on labeled data and fixed confidence thresholds for pseudo-labeling, which limits their effectiveness under label scarcity or open-set conditions. To overcome these issues, we propose a progressive semi-supervised learning (ProSSL) method for SEI that combines iterative clustering with contrastive learning to generate adaptive pseudo-labels. ProSSL introduces an “uncertain” class and employs a dual-constraint selector—prediction stability and class diversity—to suppress noisy pseudo-labels and ensure robust propagation. Experiments on the public real-world long range(LoRa) RF-fingerprint dataset show that ProSSL gains 2. 90%–6. 01% absolute accuracy over state-of-the-art baselines, reaching 96. 48% accuracy with 90% labels and 59. 88% with only 5% labels. While on the public automatic dependent surveillance-broadcast(ADS-B) Top-10 dataset, ProSSL achieves 84. 40% accuracy with 5% labeled data and 99. 40% accuracy with 90%labeled data, again outperforming all competing methods. Open-set evaluations further demonstrate that overall accuracy rises from 18. 81% when only two classes are known to 62. 25% when eight classes are known, confirming strong generalization to unseen emitters and validating ProSSL’s robustness and practicality in realistic wireless environments.

JBHI Journal 2025 Journal Article

Residual Self-Calibrated Network With Multi-Scale Channel Attention for Accurate EOG-Based Eye Movement Classification

• Zheng Zeng
• Linkai Tao
• Ruizhi Su
• Adili Tuheti
• Hao Huang
• Chen Chen
• Wei Chen

Recently, Electrooculography-based Human-Computer Interaction (EOG-HCI) technology has gained widespread attention in industrial areas, including assistive robots, augmented reality in gaming, etc. However, as the fundamental step of EOG-HCI, accurate eye movement classification (EMC) still faces a significant challenge, where their constraints in extracting discriminative features limit the performance of most existing works. To address this issue, a Residual Self-Calibrated Network with Multi-Scale Channel Attention (RSCA), focusing on efficient feature extraction and enhancement is proposed. The RSCA network first employs three self-calibrated convolution blocks within a hierarchical residual framework to fully extract the discriminative multi-scale features. Then, a multi-scale channel attention module adaptively weights the learned features to screen out the discriminative representation by aggregating the multi-scale context information along the channel dimension, thus further boosting the performance. Comprehensive experiments were performed using 5 public datasets and 7 prevailing methods for comparative validation. The results confirm that the RSCA network outperforms all other methods significantly, establishing a state-of-the-art benchmark for EOG-based EMC. Furthermore, thorough ablation analyses confirm the effectiveness of the employed modules within the RSCA network, providing valuable insights for the design of EOG-based deep models.

NeurIPS Conference 2024 Conference Paper

$\texttt{dattri}$: A Library for Efficient Data Attribution

• Junwei Deng
• Ting-Wei Li
• Shiyuan Zhang
• Shixuan Liu
• Yijun Pan
• Hao Huang
• Xinhe Wang
• Pingbang Hu

Data attribution methods aim to quantify the influence of individual training samples on the prediction of artificial intelligence (AI) models. As training data plays an increasingly crucial role in the modern development of large-scale AI models, data attribution has found broad applications in improving AI performance and safety. However, despite a surge of new data attribution methods being developed recently, there lacks a comprehensive library that facilitates the development, benchmarking, and deployment of different data attribution methods. In this work, we introduce $\texttt{dattri}$, an open-source data attribution library that addresses the above needs. Specifically, $\texttt{dattri}$ highlights three novel design features. Firstly, $\texttt{dattri}$ proposes a unified and easy-to-use API, allowing users to integrate different data attribution methods into their PyTorch-based machine learning pipeline with a few lines of code changed. Secondly, $\texttt{dattri}$ modularizes low-level utility functions that are commonly used in data attribution methods, such as Hessian-vector product, inverse-Hessian-vector product or random projection, making it easier for researchers to develop new data attribution methods. Thirdly, $\texttt{dattri}$ provides a comprehensive benchmark framework with pre-trained models and ground truth annotations for a variety of benchmark settings, including generative AI settings. We have implemented a variety of state-of-the-art efficient data attribution methods that can be applied to large-scale neural network models, and will continuously update the library in the future. Using the developed $\texttt{dattri}$ library, we are able to perform a comprehensive and fair benchmark analysis across a wide range of data attribution methods. The source code of $\texttt{dattri}$ is available at https: //github. com/TRAIS-Lab/dattri.

NeurIPS Conference 2024 Conference Paper

Benchmarking Complex Instruction-Following with Multiple Constraints Composition

• Bosi Wen
• Pei Ke
• Xiaotao Gu
• Lindong Wu
• Hao Huang
• Jinfeng Zhou
• Wenchuang Li
• Binxin Hu

Instruction following is one of the fundamental capabilities of large language models (LLMs). As the ability of LLMs is constantly improving, they have been increasingly applied to deal with complex human instructions in real-world scenarios. Therefore, how to evaluate the ability of complex instruction-following of LLMs has become a critical research problem. Existing benchmarks mainly focus on modeling different types of constraints in human instructions while neglecting the composition of different constraints, which is an indispensable constituent in complex instructions. To this end, we propose ComplexBench, a benchmark for comprehensively evaluating the ability of LLMs to follow complex instructions composed of multiple constraints. We propose a hierarchical taxonomy for complex instructions, including 4 constraint types, 19 constraint dimensions, and 4 composition types, and manually collect a high-quality dataset accordingly. To make the evaluation reliable, we augment LLM-based evaluators with rules to effectively verify whether generated texts can satisfy each constraint and composition. Furthermore, we obtain the final evaluation score based on the dependency structure determined by different composition types. ComplexBench identifies significant deficiencies in existing LLMs when dealing with complex instructions with multiple constraints composition.

AAAI Conference 2024 Conference Paper

Energy Efficient Streaming Time Series Classification with Attentive Power Iteration

• Hao Huang
• Tapan Shah
• Scott Evans
• Shinjae Yoo

Efficiently processing time series data streams in real-time on resource-constrained devices offers significant advantages in terms of enhanced computational energy efficiency and reduced time-related risks. We introduce an innovative streaming time series classification network that utilizes attentive power iteration, enabling real-time processing on resource-constrained devices. Our model continuously updates a compact representation of the entire time series, enhancing classification accuracy while conserving energy and processing time. Notably, it excels in streaming scenarios without requiring complete time series access, enabling swift decisions. Experimental results show that our approach excels in classification accuracy and energy efficiency, with over 70% less consumption and threefold faster task completion than benchmarks. This work advances real-time responsiveness, energy conservation, and operational effectiveness for constrained devices, contributing to optimizing various applications.

NeurIPS Conference 2024 Conference Paper

GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidance

• Shuaihang Yuan
• Hao Huang
• Yu Hao
• Congcong Wen
• Anthony Tzes
• Yi Fang

Zero-Shot Object Goal Navigation (ZS-OGN) enables robots to navigate toward objects of unseen categories without prior training. Traditional approaches often leverage categorical semantic information for navigation guidance, which struggles when only partial objects are observed or detailed and functional representations of the environment are lacking. To resolve the above two issues, we propose \textit{Geometric-part and Affordance Maps} (GAMap), a novel method that integrates object parts and affordance attributes for navigation guidance. Our method includes a multi-scale scoring approach to capture geometric-part and affordance attributes of objects at different scales. Comprehensive experiments conducted on the HM3D and Gibson benchmark datasets demonstrate improvements in Success Rates and Success weighted by Path Length, underscoring the efficacy of our geometric-part and affordance-guided navigation approach in enhancing robot autonomy and versatility, without any additional task-specific training or fine-tuning with the semantics of unseen objects and/or the locomotions of the robot.

YNIMG Journal 2024 Journal Article

Identifying novel data-driven subgroups in congenital heart disease using multi-modal measures of brain structure

• Marlee M. Vandewouw
• Ami Norris-Brilliant
• Anum Rahman
• Stephania Assimopoulos
• Sarah U. Morton
• Azadeh Kushki
• Sean Cunningham
• Eileen King

Individuals with congenital heart disease (CHD) have an increased risk of neurodevelopmental impairments. Given the hypothesized complexity linking genomics, atypical brain structure, cardiac diagnoses and their management, and neurodevelopmental outcomes, unsupervised methods may provide unique insight into neurodevelopmental variability in CHD. Using data from the Pediatric Cardiac Genomics Consortium Brain and Genes study, we identified data-driven subgroups of individuals with CHD from measures of brain structure. Using structural magnetic resonance imaging (MRI; N = 93; cortical thickness, cortical volume, and subcortical volume), we identified subgroups that differed primarily on cardiac anatomic lesion and language ability. In contrast, using diffusion MRI (N = 88; white matter connectivity strength), we identified subgroups that were characterized by differences in associations with rare genetic variants and visual-motor function. This work provides insight into the differential impacts of cardiac lesions and genomic variation on brain growth and architecture in patients with CHD, with potentially distinct effects on neurodevelopmental outcomes.

AAAI Conference 2024 Conference Paper

Learning Diffusions under Uncertainty

• Hao Huang
• Qian Yan
• Keqi Han
• Ting Gan
• Jiawei Jiang
• Quanqing Xu
• Chuanhui Yang

To infer a diffusion network based on observations from historical diffusion processes, existing approaches assume that observation data contain exact occurrence time of each node infection, or at least the eventual infection statuses of nodes in each diffusion process. They determine potential influence relationships between nodes by identifying frequent sequences, or statistical correlations, among node infections. In some real-world settings, such as the spread of epidemics, tracing exact infection times is often infeasible due to a high cost; even obtaining precise infection statuses of nodes is a challenging task, since observable symptoms such as headache only partially reveal a node’s true status. In this work, we investigate how to effectively infer a diffusion network from observation data with uncertainty. Provided with only probabilistic information about node infection statuses, we formulate the problem of diffusion network inference as a constrained nonlinear regression w.r.t. the probabilistic data. An alternating maximization method is designed to solve this regression problem iteratively, and the improvement of solution quality in each iteration can be theoretically guaranteed. Empirical studies are conducted on both synthetic and real-world networks, and the results verify the effectiveness and efficiency of our approach.

ECAI Conference 2024 Conference Paper

Nissist: An Incident Mitigation Copilot based on Troubleshooting Guides

• Kaikai An
• Fangkai Yang
• Junting Lu
• Liqun Li
• Zhixing Ren
• Hao Huang
• Lu Wang 0029
• Pu Zhao 0004

Effective incident management is pivotal for the smooth operation of Microsoft cloud services. In order to expedite incident mitigation, service teams gather troubleshooting knowledge into Troubleshooting Guides (TSGs) accessible to On-Call Engineers (OCEs). While automated pipelines are enabled to resolve the most frequent and easy incidents, there still exist complex incidents that require OCEs’ intervention. In addition, TSGs are often unstructured and incomplete, which requires manual interpretation by OCEs, leading to on-call fatigue and decreased productivity, especially among new-hire OCEs. In this work, we propose Nissist which leverages unstructured TSGs and incident mitigation history to provide proactive incident mitigation suggestions, reducing human intervention. Leveraging Large Language Models (LLM), Nissist extracts knowledge from unstructured TSGs and incident mitigation history, forming a comprehensive knowledge base. Its multi-agent system design enhances proficiency in precisely discerning OCE intents, retrieving relevant information, and delivering systematic plans consecutively. Through our user experiments, we demonstrate that Nissist significantly reduce Time to Mitigate (TTM) in incident mitigation, alleviating operational burdens on OCEs and improving service reliability. Our webpage is available at https: //aka. ms/nissist.

AAAI Conference 2024 Conference Paper

QI-IRA: Quantum-Inspired Interactive Ranking Aggregation for Person Re-identification

• Chunyu Hu
• Hong Zhang
• Chao Liang
• Hao Huang

Ranking aggregation (RA), the process of aggregating multiple rankings derived from multiple search strategies, has been proved effective in person re-identification (re-ID) because of a single re-ID method can not always achieve consistent superiority for different scenarios. Existing RA research mainly focus on unsupervised and fully-supervised methods. The former lack external supervision to optimize performance, while the latter are costly because of expensive labeling effort required for training. To address the above challenges, this paper proposes a quantum-inspired interactive ranking aggregation (QI-IRA) method, which (1) utilizes quantum theory to interpret and model the generation and aggregation of multiple basic rankings, (2) approximates or even exceeds the performance of fully-supervised RA methods with much less labeling cost, even as low as only two feedbacks per query on Market1501, MARS and DukeMTMC-VideoReID datasets. Comparative experiments conducted on six public re-ID datasets validate the superiority of the proposed QI-IRA method over existing unsupervised, interactive, and fully-supervised RA approaches.

EAAI Journal 2024 Journal Article

Specific emitter identification unaffected by time through adversarial domain adaptation and continual learning

• Jiaxu Liu
• Jiao Wang
• Hao Huang
• Jianqing Li

Timely identifying the emitter of target signals is crucial for communication security in complex electromagnetic environments. Specific emitter identification (SEI) is a technique to identify emitters using the hardware fingerprints of emitters. In this paper, the impact of changes in hardware fingerprints over time on SEI is solved, which significantly deteriorates identification performance. This issue is addressed from two aspects: one is mitigating the impact of these changes, and the other is tracking and adapting to them. For the aspect of mitigating impact, an alternating adversarial domain adaptation (AADA) method is proposed to eliminate the time-varying component in hardware fingerprints. Subsequently, a feature map calculation method using weighted Euclidean distance is designed, preserving the main parameters of feature maps for each emitter. For the aspect of tracking and adapting to changes, a continual learning method was designed based on feature maps of each emitter. This approach incorporates the selective annotation of unlabeled new data with an iterative optimization training process. To validate the effectiveness of the proposed method, we independently collected comprehensive time-variant datasets as well as simpler datasets with varying receivers and environments. The proposed method was tested on these datasets and compared with existing conventional and advanced methods. The experimental results indicate that the proposed SEI method exhibits superior recognition performance. Compared to existing methods, it achieved an average recognition accuracy improvement of over 8% on the time-variant dataset, and demonstrated enhanced robustness against these three types of variations.

JBHI Journal 2024 Journal Article

Unsupervised Transfer Learning Approach With Adaptive Reweighting and Resampling Strategy for Inter-Subject EOG-Based Gaze Angle Estimation

• Zheng Zeng
• Linkai Tao
• Ruizhi Su
• Yunfeng Zhu
• Long Meng
• Adili Tuheti
• Hao Huang
• Feng Shu

Gaze estimation based on electrooculograms (EOGs) has been widely explored. However, the inter-subject variability of EOGs still leaves a significant challenge for practical applications. It contributes to performance degradation when handling inter-subject issues. In this paper, an unsupervised transfer learning approach with an adaptive reweighting and resampling (ARR) strategy to fully consider individual variability is proposed for EOG-based gaze angle estimation. It allows quantifying domain shifts by leveraging the source-target similarities, reweighting and resampling the source data to retain relevant instances and disregard irrelevant instances during adaptation. Specifically, our proposed methodology first assesses the domain shifts via decomposing transformation matrices, which are estimated between the training subjects (denoted as multi-source domains) and the test subject (denoted as target domain). Then, the multi-domain shifts are assigned as weighted indicators to resample the multi-source domains for model training. Comparative experiments with several prevailing transfer learning methods including CORrelation ALignment (CORAL), Geodesic Flow Kernel (GFK), Joint Distribution Adaptation (JDA), Transfer component analysis (TCA), and Balanced distribution adaption (BDA) using two different normalization processes were conducted on a realistic scenario across 18 subjects. Experimental results demonstrate that the ARR strategy can significantly improve performance (mean absolute error (MAE) reduction: 7. 0%, root mean square error (RMSE) reduction: 6. 3%), outperforming the prevailing methods. Besides, the impacts of data diversity and data size on ARR strategy are further investigated. It exhibits that data size is more important than data diversity for EOG-based gaze angle estimation, and also presents the benefits of the ARR strategy for dealing with practical scenarios.

YNIMG Journal 2023 Journal Article

Maturation of auditory cortex neural responses during infancy and toddlerhood

• Yuhan Chen
• Heather L. Green
• Mary E. Putt
• Olivia Allison
• Emily S. Kuschner
• Mina Kim
• Lisa Blaskey
• Kylie Mol

The infant auditory system rapidly matures across the first years of life, with a primary goal of obtaining ever-more-accurate real-time representations of the external world. Our understanding of how left and right auditory cortex neural processes develop during infancy, however, is meager, with few studies having the statistical power to detect potential hemisphere and sex differences in primary/secondary auditory cortex maturation. Using infant magnetoencephalography (MEG) and a cross-sectional study design, left and right auditory cortex P2m responses to pure tones were examined in 114 typically developing infants and toddlers (66 males, 2 to 24 months). Non-linear maturation of P2m latency was observed, with P2m latencies decreasing rapidly as a function of age during the first year of life, followed by slower changes between 12 and 24 months. Whereas in younger infants auditory tones were encoded more slowly in the left than right hemisphere, similar left and right P2m latencies were observed by ∼21 months of age due to faster maturation rate in the left than right hemisphere. No sex differences in the maturation of the P2m responses were observed. Finally, an earlier left than right hemisphere P2m latency predicted better language performance in older infants (12 to 24 months). Findings indicate the need to consider hemisphere when examining the maturation of auditory cortex neural activity in infants and toddlers and show that the pattern of left–right hemisphere P2m maturation is associated with language performance.

EAAI Journal 2023 Journal Article

Reinforcement learning for energy efficiency improvement in UAV-BS access networks: A knowledge transfer scheme

• Zhiqun Hu
• Yujing Zhang
• Hao Huang
• Xiangming Wen
• Obinna Agbodike
• Jenhui Chen

Recently the possibility of forming unmanned aerial vehicle base station (UAV-BS) network systems with energy harvesting capabilities to support persistent wireless access services for pedestrian users has been validated. Due to the need of sustaining wireless access services of the UAV-BSs, we investigate an optimal policy to maximize the overall energy utilization efficiency (renewable energy) of the UAV-BSs during their active in-flight network access operations. Since the natural sources of renewable energy (e. g. , solar energy or wind energy harvesting) have stochastic properties with respect to the arrival rate of the dynamics of the unknown environment, we exploit an actor–critic reinforcement learning framework, which considers the continuous-valued states and action space for learning the best policy during interaction with the environment. To enhance and expedite the learning process, a transfer asynchronous advantage actor–critic (TA3C) algorithm is proposed, which enables UAV-BSs to transfer (i. e. , share) knowledge gained in historical periods, during parallel task asynchronous executions on multiple instances of the environment. Numerical results reveal that the proposed TA3C algorithm surpasses the classic A3C and A2C algorithms in terms of throughput and optimal energy utilization efficiency.

EAAI Journal 2023 Journal Article

Train a central traffic prediction model using local data: A spatio-temporal network based on federated learning

• Hao Huang
• Zhiqun Hu
• Yueting Wang
• Zhaoming Lu
• Xiangming Wen
• Bin Fu

With the growing complexity of onboard sensors and the widespread deployment of road sensors, deep learning enables fine-grained traffic prediction using massive amounts of raw traffic data, which facilitates accurate analysis of traffic information in the Internet of Vehicles (IoV). However, most existing studies focus on using all the local data to jointly build a prediction model, facing severe challenges of data security and privacy concerns as well as substantial communication overhead. To address these challenges, in this paper, we propose the Spatial-Temporal Traffic Prediction Network based on federated learning (F-STTP-Net), which only updates the model parameters to the centralized server without any private data. Firstly, we design a sub-area division method, which divides the road network into sub-areas with different macroscopic fundamental diagram properties. Then, we propose a local training model for each sub-area, which uses the graph attention network (GAT) and the long short-term memory (LSTM) to capture the spatio-temporal dependence of the road network. The model uses the branch structure to predict the traffic volume of each intersection in the sub-area. Finally, the local models are aggregated based on federated learning to form a powerful central model, which bridges the constraints on global data sharing and privacy guarantee. We conduct experiments on the real-life dataset in Xuchang Lotus Lake 5G automated vehicles demonstration area to demonstrate that F-STTP-Net can achieve excellent prediction performance without the interaction of sub-area raw data. In addition, the proposed model has a strong generalization ability and can be quickly transferred to a new sub-area.

EAAI Journal 2022 Journal Article

A digital implantation system for Z-direction yarn of three-dimensional preform based on flexible oriented woven process

• Zitong Guo
• Hao Huang
• Zhongde Shan
• Jihua Huang
• Zhuojian Hou
• Wenfeng Li

The implantation of Z-direction yarn is crucial in the process of forming flexible oriented 3D woven preforms, but manual implantation of Z-direction yarn is both time-consuming and inefficient. In this study, the digital Z-direction yarn implantation process and device are developed. Firstly, in view of many targets, small diameter, and serious interference in the identification process of the guide sleeve, a modified YOLOv3 algorithm is proposed to improve the accuracy and speed of detection, completing the coarse identification of guide sleeve. Then, an algorithm with modified Hough transform is proposed to improve the accuracy and speed of circle detection of coarse identification guide sleeve. Finally, based on the 1. 2 mm diameter guide sleeve, a digital yarn replacement device was built to precisely replace the guide sleeve with replacement needles and implant the Z-direction yarn into the preform. The identification error of the guide sleeve is within 0. 31% and the error between the reconstructed coordinates and the actual coordinates is within 3. 08%. This study is crucial to the identification and positioning of small targets under complex working conditions and the development of digital forming of preform.

AAAI Conference 2022 Conference Paper

CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes

• Hao Huang
• Yongtao Wang
• Zhaoyu Chen
• Yuze Zhang
• Yuheng Li
• Zhi Tang
• Wei Chu
• Jingdong Chen

Malicious applications of deepfakes (i. e. , technologies generating target facial attributes or entire faces from facial images) have posed a huge threat to individuals’ reputation and security. To mitigate these threats, recent studies have proposed adversarial watermarks to combat deepfake models, leading them to generate distorted outputs. Despite achieving impressive results, these adversarial watermarks have low imagelevel and model-level transferability, meaning that they can protect only one facial image from one specific deepfake model. To address these issues, we propose a novel solution that can generate a Cross-Model Universal Adversarial Watermark (CMUA-Watermark), protecting a large number of facial images from multiple deepfake models. Specifically, we begin by proposing a cross-model universal attack pipeline that attacks multiple deepfake models iteratively. Then, we design a two-level perturbation fusion strategy to alleviate the conflict between the adversarial watermarks generated by different facial images and models. Moreover, we address the key problem in cross-model optimization with a heuristic approach to automatically find the suitable attack step sizes for different models, further weakening the model-level conflict. Finally, we introduce a more reasonable and comprehensive evaluation method to fully test the proposed method and compare it with existing ones. Extensive experimental results demonstrate that the proposed CMUA- Watermark can effectively distort the fake facial images generated by multiple deepfake models while achieving a better performance than existing methods. Our code is available at https: //github. com/VDIGPKU/CMUA-Watermark.

IJCAI Conference 2022 Conference Paper

Reconstructing Diffusion Networks from Incomplete Data

• Hao Huang
• Keqi Han
• Beicheng Xu
• Ting Gan

To reconstruct the topology of a diffusion network, existing approaches customarily demand not only eventual infection statuses of nodes, but also the exact times when infections occur. In real-world settings, such as the spread of epidemics, tracing the exact infection times is often infeasible; even obtaining the eventual infection statuses of all nodes is a challenging task. In this work, we study topology reconstruction of a diffusion network with incomplete observations of the node infection statuses. To this end, we iteratively infer the network topology based on observed infection statuses and estimated values for unobserved infection statuses by investigating the correlation of node infections, and learn the most probable probabilities of the infection propagations among nodes w. r. t. current inferred topology, as well as the corresponding probability distribution of each unobserved infection status, which in turn helps update the estimate of unobserved data. Extensive experimental results on both synthetic and real-world networks verify the effectiveness and efficiency of our approach.

AAAI Conference 2021 Conference Paper

Diffusion Network Inference from Partial Observations

• Ting Gan
• Keqi Han
• Hao Huang
• Shi Ying
• Yunjun Gao
• Zongpeng Li

To infer the structure of a diffusion network from observed diffusion results, existing approaches customarily assume that observed data are complete and contain the final infection status of each node, as well as precise timestamps of node infections. Due to high cost and uncertainties in the monitoring of node infections, exact timestamps are often unavailable in practice, and even the final infection statuses of nodes are sometimes missing. In this work, we study how to carry out diffusion network inference without infection timestamps, using only partial observations of the final infection statuses of nodes. To this end, we iteratively infer the structure of the target diffusion network with observed data and imputed values for missing data, and learn the most likely infection transmission probabilities between nodes w. r. t. current inferred structure, which then help us update the imputation of missing data in turn. Extensive experimental results on both synthetic and real-world networks show that our approach can properly handle missing data and accurately uncover diffusion network structures.

AIIM Journal 2020 Journal Article

Regularized-Ncut: Robust and homogeneous functional parcellation of neonate and adult brain networks

• Qinmu Peng
• Minhui Ouyang
• Jiaojian Wang
• Qinlin Yu
• Chenying Zhao
• Michelle Slinger
• Hongming Li
• Yong Fan

Brain network parcellation based on resting-state functional MRI (rs-fMRI) is affected by noise, resulting in spurious small patches and decreased functional homogeneity within each network. Obtaining robust and homogeneous parcellation of neonate brain is more difficult, because neonate rs-fMRI is associated with relatively higher level of noise and no prior knowledge from a functional neonate atlas is available as spatial constraints. To meet these challenges, we developed a novel data-driven Regularized Normalized-cut (RNcut) method. RNcut is formulated by adding two regularization terms, a smoothing term using Markov random fields and a small-patch removal term, to conventional normalized-cut (Ncut) method. The RNcut and competing methods were tested with simulated datasets with known ground truth and then applied to both adult and neonate rs-fMRI datasets. Based on the parcellated networks generated by RNcut, intra-network connectivity was quantified. The test results from simulated datasets demonstrated that the RNcut method is more robust (p < 0. 01) to noise and can delineate parcellated functional networks with significantly better (p < 0. 01) spatial contiguity and significantly higher (p < 0. 01) functional homogeneity than competing methods. Application of RNcut to neonate and adult rs-fMRI dataset revealed distinctive functional brain organization of neonate brains from that of adult brains. Collectively, we developed a novel data-driven RNcut method by integrating conventional Ncut with two regularization terms, generating robust and homogeneous functional parcellation without imposing spatial constraints. A broad range of brain network applications and analyses, especially neonate and infant brain parcellation with noisy and large sample of datasets, can potentially benefit from this RNcut method.

YNIMG Journal 2019 Journal Article

Age-specific gray and white matter DTI atlas for human brain at 33, 36 and 39 postmenstrual weeks

• Lei Feng
• Hang Li
• Kenichi Oishi
• Virendra Mishra
• Limei Song
• Qinmu Peng
• Minhui Ouyang
• Jiaojian Wang

During the 3rd trimester, dramatic structural changes take place in the human brain, underlying the neural circuit formation. The survival rate of premature infants has increased significantly in recent years. The large morphological differences of the preterm brain at 33 or 36 postmenstrual weeks (PMW) from the brain at 40PMW (full term) make it necessary to establish age-specific atlases for preterm brains. In this study, with high quality (1. 5 × 1. 5 × 1. 6 mm3 imaging resolution) diffusion tensor imaging (DTI) data obtained from 84 healthy preterm and term-born neonates, we established age-specific preterm and term-born brain templates and atlases at 33, 36 and 39PMW. Age-specific DTI templates include a single-subject template, a population-averaged template with linear transformation and a population-averaged template with nonlinear transformation. Each of the age-specific DTI atlases includes comprehensive labeling of 126 major gray matter (GM) and white matter (WM) structures, specifically 52 cerebral cortical structures, 40 cerebral WM structures, 22 brainstem and cerebellar structures and 12 subcortical GM structures. From 33 to 39 PMW, dramatic morphological changes of delineated individual neural structures such as ganglionic eminence and uncinate fasciculus were revealed. The evaluation based on measurements of Dice ratio and L1 error suggested reliable and reproducible automated labels from the age-matched atlases compared to labels from manual delineation. Applying these atlases to automatically and effectively delineate microstructural changes of major WM tracts during the 3rd trimester was demonstrated. The established age-specific DTI templates and atlases of 33, 36 and 39 PMW brains may be used for not only understanding normal functional and structural maturational processes but also detecting biomarkers of neural disorders in the preterm brains.

YNIMG Journal 2019 Journal Article

Baby brain atlases

• Kenichi Oishi
• Linda Chang
• Hao Huang

The baby brain is constantly changing due to its active neurodevelopment, and research into the baby brain is one of the frontiers in neuroscience. To help guide neuroscientists and clinicians in their investigation of this frontier, maps of the baby brain, which contain a priori knowledge about neurodevelopment and anatomy, are essential. “Brain atlas” in this review refers to a 3D-brain image with a set of reference labels, such as a parcellation map, as the anatomical reference that guides the mapping of the brain. Recent advancements in scanners, sequences, and motion control methodologies enable the creation of various types of high-resolution baby brain atlases. What is becoming clear is that one atlas is not sufficient to characterize the existing knowledge about the anatomical variations, disease-related anatomical alterations, and the variations in time-dependent changes. In this review, the types and roles of the human baby brain MRI atlases that are currently available are described and discussed, and future directions in the field of developmental neuroscience and its clinical applications are proposed. The potential use of disease-based atlases to characterize clinically relevant information, such as clinical labels, in addition to conventional anatomical labels, is also discussed.

YNIMG Journal 2019 Journal Article

Delineation of early brain development from fetuses to infants with diffusion MRI and beyond

• Minhui Ouyang
• Jessica Dubois
• Qinlin Yu
• Pratik Mukherjee
• Hao Huang

Dynamic macrostructural and microstructural changes take place from the mid-fetal stage to 2 years after birth. Delineating structural changes of the brain during early development provides new insights into the complicated processes of both typical development and the pathological mechanisms underlying various psychiatric and neurological disorders including autism, attention deficit hyperactivity disorder and schizophrenia. Decades of histological studies have identified strong spatial and functional maturation gradients in human brain gray and white matter. The recent improvements in magnetic resonance imaging (MRI) techniques, especially diffusion MRI (dMRI), relaxometry imaging, and magnetization transfer imaging (MTI) have provided unprecedented opportunities to non-invasively quantify and map the early developmental changes at whole brain and regional levels. Here, we review the recent advances in understanding early brain structural development during the second half of gestation and the first two postnatal years using modern MR techniques. Specifically, we review studies that delineate the emergence and microstructural maturation of white matter tracts, as well as dynamic mapping of inhomogeneous cortical microstructural organization unique to fetuses and infants. These imaging studies converge into maturational curves of MRI measurements that are distinctive across different white matter tracts and cortical regions. Furthermore, contemporary models offering biophysical interpretations of the dMRI-derived measurements are illustrated to infer the underlying microstructural changes. Collectively, this review summarizes findings that contribute to charting spatiotemporally heterogeneous gray and white matter structural development, offering MRI-based biomarkers of typical brain development and setting the stage for understanding aberrant brain development in neurodevelopmental disorders.

YNIMG Journal 2019 Journal Article

Imaging baby brain development

• Hao Huang
• Petra S. Huppi
• Yong He
• Jason Lerch

AAAI Conference 2019 Conference Paper

Learning Diffusions without Timestamps

• Hao Huang
• Qian Yan
• Ting Gan
• Di Niu
• Wei Lu
• Yunjun Gao

To learn the underlying parent-child influence relationships between nodes in a diffusion network, most existing approaches require timestamps that pinpoint the exact time when node infections occur in historical diffusion processes. In many real-world diffusion processes like the spread of epidemics, monitoring such infection temporal information is often expensive and difficult. In this work, we study how to carry out diffusion network inference without infection timestamps, using only the final infection statuses of nodes in each historical diffusion process, which are more readily accessible in practice. Our main result is a probabilistic model that can find for each node an appropriate number of most probable parent nodes, who are most likely to have generated the historical infection results of the node. Extensive experiments on both synthetic and real-world networks are conducted, and the results verify the effectiveness and efficiency of our approach.

YNIMG Journal 2019 Journal Article

Structural network maturation of the preterm human brain

• Tengda Zhao
• Virendra Mishra
• Tina Jeon
• Minhui Ouyang
• Qinmu Peng
• Lina Chalak
• Jessica Lee Wisnowski
• Roy Heyne

During the 3rd trimester, large-scale neural circuits are formed in the human brain, resulting in a highly efficient and segregated connectome at birth. Despite recent findings identifying important preterm human brain network properties such as rich-club organization, how the structural network develops differentially across brain regions and among different types of connections in this period is not yet known. Here, using high resolution diffusion MRI of 77 preterm-born and full-term neonates scanned at 31. 9–41. 7 postmenstrual weeks (PMW), we constructed structural connectivity matrices and performed graph-theory-based analyses. Faster increases of nodal efficiency were mainly located at the brain hubs distributed in primary sensorimotor regions, superior-middle frontal, and precuneus regions during 31. 9–41. 7PMW. Higher rates of edge strength increases were found in the rich-club and within-module connections, compared to other connections. The edge strength of short-range connections increased faster than that of long-range connections. Nodal efficiencies of the hubs predicted individual postmenstrual ages more accurately than those of non-hubs. Collectively, these findings revealed more rapid efficiency increases of the hub and rich-club connections as well as higher developmental rates of edge strength in short-range and within-module connections. These jointly underlie network segregation and differentiated emergence of brain functions.

AAAI Conference 2018 Conference Paper

Directional Label Rectification in Adaptive Graph

• Xiaoqian Wang
• Hao Huang

With the explosive growth of multivariate time-series data, failure (event) analysis has gained widespread applications. A primary goal for failure analysis is to identify the fault signature, i. e. , the unique feature pattern to distinguish failure events. However, the complex nature of multivariate timeseries data brings challenge in the detection of fault signature. Given a time series from a failure event, the fault signature and the onset of failure are not necessarily adjacent, and the interval between the signature and failure is usually unknown. The uncertainty of such interval causes the uncertainty in labeling timestamps, thus makes it inapplicable to directly employ any standard supervised algorithms in signature detection. To address this problem, we present a novel directional label rectification model which identifies the faultrelevant timestamps and features in a simultaneous approach. Different from previous graph-based label propagation models using fixed graph, we propose to learn an adaptive graph which is optimal for the label rectification process. We conduct extensive experiments on both synthetic and real world datasets and illustrate the advantage of our model in both effectiveness and efficiency.

YNIMG Journal 2017 Journal Article

Heterogeneous increases of regional cerebral blood flow during preterm brain development: Preliminary assessment with pseudo-continuous arterial spin labeled perfusion MRI

• Minhui Ouyang
• Peiying Liu
• Tina Jeon
• Lina Chalak
• Roy Heyne
• Nancy K. Rollins
• Daniel J. Licht
• John A. Detre

The human brain develops rapidly during 32-45 postmenstrual weeks (PMW), a critical stage characterized by dramatic increases of metabolic demand. The increasing metabolic demand can be inferred through measurements of regional cerebral blood flow (CBF), which might be coupled to regional metabolism in preterm brains. Arterial spin labeled (ASL) perfusion MRI is one of the few viable approaches for imaging regional CBF of preterm brains, but must be optimized for the extremely slow blood velocity unique in preterm brains. In this study, we explored the spatiotemporal CBF distribution in newborns scanned at the age of 32-45PMW using a pseudo-continuous ASL (pCASL) protocol adapted to slow blood flow in neonates. A total of 89 neonates were recruited. PCASL MRI was acquired from 34 normal newborns and phase contrast (PC) images from 19 newborns. Diffusion tensor images (DTI) were acquired from all 89 neonates for measuring cortical fractional anisotropy (FA), which characterizes cortical microstructure. Reproducible CBF measurements were obtained with the adjusted pCASL sequence. Global CBF measurement based on PC MRI was found to double its value in the 3rd trimester. Regional CBF increases were heterogeneous across the brain with a significantly higher rate of CBF increase in the frontal lobe and a lower rate of CBF increase in the occipital lobe. A significant correlation was found between frontal cortical CBF and cortical FA measurements (p<0. 01). Increasing CBF values observed in the frontal lobe corresponded to lower FA values, suggesting that dendritic arborization and synaptic formation might be associated with an elevated local CBF. These results offer a preliminary account of heterogeneous regional CBF increases in a vital early developmental period and may shed the light on underlying metabolic support for cortical microstructural changes during the developmental period of 32-45PMW. Preterm effects and limitations of pCASL techniques in newborns need to be carefully considered for interpretation these results.

YNIMG Journal 2012 Journal Article

Regional changes of cortical mean diffusivities with aging after correction of partial volume effects

• Tina Jeon
• Virendra Mishra
• Jinsoo Uh
• Myron Weiner
• Kimmo J. Hatanpaa
• Charles L. White
• Yan D. Zhao
• Hanzhang Lu

Accurately measuring the cortical mean diffusivity (MD) derived from diffusion tensor imaging (DTI) at the comprehensive lobe, gyral and voxel level of young, elderly healthy brains and those with Alzheimer's disease (AD) may provide insights on heterogeneous cortical microstructural changes caused by aging and AD. Due to partial volume effects (PVE), the measurement of cortical MD is overestimated with contamination of cerebrospinal fluid (CSF). The bias is especially severe for aging and AD brains because of significant cortical thinning of these brains. In this study, we aimed to quantitatively characterize the unbiased regional cortical MD changes due to aging and AD and delineate the effects of cortical thinning of elderly healthy and AD groups on MD measurements. DTI and T1-weighted images of 14 young, 15 elderly healthy subjects and 17 AD patients were acquired. With the parcellated cortical gyri and lobes from T1 weighted image transformed to DTI, regional cortical MD of all subjects before and after PVE correction were measured. CSF contamination model was used to correct bias of MD caused by PVE. Compared to cortical MD of young group, significant increases of corrected MD for elderly healthy and AD groups were found only in frontal and limbic regions, respectively, while there were significant increases of uncorrected MD all over the cortex. Uncorrected MD are significantly higher in limbic and temporal gyri in AD group, compared to those in elderly healthy group but higher MD only remained in limbic gyri after PVE correction. Cortical thickness was also measured for all groups. The correlation slopes between cortical MD and thickness for elderly healthy and AD groups were significantly decreased after PVE correction compared to before correction while no significant change of correlation slope was detected for young group. It suggests that the cortical thinning in elderly healthy and AD groups is a significant contributor to the bias of uncorrected cortical MD measurement. The established comprehensive unbiased cortical MD profiles of young, elderly healthy subjects and AD patients at the lobe, gyral and voxel level may serve as clinical references for cortical microstructure.

YNIMG Journal 2011 Journal Article

White matter cerebral blood flow is inversely correlated with structural and functional connectivity in the human brain

• Sina Aslan
• Hao Huang
• Jinsoo Uh
• Virendra Mishra
• Guanghua Xiao
• Matthias J.P. van Osch
• Hanzhang Lu

White matter provides anatomic connections among brain regions and has received increasing attention in understanding brain intrinsic networks and neurological disorders. Despite significant progresses made in characterizing the white matter's structural properties using post-mortem techniques and in vivo diffusion-tensor-imaging (DTI) methods, its physiology remains poorly understood. In the present study, cerebral blood flow (CBF) of the white matter was investigated on a fiber tract-specific basis using MRI (n =10, 25–33years old). It was found that CBF in the white matter varied considerably, up to a factor of two between fiber groups. Furthermore, a paradoxically inverse correlation was observed between white matter CBF and structural and functional connectivities (P <0. 001). Fiber tracts that had a higher CBF tended to have a lower fractional anisotropy in water diffusion, and the gray matter terminals connected to the tract also tended to have a lower temporal synchrony in resting-state BOLD signal fluctuation. These findings suggest a clear association between white matter perfusion and gray matter activity, but the nature of this relationship requires further investigations given that they are negatively, rather than positively, correlated.

YNIMG Journal 2008 Journal Article

Human brain white matter atlas: Identification and assignment of common anatomical structures in superficial white matter

• Kenichi Oishi
• Karl Zilles
• Katrin Amunts
• Andreia Faria
• Hangyi Jiang
• Xin Li
• Kazi Akhter
• Kegang Hua

Structural delineation and assignment are the fundamental steps in understanding the anatomy of the human brain. The white matter has been structurally defined in the past only at its core regions (deep white matter). However, the most peripheral white matter areas, which are interleaved between the cortex and the deep white matter, have lacked clear anatomical definitions and parcellations. We used axonal fiber alignment information from diffusion tensor imaging (DTI) to delineate the peripheral white matter, and investigated its relationship with the cortex and the deep white matter. Using DTI data from 81 healthy subjects, we identified nine common, blade-like anatomical regions, which were further parcellated into 21 subregions based on the cortical anatomy. Four short association fiber tracts connecting adjacent gyri (U-fibers) were also identified reproducibly among the healthy population. We anticipate that this atlas will be useful resource for atlas-based white matter anatomical studies.

YNIMG Journal 2008 Journal Article

Stereotaxic white matter atlas based on diffusion tensor imaging in an ICBM template

• Susumu Mori
• Kenichi Oishi
• Hangyi Jiang
• Li Jiang
• Xin Li
• Kazi Akhter
• Kegang Hua
• Andreia V. Faria

Brain registration to a stereotaxic atlas is an effective way to report anatomic locations of interest and to perform anatomic quantification. However, existing stereotaxic atlases lack comprehensive coordinate information about white matter structures. In this paper, white matter-specific atlases in stereotaxic coordinates are introduced. As a reference template, the widely used ICBM-152 was used. The atlas contains fiber orientation maps and hand-segmented white matter parcellation maps based on diffusion tensor imaging (DTI). Registration accuracy by linear and non-linear transformation was measured, and automated template-based white matter parcellation was tested. The results showed a high correlation between the manual ROI-based and the automated approaches for normal adult populations. The atlases are freely available and believed to be a useful resource as a target template and for automated parcellation methods.

YNIMG Journal 2007 Journal Article

Evidence of slow maturation of the superior longitudinal fasciculus in early childhood by diffusion tensor imaging

• Jiangyang Zhang
• Alan Evans
• Laurent Hermoye
• Seung-Koo Lee
• Setsu Wakana
• Weihong Zhang
• Pamela Donohue
• Michael I. Miller

While the majority of axonal organization is established by birth in mammalian brains, axonal wiring and pruning processes, as well as myelination, are known to extend to the postnatal periods, where environmental stimuli often play a major role. Normal axonal and myelin development of individual white matter tracts of human in this period is poorly understood and may have a major role in cognitive development of human. In this study, we applied diffusion tensor imaging and normalization-based population analyses to 44 preteen children and 30 adult images. We observed highly significant changes of fiber orientations at regions that correspond to the superior longitudinal fasciculus during the first 5 years. The result is attributed to slow axonal and/or myelin maturation of this tract, which is believed to be involved in language functions.

YNIMG Journal 2006 Journal Article

White and gray matter development in human fetal, newborn and pediatric brains

• Hao Huang
• Jiangyang Zhang
• Setsu Wakana
• Weihong Zhang
• Tianbo Ren
• Linda J. Richards
• Paul Yarowsky
• Pamela Donohue

Brain anatomy is characterized by dramatic growth from the end of the second trimester through the neonatal stage. The characterization of normal axonal growth of the white matter tracts has not been well-documented to date and could provide important clues to understanding the extensive inhomogeneity of white matter injuries in cerebral palsy (CP) patients. However, anatomical studies of human brain development during this period are surprisingly scarce and histology-based atlases have become available only recently. Diffusion tensor magnetic resonance imaging (DTMRI) can reveal detailed anatomy of white matter. We acquired diffusion tensor images (DTI) of postmortem fetal brain samples and in vivo neonates and children. Neural structures were annotated in two-dimensional (2D) slices, segmented, measured, and reconstructed three-dimensionally (3D). The growth status of various white matter tracts was evaluated on cross-sections at 19–20 gestational weeks, and compared with 0-month-old neonates and 5- to 6-year-old children. Limbic, commissural, association, and projection white matter tracts and gray matter structures were illustrated in 3D and quantitatively characterized to assess their dynamic changes. The overall pattern of the time courses for the development of different white matter is that limbic fibers develop first and association fibers last and commissural and projection fibers are forming from anterior to posterior part of the brain. The resultant DTMRI-based 3D human brain data will be a valuable resource for human brain developmental study and will provide reference standards for diagnostic radiology of premature newborns.

YNIMG Journal 2005 Journal Article

DTI tractography based parcellation of white matter: Application to the mid-sagittal morphology of corpus callosum

• Hao Huang
• Jiangyang Zhang
• Hangyi Jiang
• Setsu Wakana
• Lidia Poetscher
• Michael I. Miller
• Peter CM. van Zijl
• Argye E. Hillis

Morphology of the corpus callosum (CC) at the mid-sagittal level has been a target of extensive studies. However, the lack of internal structures and its polymorphism make it a challenging task to quantitatively analyze shape differences among subjects. In this paper, diffusion tensor Imaging (DTI) and tract tracing technique were applied to incorporate cortical connectivity information to the morphological study. The CC was parcellated into six major subdivisions based on trajectories to different cortical areas. This subdivision was performed for eight normal subjects and one stroke patient. The parcellated CCs of the normal subjects were normalized for morphological analysis. When comparing the stroke patient to the normal population, we detected significant atrophy in the motor and sensory areas of the patient CC, in line with the clinical deficits. This approach provides a new tool to investigate callosal morphology and functional relationships.

YNIMG Journal 2003 Journal Article

Three-dimensional anatomical characterization of the developing mouse brain by diffusion tensor microimaging

• Jiangyang Zhang
• Linda J Richards
• Paul Yarowsky
• Hao Huang
• Peter C.M van Zijl
• Susumu Mori

Investigation of three-dimensional (3D) morphometry of developing brains has been hindered by a lack of imaging modalities that can monitor the 3D evolution of various anatomical structures without sectioning and staining processes. In this study, we combined magnetic resonance microimaging and diffusion tensor imaging techniques to accomplish such visualization. The application of this approach to developing mouse embryos revealed that it could clearly delineate early critical structures such as neuroepithelium, cortical plate, and various axonal structures, and follow their developmental evolution. The technique was applied to the study of the Netrin-1 mutant, allowing verification of its anatomical phenotype.