Author name cluster

Bin He

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

30 papers

2 author rows

EAAI Journal 2025 Journal Article

A fast recognition framework for identifying damage levels in rotating and small target solar greenhouse under complex scenarios

Jinhao Zhang
Danni Jia
Bin He
Wenwen Li
Xinyue Ren
Cailong Cheng
Quan Fan

Rapid identification, localization, and accurate counting are essential to prevent the abandonment of agricultural infrastructure like solar greenhouses, thereby avoiding the waste of agricultural land resources. However, detection difficulties include limited feature information from rotating small-target greenhouses, complex background environments, and inaccurate quantification of errors between predicted and actual rotating frames. To address these challenges, this study introduces an innovative framework for accurately locating and counting greenhouses with various damage levels, particularly suited for complex scenarios with multiple damage levels. Solar greenhouses are classified based on quantitative damage indicators, utilizing existing post-disaster building classification criteria from vertical remote sensing imagery. The proposed model utilizes MobileNetV3 as the backbone feature extraction network to reduce model parameters and maintain a lightweight structure. The lightweight operator and rotation target enhancement module are integrated into the head and neck layers of the network to form the Carafe-EVCBlock (CE) module, ultimately improving the loss function to enhance the feature representation and detection accuracy of rotation targets. Comprehensive experimental investigations and performance comparisons validate the superiority of this framework for detecting small, rotating greenhouse targets in dense scenarios. Furthermore, a PyQt5-based visualization system was developed for real-time detection and display of remote sensing images, demonstrating high accuracy in detecting and classifying damage levels in solar greenhouses.

AAAI Conference 2025 Conference Paper

Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems

Zhuohui Zhang
Bin He
Bin Cheng
Gang Li

Multi-agent systems must learn to communicate and understand interactions between agents to achieve cooperative goals in partially observed tasks. However, existing approaches lack a dynamic directed communication mechanism and rely on global states, thus diminishing the role of communication in centralized training. Thus, we propose the Transformer-based graph coarsening network (TGCNet), a novel multi-agent reinforcement learning (MARL) algorithm. TGCNet learns the topological structure of a dynamic directed graph to represent the communication policy and integrates graph coarsening networks to approximate the representation of global state during training. It also utilizes the Transformer decoder for feature extraction during execution. Experiments on multiple cooperative MARL benchmarks demonstrate state-of-the-art performance compared to popular MARL algorithms. Further ablation studies validate the effectiveness of our dynamic directed graph communication mechanism and graph coarsening networks.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Imagine: Image-Guided 3D Part Assembly with Structure Knowledge Graph

Weihao Wang
Yu Lan
Mingyu You
Bin He

3D part assembly is a promising task in 3D computer vision and robotics, focusing on assembling 3D parts together by predicting their 6-DoF poses. Like most 3D shape understanding tasks, existing methods primarily address this task by memorizing the poses of parts during the training process, leading to inaccuracies in complex assemblies and poor generalization to novel categories. In order to essentially improve the performance, structure knowledge of the target assembly is indispensable before assembling, which abstracts the potential part composition and their structural relationships. An image of the target assembly can serve as a common source for constructing this structure knowledge. Nevertheless, the image is far from enough, as its knowledge can be incomplete and ambiguous due to part occlusion and varying views. To tackle these issues, we propose Imagine, a novel Image-guided 3D part assembly framework with structure knowledge graph. As a novel assembly prior, the structure knowledge graph originates from the image and is refined as understanding the 3D parts. It encodes robust part-aware structural and semantic information of the assembly, guides the 3D parts from a coarse super-structure to a fine assembly, and co-evolves progressively throughout the assembly process. Extensive experiments demonstrate the state-of-the-art performance of our framework, along with strong generalization to novel images and categories.

PDF Details DOI

YNIMG Journal 2025 Journal Article

Investigating the neurovascular coupling across multiple motor execution and imagery conditions: a whole-brain EEG-informed fMRI analysis

Elena Bondi
Yidan Ding
Yisha Zhang
Eleonora Maggioni
Bin He

The complementary strengths of electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) have driven extensive research into integrating these two noninvasive modalities to better understand the neural mechanisms underlying cognitive, sensory, and motor functions. However, the precise neural patterns associated with motor functions, especially imagined movements, remain unclear. Specifically, the correlations between electrophysiological responses and hemodynamic activations during executed and imagined movements have not been fully elucidated at a whole-brain level. In this study, we employed a unified EEG-informed fMRI approach on concurrent EEG-fMRI data to map hemodynamic changes associated with dynamic EEG temporal features during motor-related brain activities. We localized and differentiated the hemodynamic activations corresponding to continuous EEG temporal dynamics across multiple motor execution and imagery tasks. Validation against conventional block fMRI analysis demonstrated high precision in identifying regions specific to motor activities, underscoring the accuracy of the EEG-driven model. Beyond the expected sensorimotor activations, the integrated analysis revealed supplementary coactivated regions showing significant negative covariation between blood oxygenation level-dependent (BOLD) activities and sensorimotor EEG alpha power, including the cerebellum, frontal, and temporal regions. These findings confirmed both the colocalization of EEG and fMRI activities in sensorimotor regions and a negative covariation between EEG alpha band power and BOLD changes. Moreover, the results provide novel insights into neurovascular coupling during motor execution and imagery on a brain-wide scale, advancing our understanding of the neural dynamics underlying motor functions.

IJCAI Conference 2025 Conference Paper

Rotation Invariant Spatial Networks for Single-View Point Cloud Classification

Feng Luan
Jiarui Hu
Changshi Zhou
Zhipeng Wang
Jiguang Yue
Yanmin Zhou
Bin He

Point cloud classification is critical for three-dimensional scene understanding. However, in real-world scenarios, depth cameras often capture partial, single-view point clouds of objects with different poses, making their accurate classification a challenge. In this paper, we propose a novel point cloud classification network that captures the detailed spatial structure of objects by constructing tetrahedra, which is different from point-wise operations. Specifically, we propose a RISpaNet block to extract rotation-invariant features. A rotation-invariant property generation module is designed in RISpaNet for constructing rotation-invariant tetrahedron properties (RITPs). Meanwhile, a multi-scale pooling module and a hybrid encoder are used to process RITPs to generate integrated rotation-invariant features. Further, for single-view point clouds, a complete point cloud auxiliary branch and a part-whole correlation module are jointly employed to obtain complete point cloud features from partial point clouds. Experimental results show that this network performs better than other state-of-the-art methods, evaluated on four public datasets. We achieved an overall accuracy of 94. 7% (+2. 0%) on ModelNet40, 93. 4% (+5. 9%) on MVP, 94. 7% (+6. 3%) on PCN and 94. 8% (+1. 7%) on ScanObjectNN. Our project website is https: //luxurylf. github. io/RISpaNet_project/.

PDF Details DOI

ICRA Conference 2024 Conference Paper

Ultrafast capturing in-flight objects with reprogrammable working speed ranges

Yongkang Jiang
Xin Tong
Zhongqing Sun
Yaimiin Zhou
Zhipeng Wang
Shuo Jiang
Zhen Yin
Yulong Ding

In-flight high-speed object capturing is crucial in nature to improve survival and adaptation to the environment, such as the predation of frogs, leopards, and eagles. Despite its ubiquitousness in nature, capturing fast-moving objects is extremely challenging in engineering implementations. In this paper, we report an ultrafast gripper based on tunable bistable structures. Different from current designs which are only suitable for objects with certain speed ranges once the grippers are fabricated, the working range of object speed of the proposed gripper could be reprogrammed by controlling the sensitivity of the structures. We present the design and fabrication of the proposed gripper in detail. A theoretical model is introduced to construct the energy landscape of the structures and the force response of the gripper when programmed to different states. The results show that in the original state, the gripper is capable of capturing a flying table tennis ball with a high speed of 15 m/s in only 6 ms. When the proposed gripper is controlled to the ultra-sensitive state, a flying ball with only 1 m/s could also be captured. This work broadens the frontiers of in-flight capturing design, and we envision broader promising applications.

AAAI Conference 2023 Conference Paper

3D Assembly Completion

Weihao Wang
Rufeng Zhang
Mingyu You
Hongjun Zhou
Bin He

Automatic assembly is a promising research topic in 3D computer vision and robotics. Existing works focus on generating assembly (e.g., IKEA furniture) from scratch with a set of parts, namely 3D part assembly. In practice, there are higher demands for the robot to take over and finish an incomplete assembly (e.g., a half-assembled IKEA furniture) with an off-the-shelf toolkit, especially in human-robot and multi-agent collaborations. Compared to 3D part assembly, it is more complicated in nature and remains unexplored yet. The robot must understand the incomplete structure, infer what parts are missing, single out the correct parts from the toolkit and finally, assemble them with appropriate poses to finish the incomplete assembly. Geometrically similar parts in the toolkit can interfere, and this problem will be exacerbated with more missing parts. To tackle this issue, we propose a novel task called 3D assembly completion. Given an incomplete assembly, it aims to find its missing parts from a toolkit and predict the 6-DoF poses to make the assembly complete. To this end, we propose FiT, a framework for Finishing the incomplete 3D assembly with Transformer. We employ the encoder to model the incomplete assembly into memories. Candidate parts interact with memories in a memory-query paradigm for final candidate classification and pose prediction. Bipartite part matching and symmetric transformation consistency are embedded to refine the completion. For reasonable evaluation and further reference, we design two standard toolkits of different difficulty, containing different compositions of candidate parts. We conduct extensive comparisons with several baseline methods and ablation studies, demonstrating the effectiveness of the proposed method.

PDF Details DOI

ICRA Conference 2023 Conference Paper

Continuous-Time LiDAR-Inertial-Vehicle Odometry Method with Lateral Acceleration Constraint

Bin He
Weichen Dai 0001
Zeyu Wan
Hong Zhang
Yu Zhang 0018

In this paper, we propose a continuous-time-based LiDAR-inertial-vehicle odometry method, which can tightly fuse the data from Light Detection And Ranging (LiDAR), inertial measurement units (IMU), and vehicle measurements. The lateral acceleration constraint is further added to trajectory estimation to make the estimated trajectory follow the motion characteristics of vehicles. In addition, since vehicle model parameters vary with different motion conditions and tyre pressure, we estimate vehicle correction factors that rectify changes in vehicle model parameters online, and also analyze the observability of these vehicle correction factors. In experiments, the proposed method is evaluated and compared with state-of-the-art methods in the public dataset. The experimental results show that the proposed method achieves more accurate results in all sequences since we add additional sensor measurements and utilize the characteristic of vehicle motion to restrict the trajectory estimation. The ablation study also proved the effectiveness of continuous-time representation, online correction factor estimation, and incorporation of lateral acceleration constraint.

YNIMG Journal 2023 Journal Article

Deep learning based source imaging provides strong sublobar localization of epileptogenic zone from MEG interictal spikes

Rui Sun
Wenbo Zhang
Anto Bagić
Bin He

Electromagnetic source imaging (ESI) offers unique capability of imaging brain dynamics for studying brain functions and aiding the clinical management of brain disorders. Challenges exist in ESI due to the ill-posedness of the inverse problem and thus the need of modeling the underlying brain dynamics for regularizations. Advances in generative models provide opportunities for more accurate and realistic source modeling that could offer an alternative approach to ESI for modeling the underlying brain dynamics beyond equivalent physical source models. However, it is not straightforward to explicitly formulate the knowledge arising from these generative models within the conventional ESI framework. Here we investigate a novel source imaging framework based on mesoscale neuronal modeling and deep learning (DL) that can learn the sensor-source mapping relationship directly from MEG data for ESI. Two DL-based ESI models were trained based on data generated by neural mass models and either generic or personalized head models. The robustness of the two DL models was evaluated by systematic computer simulations and clinical validation in a cohort of 29 drug-resistant focal epilepsy patients who underwent intracranial EEG (iEEG) evaluation or surgical resection. Results estimated from pre-operative MEG interictal spikes were quantified using the overlap with resection regions and the distance to the seizure-onset zone (SOZ) defined by iEEG recordings. The DL-based ESI provided robust results when no personalized head geometry is considered, reaching a spatial dispersion of 21.90 ± 19.03 mm, sublobar concordance of 83 %, and sublobar sensitivity and specificity of 66 and 97 % respectively. When using personalized head geometry derived from individual patients' MRI in the training data, personalized DL-based ESI model can further improve the performance and reached a spatial dispersion of 8.19 ± 8.14 mm, sublobar concordance of 93 %, and sublobar sensitivity and specificity of 77 and 99 % respectively. When compared to the SOZ, the localization error of the personalized approach is 15.78 ± 5.54 mm, outperforming the conventional benchmarks. This work demonstrates that combining generative models and deep learning enables an accurate and robust imaging of epileptogenic zone from MEG recordings with strong sublobar precision, suggesting its added value to enhancing MEG source localization and imaging, and to epilepsy source localization and other clinical applications.

EAAI Journal 2023 Journal Article

GTRF: A general deep learning framework for tuples recognition towards supervised, semi-supervised and unsupervised paradigms

Qingsong Xiong
Cheng Yuan
Bin He
Haibei Xiong
Qingzhao Kong

Tuple, featured as sequences of elements are regarded as one of the most predominant data forms in structural health monitoring (SHM). Activated by powerful capabilities of deep learning (DL) techniques, the DL-driven tuple recognition regime has facilitated plenty of problems settlement in SHM practice by mapping tuples with structural patterns, whereas the determined feature extraction strategies, designated network architectures and specified learning schemas (i. e. , supervision paradigms) degrade severely to the model’s transferability and generalizability. Thereby, this study devises a novel General Tuple Recognition Framework (GTRF) towards supervised (SL), unsupervised (UL) and semi-supervised learning (SSL) paradigms. In the framework, pattern-sensitive features (PSFs) are quantitatively defined via a novel feature extractor intervened by deep autoencoder for downstream label propagation via an optimized fuzzy clustering algorithm in SL, UL and SSL paradigms. With sophisticated networks integrated and exquisite novelties embedded, the proposed GTRF is competent for various tuple recognition tasks in diverse learning paradigms regardless of the measurement types or lengths. Multi-level experimental tasks implementation representative in SHM scope were conducted for validations, varying in vibration SL-recognition of a prototype skyscraper, damage UL-detection of a laboratory RC beam and condition SSL-assessment of a full-scale building model. The results comprehensively confirmed the effectiveness and generality of proposed GTRF as well as comparable superiority in recognition accuracy and model adaptability. With flexible paradigm specialization, broad application and great space for optimization, the proposed GTRF framework can promisingly be a prototype for bridging the gap for DL algorithms fusion and models integration of different learning paradigms.

YNICL Journal 2022 Journal Article

Imaging the extent and location of spatiotemporally distributed epileptiform sources from MEG measurements

Xiyuan Jiang
Shuai Ye
Abbas Sohrabpour
Anto Bagić
Bin He

Non-invasive MEG/EEG source imaging provides valuable information about the epileptogenic brain areas which can be used to aid presurgical planning in focal epilepsy patients suffering from drug-resistant seizures. However, the source extent estimation for electrophysiological source imaging remains to be a challenge and is usually largely dependent on subjective choice. Our recently developed algorithm, fast spatiotemporal iteratively reweighted edge sparsity minimization (FAST-IRES) strategy, has been shown to objectively estimate extended sources from EEG recording, while it has not been applied to MEG recordings. In this work, through extensive numerical experiments and real data analysis in a group of focal drug-resistant epilepsy patients' interictal spikes, we demonstrated the ability of FAST-IRES algorithm to image the location and extent of underlying epilepsy sources from MEG measurements. Our results indicate the merits of FAST-IRES in imaging the location and extent of epilepsy sources for pre-surgical evaluation from MEG measurements.

AIIM Journal 2019 Journal Article

Classifying medical relations in clinical text via convolutional neural networks

Bin He
Yi Guan
Rui Dai

Deep learning research on relation classification has achieved solid performance in the general domain. This study proposes a convolutional neural network (CNN) architecture with a multi-pooling operation for medical relation classification on clinical records and explores a loss function with a category-level constraint matrix. Experiments using the 2010 i2b2/VA relation corpus demonstrate these models, which do not depend on any external features, outperform previous single-model methods and our best model is competitive with the existing ensemble-based method.

YNICL Journal 2019 Journal Article

Graph theory analysis reveals how sickle cell disease impacts neural networks of patients with more severe disease

Michelle Case
Sina Shirinpour
Vishal Vijayakumar
Huishi Zhang
Yvonne Datta
Stephen Nelson
Paola Pergami
Deepika S. Darbari

Sickle cell disease (SCD) is a hereditary blood disorder associated with many life-threatening comorbidities including cerebral stroke and chronic pain. The long-term effects of this disease may therefore affect the global brain network which is not clearly understood. We performed graph theory analysis of functional networks using non-invasive fMRI and high resolution EEG on thirty-one SCD patients and sixteen healthy controls. Resting state data were analyzed to determine differences between controls and patients with less severe and more severe sickle cell related pain. fMRI results showed that patients with higher pain severity had lower clustering coefficients and local efficiency. The neural network of the more severe patient group behaved like a random network when performing a targeted attack network analysis. EEG results showed the beta1 band had similar results to fMRI resting state data. Our data show that SCD affects the brain on a global level and that graph theory analysis can differentiate between patients with different levels of pain severity.

AIIM Journal 2018 Journal Article

EMR-based medical knowledge representation and inference via Markov random fields and distributed representation learning

Chao Zhao
Jingchi Jiang
Yi Guan
Xitong Guo
Bin He

Objective Electronic medical records (EMRs) contain medical knowledge that can be used for clinical decision support (CDS). Our objective is to develop a general system that can extract and represent knowledge contained in EMRs to support three CDS tasks—test recommendation, initial diagnosis, and treatment plan recommendation—given the condition of a patient. Methods We extracted four kinds of medical entities from records and constructed an EMR-based medical knowledge network (EMKN), in which nodes are entities and edges reflect their co-occurrence in a record. Three bipartite subgraphs (bigraphs) were extracted from the EMKN, one to support each task. One part of the bigraph was the given condition (e. g. , symptoms), and the other was the condition to be inferred (e. g. , diseases). Each bigraph was regarded as a Markov random field (MRF) to support the inference. We proposed three graph-based energy functions and three likelihood-based energy functions. Two of these functions are based on knowledge representation learning and can provide distributed representations of medical entities. Two EMR datasets and three metrics were utilized to evaluate the performance. Results As a whole, the evaluation results indicate that the proposed system outperformed the baseline methods. The distributed representation of medical entities does reflect similarity relationships with respect to knowledge level. Conclusion Combining EMKN and MRF is an effective approach for general medical knowledge representation and inference. Different tasks, however, require individually designed energy functions.

YNICL Journal 2017 Journal Article

Characterization of functional brain activity and connectivity using EEG and fMRI in patients with sickle cell disease

Michelle Case
Huishi Zhang
John Mundahl
Yvonne Datta
Stephen Nelson
Kalpna Gupta
Bin He

Sickle cell disease (SCD) is a red blood cell disorder that causes many complications including life-long pain. Treatment of pain remains challenging due to a poor understanding of the mechanisms and limitations to characterize and quantify pain. In the present study, we examined simultaneously recording functional MRI (fMRI) and electroencephalogram (EEG) to better understand neural connectivity as a consequence of chronic pain in SCD patients. We performed independent component analysis and seed-based connectivity on fMRI data. Spontaneous power and microstate analysis was performed on EEG-fMRI data. ICA analysis showed that patients lacked activity in the default mode network (DMN) and executive control network compared to controls. EEG-fMRI data revealed that the insula cortex's role in salience increases with age in patients. EEG microstate analysis showed patients had increased activity in pain processing regions. The cerebellum in patients showed a stronger connection to the periaqueductal gray matter (involved in pain inhibition), and negative connections to pain processing areas. These results suggest that patients have reduced activity of DMN and increased activity in pain processing regions during rest. The present findings suggest resting state connectivity differences between patients and controls can be used as novel biomarkers of SCD pain.

YNIMG Journal 2017 Journal Article

Deactivation in the posterior mid-cingulate cortex reflects perceptual transitions during binocular rivalry: Evidence from simultaneous EEG-fMRI

Abhrajeet V. Roy
Keith W. Jamison
Sheng He
Stephen A. Engel
Bin He

Binocular rivalry is a phenomenon in which perception spontaneously shifts between two different images that are dichoptically presented to the viewer. By elucidating the cortical networks responsible for these stochastic fluctuations in perception, we can potentially learn much about the neural correlates of visual awareness. We obtained concurrent EEG-fMRI data for a group of 20 healthy human subjects during the continuous presentation of dichoptic visual stimuli. The two eyes’ images were tagged with different temporal frequencies so that eye specific steady-state visual evoked potential (SSVEP) signals could be extracted from the EEG data for direct comparison with changes in fMRI BOLD activity associated with binocular rivalry. We additionally included a smooth replay condition that emulated the perceptual transitions experienced during binocular rivalry as a control stimulus. We evaluated a novel SSVEP-informed fMRI analysis in this study in order to delineate the temporal dynamics of rivalry-related BOLD activity from both an electrophysiological and behavioral perspective. In this manner, we assessed BOLD activity during rivalry that was directly correlated with peaks and crosses of the two rivaling, frequency-tagged SSVEP signals, for comparison with BOLD activity associated with subject reported perceptual transitions. Our findings point to a critical role of a right lateralized fronto-parietal network in the processing of bistable stimuli, given that BOLD activity in the right superior/inferior parietal lobules was significantly elevated throughout binocular rivalry and in particular during perceptual transitions, compared with the replay condition. Based on the SSVEP-informed analysis, rivalry was further associated with significantly enhanced BOLD suppression in the posterior mid-cingulate cortex during perceptual transitions, compared with SSVEP crosses. Overall, this work points to a careful interplay between early visual areas, the right posterior parietal cortex and the mid-cingulate cortex in mediating the spontaneous perceptual changes associated with binocular rivalry and has significant implications for future multimodal imaging studies of perception and awareness.

YNIMG Journal 2016 Journal Article

Imaging brain source extent from EEG/MEG by means of an iteratively reweighted edge sparsity minimization (IRES) strategy

Abbas Sohrabpour
Yunfeng Lu
Gregory Worrell
Bin He

Estimating extended brain sources using EEG/MEG source imaging techniques is challenging. EEG and MEG have excellent temporal resolution at millisecond scale but their spatial resolution is limited due to the volume conduction effect. We have exploited sparse signal processing techniques in this study to impose sparsity on the underlying source and its transformation in other domains (mathematical domains, like spatial gradient). Using an iterative reweighting strategy to penalize locations that are less likely to contain any source, it is shown that the proposed iteratively reweighted edge sparsity minimization (IRES) strategy can provide reasonable information regarding the location and extent of the underlying sources. This approach is unique in the sense that it estimates extended sources without the need of subjectively thresholding the solution. The performance of IRES was evaluated in a series of computer simulations. Different parameters such as source location and signal-to-noise ratio were varied and the estimated results were compared to the targets using metrics such as localization error (LE), area under curve (AUC) and overlap between the estimated and simulated sources. It is shown that IRES provides extended solutions which not only localize the source but also provide estimation for the source extent. The performance of IRES was further tested in epileptic patients undergoing intracranial EEG (iEEG) recording for pre-surgical evaluation. IRES was applied to scalp EEGs during interictal spikes, and results were compared with iEEG and surgical resection outcome in the patients. The pilot clinical study results are promising and demonstrate a good concordance between noninvasive IRES source estimation with iEEG and surgical resection outcomes in the same patients. The proposed algorithm, i. e. IRES, estimates extended source solutions from scalp electromagnetic signals which provide relatively accurate information about the location and extent of the underlying source.

YNICL Journal 2015 Journal Article

Thalamocortical relationship in epileptic patients with generalized spike and wave discharges — A multimodal neuroimaging study

Clara Huishi Zhang
Zhiyi Sha
John Mundahl
Sa Liu
Yunfeng Lu
Thomas R. Henry
Bin He

Unlike focal or partial epilepsy, which has a confined range of influence, idiopathic generalized epilepsy (IGE) often affects the whole or a larger portion of the brain without obvious, known cause. It is important to understand the underlying network which generates epileptic activity and through which epileptic activity propagates. The aim of the present study was to investigate the thalamocortical relationship using non-invasive imaging modalities in a group of IGE patients. We specifically investigated the roles of the mediodorsal nuclei in the thalami and the medial frontal cortex in generating and spreading IGE activities. We hypothesized that the connectivity between these two structures is key in understanding the generation and propagation of epileptic activity in brains affected by IGE. Using three imaging techniques of EEG, fMRI and EEG-informed fMRI, we identified important players in generation and propagation of generalized spike-and-wave discharges (GSWDs). EEG-informed fMRI suggested multiple regions including the medial frontal area near to the anterior cingulate cortex, mediodorsal nuclei of the thalamus, caudate nucleus among others that related to the GSWDs. The subsequent seed-based fMRI analysis revealed a reciprocal cortical and bi-thalamic functional connection. Through EEG-based Granger Causality analysis using (DTF) and adaptive DTF, within the reciprocal thalamocortical circuitry, thalamus seems to serve as a stronger source in driving cortical activity from initiation to the propagation of a GSWD. Such connectivity change starts before the GSWDs and continues till the end of the slow wave discharge. Thalamus, especially the mediodorsal nuclei, may serve as potential targets for deep brain stimulation to provide more effective treatment options for patients with drug-resistant generalized epilepsy.

AAAI Conference 2014 Conference Paper

Representing Words as Lymphocytes

Jinfeng Yang
Yi Guan
Xishuang Dong
Bin He

Similarity between words is becoming a generic problem for many applications of computational linguistics, and computing word similarities is determined by word representations. Inspired by the analogies between words and lymphocytes, a lymphocyte-style word representation is proposed. The word representation is built on the basis of dependency syntax of sentences and represent word context as head properties and dependent properties of the word. Lymphocyte-style word representations are evaluated by computing the similarities between words, and experiments are conducted on the Penn Chinese Treebank 5. 1. Experimental results indicate that the proposed word representations are effective.

YNIMG Journal 2011 Journal Article

Dynamic imaging of ictal oscillations using non-invasive high-resolution EEG

Lin Yang
Christopher Wilke
Benjamin Brinkmann
Gregory A. Worrell
Bin He

Scalp electroencephalography (EEG) has been established as a major component of the pre-surgical evaluation for epilepsy surgery. However, its ability to localize seizure onset zones (SOZ) has been significantly restricted by its low spatial resolution and indirect correlation with underlying brain activities. Here we report a novel non-invasive dynamic seizure imaging (DSI) approach based upon high-density EEG recordings. This novel approach was particularly designed to image the dynamic changes of ictal rhythmic discharges that evolve through time, space and frequency. This method was evaluated in a group of 8 epilepsy patients and results were rigorously validated using intracranial EEG (iEEG) (n=3) and surgical outcome (n=7). The DSI localized the ictal activity in concordance with surgically resected zones and ictal iEEG recordings in the cohort of patients. The present promising results support the ability to precisely and accurately image dynamic seizure activity from non-invasive measurements. The successful establishment of such a non-invasive seizure imaging modality for surgical evaluation will have a significant impact in the management of medically intractable epilepsy.

IS Journal 2011 Journal Article

Imaging the Social Brain by Simultaneous Hyperscanning during Subject Interaction

Laura Astolfi
Jlenia Toppi
Fabrizio De Vico Fallani
Giovanni Vecchiato
Febo Cincotti
Christopher Wilke
Han Yuan
Donatella Mattia

Advances in neuroelectric recordings and computational tools allow investigation of interactive brain activity and connectivity in a group of subjects engaged in social interactions.

YNIMG Journal 2011 Journal Article

Noninvasive cortical imaging of epileptiform activities from interictal spikes in pediatric patients

Yuan Lai
Xin Zhang
Wim van Drongelen
Michael Korhman
Kurt Hecox
Ying Ni
Bin He

Improved non-invasive localization of the epileptogenic foci prior to epilepsy surgery would improve surgical outcome in patients with partial seizure disorders. A critical component for the identification of the epileptogenic brain is the analysis of electrophysiological data obtained during ictal activity from prolonged intracranial recordings. The development of a noninvasive means to identify the seizure onset zone (SOZ) would thus play an important role in treating patients with intractable epilepsy. In the present study, we have investigated non-invasive imaging of epileptiform activity in patients with medically intractable epilepsy by means of a cortical potential imaging (CPI) technique. Eight pediatric patients (1M/7F, ages 4–14years) with intractable partial epilepsy were studied. Each patient had multiple (6 to 14) interictal spikes (IIS) subjected to the CPI analysis. Realistic geometry boundary element head models were built using each individual's MRI in order to maximize the imaging precision. CPI analysis was performed on the IISs, and extrema in the estimated CPI images were compared with SOZs as determined from the ictal electrocorticogram (ECoG) recordings, as well as the resected areas in the patients and surgical outcomes. The distances between the maximum cortical activities of the IISs reflected by the estimated cortical potential distributions and the SOZs were determined to quantitatively evaluate the performance of the CPI in localizing the epileptogenic zone. Ictal ECoG recordings revealed that six patients exhibited a single epileptogenic focus while two patients had multiple foci. In each patient, the CPI results revealed an area of activity overlapping with the SOZs as identified by ictal ECoG. The distance from the extreme of the CPI images at the peak of IIS to the nearest intracranial electrode associated with the onset of the ictal activity was evaluated for each patient and the averaged distance was 4. 6mm. In the group of patients studied, the CPI imaged epileptogenic foci were within the resected areas. According to the follow-up of the eight patients included, two were seizure free and six had substantial reduction in seizure frequency. These promising results demonstrate the potential for noninvasive localization of the epileptogenic focus from interictal scalp EEG recordings. Confirmation of our results may have a significant impact on the process of presurgical planning in pediatric patients with intractable epilepsy by dramatically reducing or potentially eliminating the use of intracranial recording.

YNIMG Journal 2010 Journal Article

Linear and nonlinear relationships between visual stimuli, EEG and BOLD fMRI signals

Zhongming Liu
Cristina Rios
Nanyin Zhang
Lin Yang
Wei Chen
Bin He

In the present study, the cascaded interactions between stimuli and neural and hemodynamic responses were modeled using linear systems. These models provided the theoretical hypotheses that were tested against the electroencephalography (EEG) and blood oxygen level dependent (BOLD) functional magnetic resonance imaging (fMRI) data recorded from human subjects during prolonged periods of repeated visual stimuli with a variable setting of the inter-stimulus interval (ISI) and visual contrast. Our results suggest that (1) neural response is nonlinear only when ISI<0. 2 s, (2) BOLD response is nonlinear with an exclusively vascular origin when 0. 25<ISI<4. 2 s, (3) vascular response nonlinearity reflects a refractory effect, rather than a ceiling effect, and (4) there is a strong linear relationship between the BOLD effect size and the integrated power of event-related synaptic current activity, after modeling and taking into account the vascular refractory effect. These conclusions offer important insights into the origins of BOLD nonlinearity and the nature of neurovascular coupling, and suggest an effective means to quantitatively interpret the BOLD signal in terms of neural activity. The validated cross-modal relationship between fMRI and EEG may provide a theoretical basis for the integration of these two modalities.

YNIMG Journal 2010 Journal Article

Negative covariation between task-related responses in alpha/beta-band activity and BOLD in human sensorimotor cortex: An EEG and fMRI study of motor imagery and movements

Han Yuan
Tao Liu
Rebecca Szarkowski
Cristina Rios
James Ashe
Bin He

Similar to the occipital alpha rhythm, electroencephalographic (EEG) signals in the alpha- and beta-frequency bands can be suppressed by movement or motor imagery and have thus been thought to represent the “idling state” of the sensorimotor cortex. A negative correlation between spontaneous alpha EEG and blood-oxygen-level-dependent (BOLD) signals has been reported in combined EEG and fMRI (functional Magnetic Resonance Imaging) experiments when subjects stayed at the resting state or alternated between the resting state and a task. However, the precise nature of the task-induced alpha modulation remains elusive. It was not clear whether alpha/beta rhythm suppressions may co-vary with BOLD when conducting tasks involving varying activations of the cortex. Here, we quantified the task-evoked responses of BOLD and alpha/beta-band power of EEG directly in the cortical source domain, by using source imaging technology, and examined their covariation across task conditions in a mixed block and event-related design. In this study, 13 subjects performed tasks of right-hand, right-foot or left-hand movement and motor imagery when EEG and fMRI data were separately collected. Task-induced increase of BOLD signal and decrease of EEG amplitudes in alpha and beta bands were shown to be co-localized at the somatotopic sensorimotor cortex. At the corresponding regions, the reciprocal changes of the two signals co-varied in the magnitudes across imagination and movement conditions. The spatial correspondence and negative covariation between the two measurements were further shown to exist at somatotopic brain regions associated with different body parts. These results suggest an inverse functional coupling relationship between task-induced changes of BOLD and low-frequency EEG signals.

YNIMG Journal 2009 Journal Article

Mapping the bilateral visual integration by EEG and fMRI

Zhongming Liu
Nanyin Zhang
Wei Chen
Bin He

In the human visual system, the internal representation of the left and right visual hemifields is split at the midline of the two cerebral hemispheres. The present study aims to address the questions of when and where the lateralized cortical visual representations are merged to form an intact percept by using a multimodal neuroimaging approach. Visual evoked potential (VEP) and functional magnetic resonance imaging (fMRI) data were acquired from a group of healthy subjects presented with unilateral versus bilateral visual stimuli. Cortical activities involved in processing bilateral visual information are expected to be equally responsive to ipsilateral and contralateral stimuli, and demonstrate spatial nonlinearity in the response to bilateral stimuli. Utilizing these features, we performed integrative as well as separate analyses for both VEP and fMRI data. The present results suggest that i) the majority of cortical activity that integrates visual information across hemifields takes place at extrastriate areas during late visual processing, and that ii) the lateral occipito-temporal (LOT) regions (likely the MT+ complex) and the medial occipital cortex (i. e. V1) may contribute to bilateral visual integration during early visual processing. Our findings are generally in agreement with the bottom-up visual hierarchy, with the exception of the evidence suggesting an early activation of the higher-tier LOT areas and the influence from ipsilateral visual inputs upon the V1 response.

YNIMG Journal 2008 Journal Article

fMRI–EEG integrated cortical source imaging by use of time-variant spatial constraints

Zhongming Liu
Bin He

In response to the need of establishing a high-resolution spatiotemporal neuroimaging technique, tremendous efforts have been focused on developing multimodal strategies that combine the complementary advantages of high-spatial-resolution functional magnetic resonance imaging (fMRI) and high-temporal-resolution electroencephalography (EEG) or magnetoencephalography (MEG). A critical challenge to the fMRI–EEG/MEG integration lies in the spatial mismatches between fMRI activations and instantaneous electrical source activities. Such mismatches are fundamentally due to the fact that fMRI and EEG/MEG signals are generated and collected in highly different time scales. In this paper, we propose a new theoretical framework to solve the problem of fMRI–EEG integrated cortical source imaging. The new framework has two principal technical advancements. First, by assuming a linear neurovascular coupling, a method is derived to quantify the fMRI signal in each voxel as proportional to the time integral of the power of local electrical current during the period of event-related potentials (ERP). Second, the EEG inverse problem is solved for every time instant using an adaptive Wiener filter, in which the prior time-variant source covariance matrix is estimated by combining the quantified fMRI responses and the segmented EEG signals before response averaging. A series of computer simulations were conducted to evaluate the proposed methods in terms of imaging the instantaneous cortical current density (CCD) distribution and estimating the source time courses with a millisecond temporal resolution. As shown in the simulation results, the instantaneous CCD reconstruction by using the proposed fMRI–EEG integration method was robust against both fMRI false positives and false negatives while retaining a spatial resolution nearly as high as that of fMRI. The proposed method could also reliably estimate the source waveforms when multiple sources were temporally correlated or uncorrelated, or were sustained or transient, or had some features in frequency or phase, or had even more complicated temporal dynamics. Moreover, applying the proposed method to real fMRI and EEG data acquired in a visual experiment yielded a time series of reconstructed CCD images, in agreement with the traditional view of hierarchical visual processing. In conclusion, the proposed method provides a reliable technique for the fMRI–EEG integration and represents a significant advancement over the conventional fMRI-weighted EEG (or MEG) source imaging techniques and is also applicable to the fMRI–MEG integrated source imaging.

YNIMG Journal 2008 Journal Article

Three-dimensional brain current source reconstruction from intra-cranial ECoG recordings

Yingchun Zhang
Wim van Drongelen
Michael Kohrman
Bin He

We have investigated 3-dimensional brain current density reconstruction (CDR) from intracranial electrocorticogram (ECoG) recordings by means of finite element method (FEM). The brain electrical sources are modeled by a current density distribution and estimated from the ECoG signals with the aid of a weighted minimum norm estimation algorithm. A series of computer simulations were conducted to evaluate the performance of ECoG-CDR by comparing with the scalp EEG based CDR results. The present computer simulation results indicate that the ECoG-CDR provides enhanced performance in localizing single dipole sources which are located in regions underneath the implanted subdural ECoG grids, and in distinguishing and imaging multiple separate dipole sources, in comparison to the CDR results as obtained from the scalp EEG under the same conditions. We have also demonstrated the applicability of the present ECoG-CDR method to estimate 3-dimensional current density distribution from the subdural ECoG recordings in a human epilepsy patient. Eleven interictal epileptiform spikes (seven from the frontal region and four from parietal region) in an epilepsy patient undergoing surgical evaluation were analyzed. The present promising results indicate the feasibility and applicability of the developed ECoG-CDR method of estimating brain sources from intracranial electrical recordings, with detailed forward modeling using FEM.

YNIMG Journal 2007 Journal Article

Evaluation of cortical current density imaging methods using intracranial electrocorticograms and functional MRI

Xiaoxiao Bai
Vernon L. Towle
Eric J. He
Bin He

Objective: EEG source imaging provides important information regarding the underlying neural activity from noninvasive electrophysiological measurements. The aim of the present study was to evaluate source reconstruction techniques by means of the intracranial electrocorticograms (ECoGs) and functional MRI. Methods: Five source imaging algorithms, including the minimum norm least square (MNLS), LORETA with L p -norm (p equal to 1, 1. 5 and 2), sLORETA, the minimum L p -norm (p equal to 1 and 1. 5; when p =2, the MNLS method is mathematically equivalent to the minimum L p -norm) and L 1-norm (the linear programming) methods, were evaluated in a group of 10 human subjects, in a paradigm with somatosensory stimulation. Cortical current density (CCD) distributions were estimated from the scalp somatosensory evoked potentials (SEPs), at approximately 30 ms following electrical stimulation of median nerve at the wrist. Realistic geometry boundary element head models were constructed from the MRIs of each subject and used in the CCD analysis. Functional MRI results obtained from a motor task and sensory stimulation in all subjects were used to identify the central sulcus, motor and sensory areas. In three patients undergoing neurosurgical evaluation, ECoGs were recorded in response to the somatosensory stimulation, and were used to help determine the central sulcus and the sensory cortex. Results: The CCD distributions estimated by the L p -norm and LORETA-L p methods were smoother when the p values were high. The LORETA based on the L 1-norm performed better than the LORETA-L 2 method for imaging well localized sources such as the P30 component of the SEP. The mean and standard deviation of the distance between the location of maximum CCD value and the central sulcus, estimated by the minimum L p -norm (with p equal to 1), L 1-norm (the Linear programming) and LORETA-L p (with p equal to 1) methods, were 4, 7, 7 mm and 3, 4, 2 mm, respectively (after converting into Talairach coordinates). The mean and standard deviation of the aforementioned distance, estimated by the MNLS, LORETA with L p -norm (p equal to 1. 5 and 2. 0), sLORETA and the minimum L p -norm (p equal to 1. 5) methods, were over 11 mm and 6 mm, respectively. Conclusions: The present experimental study suggests that L 1-norm-based algorithms provide better performance than L 2 and L 1. 5-norm-based algorithms, in the context of CCD imaging of well localized sources induced by somatosensory electrical stimulation of median nerve at the wrist.

YNIMG Journal 2007 Journal Article

Ictal source analysis: Localization and imaging of causal interactions in humans

Lei Ding
Gregory A. Worrell
Terrence D. Lagerlund
Bin He

We propose a new integrative approach to characterize the structure of seizures in the space, time, and frequency domains. Such characterization leads to a new technical development of ictal source analysis for the presurgical evaluation of epilepsy patients. The present new ictal source analysis method consists of three parts. First, a three-dimensional source scanning procedure is performed by a spatio-temporal FINE source localization method to locate the multiple sources responsible for the time evolving ictal rhythms at their onsets. Next, the dynamic behavior of the sources is modeled by a multivariate autoregressive process (MVAR). Lastly, the causal interaction patterns among the sources as a function of frequency are estimated from the MVAR modeling of the source temporal dynamics. The causal interaction patterns indicate the dynamic communications between sources, which are useful in distinguishing the primary sources responsible for the ictal onset from the secondary sources caused by the ictal propagation. The present ictal analysis strategy has been applied to a number of seizures from five epilepsy patients, and their results are consistent with observations from either MRI lesions or SPECT scans, which indicate its effectiveness. Each step of the ictal source analysis is statistically evaluated in order to guarantee the confidence in the results.

YNIMG Journal 2006 Journal Article

A cortical potential imaging study from simultaneous extra- and intracranial electrical recordings by means of the finite element method

Yingchun Zhang
Lei Ding
Wim van Drongelen
Kurt Hecox
David M. Frim
Bin He

In the present study, we have validated the cortical potential imaging (CPI) technique for estimating cortical potentials from scalp EEG using simultaneously recorded electrocorticogram (ECoG) in the presence of strong local inhomogeneity, i. e. , Silastic ECoG grid(s). The finite element method (FEM) was used to model the realistic postoperative head volume conductor, which includes the scalp, skull, cerebrospinal fluid (CSF) and brain, as well as the Silastic ECoG grid(s) implanted during the surgical evaluation in epilepsy patients, from the co-registered magnetic resonance (MR) and computer tomography (CT) images. A series of computer simulations were conducted to evaluate the present FEM-based CPI technique and to assess the effect of the Silastic ECoG grid on the scalp EEG forward solutions. The present simulation results show that the Silastic ECoG grid has substantial influence on the scalp potential forward solution due to the distortion of current pathways in the presence of the extremely low conductive materials. On the other hand, its influence on the estimated cortical potential distribution is much less than that on the scalp potential distribution. With appropriate numerical modeling and inverse estimation techniques, we have demonstrated the feasibility of estimating the cortical potentials from the scalp EEG with the implanted Silastic ECoG gird(s), in both computer simulations and in human experimentation. In an epilepsy patient undergoing surgical evaluation, the cortical potentials were reconstructed from the simultaneously recorded scalp EEG, in which main features of spatial patterns during interictal spike were preserved and over 0. 75 correlation coefficient value was obtained between the recorded and estimated cortical potentials. The FEM-based CPI technique provides a means of connecting the simultaneous recorded ECoG and the scalp EEG and promises to become an effective tool to evaluate and validate CPI techniques using clinic data.