Han Zhang is an Associate Professor, the Director of the Disease and Intelligent Analytics Lab (DIAL), the Director of the Brain-Intelligence Development Lab (BID), the Vice Director of the Advanced Imaging Research Lab (AIR) at the ShanghaiTech University School of Biomedical Engineering. His research has been focusing on brain network modeling and network-based learning, not only for their basic neuroscience and clinical applications, but also for better understanding the developing/aging brain and the associated disorders, such as autism spectrum disorder (ASD) and Alzheimer’s disease (AD).

Dr. Zhang has published more than 130 papers on research journals and conference proceedings such as PNAS, Brain, IEEE TMI, AAAI, and MICCAI. He was also the core member and co-PI of the NIH funding “Baby Connectome Project (BCP)”. As PI or co-PI, he has received sponsorship of multiple NIH grants at the US, and is currently leading several NSFC grants, STI-Major Grants in China totaled more than 6 million USD. One of the major tasks his team is to build the largest and the most comprehensive, high-quality infant longitudinal cohort at age 0-6 in China (Chinese Baby Connectome Project, CBCP), for charting 0-6 brain development, understanding mechanism of individualized developmental outcomes and that of various disorders.

Dr. Zhang got his BS (major: EE) from Zhejiang University and his PhD (major: Cognitive Neuroscience and Neuroimage Computing) from the State Key Laboratory of Cognitive Neuroscience and Learning at the Beijing Normal University. He was a Faculty Investigator at Hangzhou Normal University before he worked at the University of North Carolina at Chapel Hill as a postdoctoral fellow, lecturer, and Assistant Professor. Before joining ShanghaiTech, he was an PI at the Institute of Brain-Intelligence Technology, Zhangjiang LAB.

• Infant brain development: Sponsored by the National Brain Initiative Project (Chinese Baby Connectome Project), our lab is targeting to construct the largest and the most comprehensive and high-quality infant cohort with MRI, EEG, behavioral, environmental, and genetic data. Based on this big data, scientists can better understand brain structural, functional, and connectome changes in the pivotal 0-6 years of age. To facilitate developmental and clinical neuroscience studies, we are also developing AI-based evaluation and analysis tools and disseminating to the community. In some paralleled studies, we are collaborating with clinicians for uncovering neuromechanism of ASD and ADHD. 

  
  

• Aging brain and Alzheimer’s disease: We put together different imaging techniques (MRI, EEG, PET, and fNIRS) and utilize advanced AI technology to delineate trajectories of aging brain. Based on our extensive collaboration with hospitals, we are building clinically feasible and easy-to-implement evaluation and prediction model for early diagnosis of Alzheimer’s disease and related dementia. We are trying to improve the diagnosis accuracy without introducing complicated testing procedures for future clinical translations. We are also building prototypic ADRD early screening system with tailored software and hardware. Our aim is to detect AD 10+ years before the onset of the symptom.

  
  

• Brain network modeling: Network, or graph analysis is one of the powerful tools for us to understand brain connectivity and its functioning. It is also very important in revealed brain biomarkers of neurological and psychiatric diseases. We are striving to development new brain network construction methods 1) from different modalities (fMRI/EEG/dMRI/fNIRS), 2) characterizing spatiotemporal dynamics of brain organization, 3) capturing commonalities (at the group level) and individual variabilities for the healthy and disease brains, and 4) for developing AI-based diagnosis/prognosis model with graph representation learning.

Scientific writing

Scientific presentation

Brain sciences and brain diseases

Senior Member, Institute of Electrical and Electronics Engineers (IEEE)

Associate Editor, Brain Informatics

Associate Editor, Frontiers in Oncology

Guest Associate Editor, Frontiers in Oncology

Online Committee member, Medical Image Computing Seminar

Associated Editor, PLOS ONE

Brain network modeling

• Ghanbari, M., Zhou, Z., Hsu, L.-M., Han, Y., Sun, Y., Yap, P.-T., Zhang, H.*, Shen, D.*, Altered Connectedness of the Brain Chronnectome During the Progression to Alzheimer’s Disease, Neuroinformatics, 2021, Accepted

• Li, G., Liu, Y., Zheng, Y., Wu, Y., Li, D., Liang, X., Chen, Y., Cui, Y., Yap, P.-T., Qiu, S.*, Zhang, H.*, Shen, D.*, 2021, Multiscale Neural Modeling of Resting-state fMRI Reveals Executive-Limbic Malfunction as a Core Mechanism in Major Depressive Disorder, NeuroImage: Clinical, 2021, 31: 102758.

• Zhou, Z., Chen, X., Zhang, Y., Hu, D., Qiao, L., Yu, R., Yap, P.-T., Pan, G.*, Zhang, H.*, Shen, D.*, A Toolbox for Brain Network Construction and Classification (BrainNetClass). Human Brain Mapping, 2020, 41(10): 2808-2826.

• Li, G., Liu, Y., Zheng, Y., Li, D., Liang, X., Chen, Y., Cui, Y., Yap, P.-T., Qiu, S.*, Zhang, H.*, Shen, D.*, Large-scale Dynamic Causal Modeling of Major Depressive Disorder based on Resting-state fMRI. Human Brain Mapping, 2019.

• Yu, R.#, Zhang, H.#, An, L., Chen, X., Wei, Z., Shen, D., 2017. Connectivity strength-weighted sparse group representation-based brain network construction for MCI classification. Human Brain Mapping, 38(5): 2370-2383.

Computer-aided diagnosis

• Chen, Y.#, Zhou, Z.#, Liang, Y., Tan X., Li, Y., Qin, C., Feng, Y., Ma, X., Mo, Z., Xia, J., Zhang, H.*, Qiu, S.*, Shen, D.*, Classification of Type 2 Diabetes Mellitus with or without Cognitive Impairment from Healthy Controls Using High-order Functional Connectivity. Human Brain Mapping, 2021, 42(14): 4671-4684.

• Jiang, W., Zhang, H.*, Zeng, L.-L., Shen, H., Jian, Q., Thung, K.-H., Yap, P.-T., Liu, H., Hu, D., Wang, W.*, Shen, D.*, Dynamic neural circuit disruptions associated with antisocial behaviors. Human Brain Mapping, 2021, 42 (2): 329-344

• Ding, Z.#, Zhang, H.#, Lv, X.#, Xie, F., Liu L., Li, L., Shen, D., 2018. Radiation-induced Brain Structural and Functional Abnormalities in Pre-symptomatic Phase and Outcome Prediction. Human Brain Mapping, 39(1):407-427.

• Chen, X.#, Zhang, H.#, Zhang, L., Shen, C., Lee, S.-W., Shen, D., 2017. Extraction of Dynamic Functional Connectivity from Brain Grey Matter and White Matter for MCI Classification, Human Brain Mapping, 38(10):5019-5034.

Alzheimer’s disease and related dementias

• Yue, L.#, Hu, D.#, Zhang, H.#, Wen, J., Wu, Y., Li, W., Sun, L., Li, X., Wang, J., Li, G., Wang, T., Shen, D., Xiao, 2021, Prediction of 7-year’s Conversion from Subjective Cognitive Decline to Mild Cognitive Impairment. Human Brain Mapping. DOI: 10.1002/hbm.25216.

• Kam, T.-E., Zhang, H.*, Jiao, Z., Shen, D., Deep Learning of Static and Dynamic Brain Functional Networks for Early MCI Detection, IEEE Transactions on Medical Imaging, 2020, 39(2): 478–487.

• Ghanbari, M., Hsu, L.-M., Zhou, Z., Ghanbari, A., Mo, Z., Yap, P.-T., Zhang, H.*, Shen, D.*, A New Metric for Characterizing Dynamic Redundancy of Dense Brain Chronnectome and Its Application to Early Detection of Alzheimer's Disease, MICCAI 2020, Lima, Peru, Oct 4-8, 2020 (MICCAI 2020 NIH Award).

• Jiao, Z., Huang, P., Kam, T.-E., Hsu, L.-M., Wu, Y., Zhang, H.*, Shen, D.*, Dynamic Routing Capsule Networks for Mild Cognitive Impairment Diagnosis, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019.

Infant brain development

• Wen, X., Wang, R., Yin, W., Lin, W., Zhang, H.*, Shen, D.*, Development of Dynamic Functional Architecture during Early Infancy. Cerebral Cortex, 2020, 30(11): 5626-5638.

• Wen, X., Zhang, H.*, Li, G., Liu, M., Yin, W., Lin, W., Zhang, J., Shen, D.*, First-Year Development of Modules and Hubs in Infant Brain Functional Networks. NeuroImage, 2019, 185:222-235.

• Zhang, H., Shen, D., Lin, W., 2019. Resting-state Functional MRI Studies on Infant Brains: a Decade of Gap-Filling Efforts, NeuroImage, 185:664-684.

• Sousia, M., Wen X., Zhou, Z., Jin, B., Kam, T.-E., Hsu, L.-M., Wu, Z., Li, G., Wang, L., Rekik, I., Lin, W., Shen, D., Zhang, H.*, and for UNC/UMN Baby Connectome Project Consortium, A computational framework for dissociating development-related from individually variable flexibility in regional modularity assignment in early infancy, MICCAI 2020, Lima, Peru, Oct 4-8, 2020.

• Jiang, W., Zhang, H.*, Wu, Y., Hsu, L.-M., Hu, D., Shen, D.*, Early Development of Infant Brain Complex Network, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019.

• Zhou, Z., Zhang, H.*, Hsu, L.-M., Lin, W., Pan, G.*, Shen, D.*, and for the UNC/UMN Baby Connectome Project Consortium, Multi-layer temporal network analysis reveals increasing temporal reachability and spreadability in the first two years of life, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019.

• Kam, T.-E., Wen, X., Jin, B., Jiao, Z., Hsu, L.-M., Zhou, Z., Liu, Y., Yamashita, K., Hung, S.-C., Lin, W., Zhang, H.*, Shen, D.*, and for UNC/UMN Baby Connectome Project Consortium, A Deep Learning Framework for Noise Component Detection from Resting-state Functional MRI, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019.

• Zhang, H., Stanley, N., Mucha, P.J., Yin, W., Lin, W., Shen, D., Multi-layer large-scale functional connectome reveals infant brain developmental patterns. MICCAI 2018, Granada, Spain, Sep. 16-20, 2018.

Brain tumors

• Tang, Z., Xu, Y., Jin, L., Aibaidula, A., Lu, J., Jiao, Z., Wu, J.*, Zhang, H.*, Shen, D.*, Deep Learning of Imaging Phenotype and Genotype for Predicting Overall Survival Time of Glioblastoma Patients. IEEE Transactions on Medical Imaging, 2020, 39(6): 2100-2109.

• Chen, L.#, Zhang, H.#,Lu, J.#, Thung, K., Aibaidula, A., Liu, L., Chen, S., Jin, L., Wu, J., Wang, Q., Zhou, L., Shen, D., 2018. Multi-label Nonlinear Matrix Completion with Transductive Multi-task Feature Selection for Joint MGMT and IDH1 Status Prediction of Patient with High-Grade Gliomas. IEEE Transactions on Medical Imaging, 37(8):1775-1787.

• Cao, B., Zhang, H.*, Wang, N.*, Gao, X., Shen, D.*, Auto-GAN: Self-Supervised Collaborative Learning for Medical Image Synthesis, AAAI 2020, New York, USA, Feb 7-12, 2020 (Travel award).

• Huang, P., Li, D., Jiao, Z., Wei, D., Li, G., Zhang, H.*, Shen, D.*, CoCa-GAN: Common-feature-learning-based Context-aware Generative Adversarial Network for Glioma Grading, MICCAI 2019, Shenzhen, China, Oct 13-17, 2019.

Sponsored by the STI major projects and other key projects of the NSFC grants totaled more than 6 million US Dollars, the Disease and Intelligent Analytics Lab (DIAL) has more than 30 multidisciplinary researchers, clinicians, and students from CS, EE, BME, Psychology, Education, Data Science, Cognitive Neuroscience. The DIAL utilizes the 250-square meter Brain Intelligence Development Laboratory (BID lab) well-designed for infant studies and a state-of-the-art 3.0T MRI scanner customized for Chinese Brain Initiative Projects with novel imaging techniques at the Advanced Imaging Research Laboratory (AIR lab) to collect comprehensive, high-quality infant longitudinal data consisting of MRI, EEG, fNIRS, as well as behavioral, developmental, environmental, and genetic information, for conducting cutting-edge research on brain development, disease, and aging.

Based on the first-ever 0-6 large scale infant cohort in China, the DIAL lab conducts research on depicting normative brain development atlases and trajectories, detecting individualized or abnormal development, constructing computer-aided model for early developmental disorder diagnosis. Our collaborators include top hospitals such as the SHMC, Renji Hospital, Fudan Pediatric Hospital as well as imaging and medical AI enterprises such as United Imaging and United Imaging Intelligence.

The DIAL lab commits to exploring the following research directions, covering brain data science, neuroimage computing, cognitive neuroscience 1) Sensitive brain network construction technologies for better detection of brain diseases and mental disorders. The methods include but not limited to brain high-order networks, dynamic networks, directed networks and multimodal network fusion. 2) Machine learning and deep learning on brain functional imaging and networks. The brain networks constructed from structure, functional, diffusion, perfusion MRI, PET, EEG and fNIRS are fused by using graph representation algorithms for disease evaluation. 3) Understanding brain mechanisms for infant early development and developmental abnormalities. Develop full-stack, full-spectrum AI techniques for construction of a large infant cohort and the normative trajectories and atlases. Establish the association between genes, environment, images and behaviors to provide a theoretical model for the study of abnormal development. In addition to conventional data such as MRI, we also use CV technology to capture diagnostic information from infant video and vocalization data for early autism diagnosis. 4) Early diagnosis of aging-related, neurodegenerative diseases. We especially focus on ultra-early Alzheimer’s disease detection using AI and medical images. That is, we will detect individuals with Alzheimer’s disease pathology at the preclinical stage, i.e., when the patient does not have any symptoms.