Neuroimaging and Clinical AI
Developing multimodal models for MRI, clinical data, and neurological disease diagnosis.
Ping-Ju Lin
Research Assistant Professor · Peking University
Research Direction
AI for biomedical data, neuroimaging, and recovery prediction.
I develop machine-learning models that connect MRI, EEG, clinical measurements, and behavioral data with neurological disease mechanisms and rehabilitation outcomes.
About Me
I'm a Research Assistant Professor at Peking University. My work focuses on AI and machine learning for biomedical data, especially neuroimaging, Alzheimer's disease diagnosis, stroke recovery prediction, and brain-computer-interface supported rehabilitation. Previously, I was a Postdoctoral Scholar in the Laboratory of NeuroImaging of Prof. Arthur W. Toga at the Keck School of Medicine, University of Southern California, where my research centered on developing and improving AI/ML models for biomedical data to better understand the mechanisms of Alzheimer's disease.
I received my Ph.D. at Tsinghua University in 2024, supervised by Prof. Linhong Ji. During my Ph.D., I was a Visiting Scholar at Harvard Medical School and the Laboratory for Translational Neurorecovery of David Lin, MD, at Massachusetts General Hospital in 2023. My Ph.D. thesis focused on designing and applying artificial intelligence methods to predict and uncover stroke patients' motor recovery based on neurological changes.
I earned my master's degree at George Washington University in 2020, supervised by Prof. Murray Loew at the Medical Imaging & Image Analysis Laboratory. My master's work focused on AI-based medical imaging for tumor segmentation.
Research Focus
Explainable Biomedical Models
Designing interpretable learning frameworks that map predictions back to clinically meaningful signals.
Stroke Recovery and BCI
Predicting rehabilitation response from EEG, biomechanics, behavioral measures, and corticomuscular coupling.
Publications
For the full citation record and newly indexed papers, visit Google Scholar.
Google ScholarPublication Timeline
2025
Structured and sparse partial least squares coherence for multivariate cortico-muscular analysis
IEEE Transactions on Biomedical Engineering. A structured sparse coherence method for multivariate cortico-muscular analysis.
2025
A vision-language foundation model for Alzheimer's disease diagnosis using MRI and clinical data
Alzheimer's & Dementia. A multimodal foundation-model framework combining MRI and clinical data for Alzheimer's disease diagnosis.
2025
Design, Modeling, and Application of Bioinspired High-Force-Output Soft Pneumatic Bending Actuator
IEEE Transactions on Robotics. Bioinspired soft actuator design and modeling for high-force robotic applications.
2025
Multimodal behavioral data predict stroke patient's response to BCI treatment through explainable AI
IEEE Transactions on Neural Systems and Rehabilitation Engineering. Explainable multimodal AI for predicting response to BCI-supported stroke rehabilitation.
2025
Beta-band corticomuscular coherence: a novel biomarker of functional corticospinal tract integrity and motor recovery after stroke
IEEE Transactions on Neural Systems and Rehabilitation Engineering. Beta-band corticomuscular coherence as a biomarker of corticospinal integrity and motor recovery.
2025
Development and validation of a collaborative framework for assessment of peripheral facial paralysis using facial image regions of interest
Acta Oto-Laryngologica. A facial image ROI framework for peripheral facial paralysis assessment.
2025
Bioinspired smart triboelectric soft pneumatic actuator-enabled hand rehabilitation robot
Advanced Materials. A smart soft pneumatic actuator-enabled robotic system for hand rehabilitation.
2024
AM-EEGNet: An advanced multi-input deep learning framework for classifying stroke patient EEG task states
Neurocomputing. Multi-input EEG deep learning for stroke-patient task-state classification and model interpretation.
2024
Explainable deep-learning prediction for brain-computer interfaces supported lower extremity motor gains based on multistate fusion
IEEE Transactions on Neural Systems and Rehabilitation Engineering. Multi-state EEG fusion for explainable BCI rehabilitation outcome prediction.
2024
Motor-Respiratory Coupling Improves Endurance Performance during Rhythmic Isometric Handgrip Exercise
Medicine & Science in Sports & Exercise. A study of motor-respiratory coupling and endurance performance.
2023
Multiscale canonical coherence for functional corticomuscular coupling analysis
IEEE Journal of Biomedical and Health Informatics. A multiscale framework for functional corticomuscular coupling analysis.
2023
Lesion-specific cortical activation following sensory stimulation in patients with subacute stroke
Journal of NeuroEngineering and Rehabilitation. EEG activation patterns after sensory stimulation in subacute stroke.
2022
A transferable deep learning prognosis model for predicting stroke patients' recovery in different rehabilitation trainings
IEEE Journal of Biomedical and Health Informatics. Transferable prognosis modeling for stroke recovery across rehabilitation settings.
2021
CNN-based prognosis of BCI rehabilitation using EEG from first session BCI training
IEEE Transactions on Neural Systems and Rehabilitation Engineering. Early-session EEG prediction of BCI rehabilitation prognosis.
2021
Quantitative assessment of motor function by an end-effector upper limb rehabilitation robot based on admittance control
Applied Sciences. Robot-assisted quantitative assessment of upper-limb motor function.
CV
The PDF opens directly in the browser's built-in PDF viewer.