Robustness & Generalization
Domain generalization, test-time adaptation, and semi-supervised learning for reliable medical image and signal processing.
Biography
I am a postdoctoral researcher at Westlake University, working with Prof. Yefeng Zheng (IEEE & AIMBE Fellow). I received my Ph.D. degree from Science Tokyo. Before that, I obtained my M.Sc. from Hong Kong University of Science and Technology and my bachelor's degree from Wuhan University of Technology.
Research Interests
I build Trustworthy Medical AI systems designed for the complexities of real-world clinical deployment. By addressing core challenges in model robustness, privacy preservation, and lifecycle safety, my research aims to develop dependable tools that responsibly integrate into dynamic healthcare environments.
Research Direction
Trustworthy Medical AI
Privacy Preservation
Federated learning, machine unlearning, and data-use rights protection via unlearnable examples for sensitive clinical data.
Lifecycle Medical AI
Continuous validation, deployment-time monitoring, and dynamic updates across the lifespan of medical AI systems.
Safety & Evaluation
Safety alignment and rigorous evaluation for medical foundation models, including VLMs and autonomous clinical agents.
News
-
Two papers were accepted to MICCAI 2026: VoxShield and BeatRhythm-TTA.
-
Our paper "FedSemiDG: Domain Generalized Federated Semi-supervised Medical Image Segmentation" was accepted by Medical Image Analysis.
-
I passed the final defense of my Ph.D. thesis and graduated from Science Tokyo.
-
Our contributed book chapter on federated learning in modern medical imaging was published.
Selected Publications
-
MedIA 2026
Medical Image Analysis -
MICCAI 2024
The 27th International Conference on Medical Image Computing and Computer-Assisted Intervention -
MICCAI 2023
The 26th International Conference on Medical Image Computing and Computer-Assisted Intervention