ShanghaiTech University

A general CT image segmentation foundation model that uses task-prompted automatic pathway decoding to segment 83 anatomical structures and lesions across whole-body CT.

Text-guided universal MRI synthesis generalist that generates customized brain MR sequences and resolutions from routine scans using imaging-metadata text prompts.

A transformer EEG foundation model pretrained with vector-quantized self-supervision on 1.7 TB of EEG, yielding transferable, interpretable discrete representations.

Self-supervised pre-training framework for medical image analysis that unifies pixel restoration with contrastive feature comparison across 2D and 3D modalities.