Technical University of Munich (Zhang, Hager, Pan et al.)
Multimodal cardiac MRI foundation model that fuses 3D+T cine CMR (short-axis and long-axis views) with tabular patient health records (demographics, metabolic, and lifestyle factors) from 42,000 UK Biobank participants. Two-stage self-supervised pretraining -- masked-image reconstruction, then imaging-tabular contrastive alignment -- produces representations that transfer to whole-heart segmentation, cardiac phenotype/physiological-feature regression, and cardiac/metabolic disease classification within one unified framework.
Architecture
Hybrid
Multimodal transformer: masked-autoencoder 3D+T cine-CMR image encoder fused with a tabular patient-record encoder via two-stage contrastive pretraining
Framework
PyTorch
Added to catalog
2026-08-10
MIT
License for model weights only. Associated code may be licensed seperately, check code source for specific terms.
UK Biobank cardiac MRI imaging substudy; CineMA pretrained on 74,916 cine CMR studies, ukbb_cardiac (Bai et al. 2018) trained on ~4,875 subjects / 93,500 annotated images from an earlier release.
Multi-plane, multi-frame whole-heart segmentation from short-axis/long-axis cine CMR
Cardiac phenotype and physiological-feature prediction from fused imaging+tabular representation
Coronary artery disease (CAD) classification