CMRVision, a CMR-specific foundation model trained using DINOv3-style self-supervised learning on a multi-center, multi-sequence cohort of 36 million CMR images, is introduced and the potential of CMRVision to support robust and generalizable cardiac MRI analysis across multiple sequences and views is highlighted.
Athira J. Jacob, Puneet Sharma, D. Rueckert· 0 citations
MR-JEPA is presented, a self-supervised video foundation model for CMR that extends LeJEPA to 3D spatiotemporal inputs through tubelet tokenization, spatiotemporal masking augmentation, and initialization from a 2D CMR foundation model.
Athira J. Jacob, Puneet Sharma, D. Comaniciu et al.· 0 citations
A Dynamic, Automatic and Systematic red-teaming audit framework that continuously stress-tests LLMs for health across four safety-critical axes: robustness, privacy, bias and hallucination, which provides a scalable framework for surfacing latent risks before such systems are deployed in consumer-facing health assistan...
Jiazhen Pan, Bailiang Jian, Paul Hager et al.· Nature Health· 0 citations
This work proposes a multi-dimensional, primitive based framework for dynamic contrast-enhanced MRI reconstruction that disentangles the underlying anatomy, the dynamic contrast enhancement, and residual motion into separate temporal basis functions, thereby enabling a geometrical interpretation of the representation.
Veronika Spieker, Wenqi Huang, Cemre Ariyurek et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
