Metraipolis › archive › dc_b1b9ec3232de

MR-JEPA: A General Purpose Video Foundation Model for Cardiac MRI — arXiv:2608.30975

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30975
License (as archived)
CC0-1.0
Archived
2026-10-17T07:55:10.117Z
SHA-256 of the archived text
1c7bdf08543c342fecb7634b9ce6f5ddc75e02a2db5c946d0267ff9951217ce7
Stable URL of this page
https://metraipolis.com/documento/dc_b1b9ec3232de

How to cite

MR-JEPA: A General Purpose Video Foundation Model for Cardiac MRI — arXiv:2608.30975 — arXiv (en), https://arxiv.org/abs/2608.30975 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b1b9ec3232de (Metraipolis archive dc_b1b9ec3232de, sha256 1c7bdf08543c342fecb7634b9ce6f5ddc75e02a2db5c946d0267ff9951217ce7)
BibTeX
@misc{dcb1b9ec3232de,
  title = {MR-JEPA: A General Purpose Video Foundation Model for Cardiac MRI — arXiv:2608.30975},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30975},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b1b9ec3232de; sha256 1c7bdf08543c342fecb7634b9ce6f5ddc75e02a2db5c946d0267ff9951217ce7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30975. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cardiac magnetic resonance imaging (CMR) produces rich sequential data such as temporal cine videos and spatial LGE/mapping stacks, yet most deep learning approaches process individual 2D slices, discarding this context. We present MR-JEPA, 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. Unlike prior CMR video models limited to cine data, MR-JEPA is pretrained on multi-sequence data (cine, LGE, mapping) from 10,505 patients across two centers without annotations. We evaluate the frozen encoder on six downstream tasks using a unified multi-view gated attention architecture: LV ejection fraction, RV ejection fraction, three myocardial strains (GLS, GCS, GRS), and four-class disease detection. MR-JEPA outperforms other compared methods on all five regression tasks, including both a domain-specific CMR model pretrained on more data with text supervision and a natural-video foundation model, achieving an LV EF MAE of 4.79% (r =0.764) and a GLS MAE of 1.87 (r=0.805), with 21-27% MAE reductions over baselines on strain tasks. For disease detection, MR-JEPA achieved a macro AUG of 0.868, remaining competitive with the domain-specific baseline despite using a fully self-supervised pretraining objective. These results demonstrate the potential of a unified video encoder for robust, multi-view utilization of diverse CMR sequences in clinical cardiac quantification and diagnosis.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.30975 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T07:28:26.933Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).