Metraipolis › archive › dc_30dd4f4264cb

Beyond Representation Learning: A Systematic Study of Joint-Embedding Predictive Generation for 3D Brain MRI — arXiv:2608.28787

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28787
License (as archived)
CC0-1.0
Archived
2026-10-17T09:53:25.083Z
SHA-256 of the archived text
d9ee98aadd4ed0a65ea93a91875a375a0d64ae85b01862aebd7f2e2016d27d48
Stable URL of this page
https://metraipolis.com/documento/dc_30dd4f4264cb

How to cite

Beyond Representation Learning: A Systematic Study of Joint-Embedding Predictive Generation for 3D Brain MRI — arXiv:2608.28787 — arXiv (en), https://arxiv.org/abs/2608.28787 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_30dd4f4264cb (Metraipolis archive dc_30dd4f4264cb, sha256 d9ee98aadd4ed0a65ea93a91875a375a0d64ae85b01862aebd7f2e2016d27d48)
BibTeX
@misc{dc30dd4f4264cb,
  title = {Beyond Representation Learning: A Systematic Study of Joint-Embedding Predictive Generation for 3D Brain MRI — arXiv:2608.28787},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28787},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_30dd4f4264cb; sha256 d9ee98aadd4ed0a65ea93a91875a375a0d64ae85b01862aebd7f2e2016d27d48},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28787. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Joint-embedding predictive architectures (JEPAs) have primarily been developed for self-supervised representation learning. Denoising JEPA (D-JEPA) recently demonstrated strong generative capabilities on natural images, yet the applicability to 3D medical imaging remains unexplored. Building on the D-JEPA framework, we present Med-D-JEPA, a systematic adaptation and evaluation of joint-embedding predictive generation for 3D brain MRI. Med-D-JEPA operates on continuous latent tokens produced by a 3D KL-regularized adversarial variational autoencoder, and combines masked context prediction, representation-level alignment, per-token diffusion, and iterative next-set-of-token sampling. We evaluate unconditional and class-conditional generation quality on BraTS2019 and OASIS-1 datasets; downstream classification utility; and preliminary whole-tumor segmentation on BraTS2020. Across different generation settings, Med-D-JEPA achieves superior or competitive performance compared to several strong baselines on fidelity and diversity metrics. Compared to training with real samples, Med-D-JEPA-based synthetic pretraining improves classification AUC from 0.63 to 0.85 on BraTS2019 and from 0.78 to 0.87 on OASIS-1. In the segmentation study, pretraining on Med-D-JEPA samples improves Dice from 0.74 to 0.80 and reduces HD95 from 13.40 to 9.56 mm. These findings establish joint-embedding predictive generation as a promising direction for 3D medical image synthesis and encourage further research in this direction.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.28787 — 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 2026-10-17T09:28:47.956Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).