Metraipolis › archive › dc_94f7c47797fa

Reading the Whole Heart: Latent-Attention Masked Autoencoders for Multimodal Cardiac Representation Learning — arXiv:2609.12035

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12035
License (as archived)
CC0-1.0
Archived
2026-10-16T03:02:31.952Z
SHA-256 of the archived text
a688161b1ea4af87b3d9759b6462d7c35cc8bb0e9399be408c87fffc35b0016b
Stable URL of this page
https://metraipolis.com/documento/dc_94f7c47797fa

How to cite

Reading the Whole Heart: Latent-Attention Masked Autoencoders for Multimodal Cardiac Representation Learning — arXiv:2609.12035 — arXiv (en), https://arxiv.org/abs/2609.12035 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_94f7c47797fa (Metraipolis archive dc_94f7c47797fa, sha256 a688161b1ea4af87b3d9759b6462d7c35cc8bb0e9399be408c87fffc35b0016b)
BibTeX
@misc{dc94f7c47797fa,
  title = {Reading the Whole Heart: Latent-Attention Masked Autoencoders for Multimodal Cardiac Representation Learning — arXiv:2609.12035},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12035},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_94f7c47797fa; sha256 a688161b1ea4af87b3d9759b6462d7c35cc8bb0e9399be408c87fffc35b0016b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12035. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cardiovascular diagnosis and treatment rest on integrating complementary modalities, such as electrocardiogram, echocardiography, and chest X-rays, each capturing distinct but complementary aspects of cardiac pathophysiology. Yet most medical foundation models remain modality-specific, combining modalities only for finetuning or post-training. This discards the cross-modal evidence clinicians naturally integrate and ignores the structure within each modality. We introduce Latent-Attention Masked Autoencoder (LAMAE), a multimodal, structure-aware masked autoencoder that jointly learns patient-level representations during self-supervised pretraining. Instead of fusing modalities post hoc, LAMAE exchanges information directly in the latent space through a shared latent-attention module operating over a study-view-entity hierarchy, enabling aggregation of variable observations and handling of missing modalities. Pretrained on over 500'000 MIMIC-IV hospital stays, LAMAE outperforms modality-specific pretraining and strong contrastive and vision-language baselines across multimodal hospital-stay tasks, such as in-hospital mortality, ICD-10 and DRG coding, and length of stay, while remaining competitive on unimodal tasks. Modeling this structure also pays off within a single modality: even without cross-modal information, the latent-attention module improves representations over modality-specific pretraining.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.12035 — 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 2026-10-16T02:51:27.751Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).