קריאה בלב שלם: מסכמי-לווים-תופסי-תשומת-לב ללמידת הוויית-מרכזית-של-לב-במודלי-מידע-רב-מודלי

תקציר מקורי באנגליתarXiv:2609.12035v3 Announce Type: replace Abstract: 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 s