MARCUS: מודל ראייה-שפה רב-מודלי לאבחון וניהול של מחלות לב

תקציר מקורי באנגליתarXiv:2603.22179v2 Announce Type: replace Abstract: Cardiovascular disease remains the leading cause of global mortality, with progress hindered by human interpretation of complex cardiac tests. Current AI vision-language models are limited to single-modality inputs and are non-interactive. We present MARCUS (Multimodal Autonomous Reasoning and Chat for Ultrasound and Signals), an agentic vision-language system for end-to-end interpretation of electrocardiograms (ECGs), echocardiograms, and cardiac magnetic resonance imaging (CMR) independently and as multimodal input. MARCUS employs a hierarchical agentic architecture comprising modality-specific vision-language expert models, each integrating domain-trained visual encoders with multi-stage language model optimization, coordinated by a mu