Citations 1
EchoAtlas: A Conversational, Multi-View Vision-Language Foundation Model for Echocardiography Interpretation and Clinical Reasoning
Chao, Chieh-Ju, Asadi, Mohammad, Ramasamy, Gokul , Pecco, Nicolò , Oh, Jae K. , Banerjee, Imon, Langlotz, Curtis P, Fei-Fei, Li , Adeli, Ehsan, Erickson, B., Chao, Chieh‐Ju , Chao, Chieh-Ju , Wang, Yu-Chiang , Poterucha, Timothy, Kane, Garvan, Fei-Fei, Li , Erickson, Bradley J , Asadi, Mohammad, Li, Lavonda, Poterucha, Timothy Joseph , Arsanjani, Reza , Kane, Garvan C. , Banerjee, Imon , Langlotz, Curtis P. , Adeli, Ehsan
No container title available | March 18, 2026 | Volume: No volume available | Issue: No issue available | Pages: No page available
Abstract Echocardiography is the most widely used cardiac imaging modality, yet artificial intelligence-enabled interpretation remains limited by the inability of existing models to integrate visual assessment, quantitative measurement, and clinical reasoning within a unified framework. Here we present EchoAtlas, the first autoregressive vision-language model developed for echocardiographic interpretation. Trained on over 12.9 million question-answer pairs derived from approximately 2 million echocardiogram videos, EchoAtlas achieves 0.966 accuracy on multiple-choice questions in our internal test set and establishes a new state-of-the-art on the public MIMIC-EchoQA benchmark (0.699 vs. 0.508 previously). EchoAtlas also provides accurate quantitative measurements, segment-level regional wall motion assessment, longitudinal comparison, and diagnostic reasoning across diverse question formats — capabilities not previously demonstrated in this domain. These results highlight the potential of autoregressive vision-language models as a foundation for interactive echocardiographic interpretation, representing an early step toward scalable, auditable artificial intelligence systems in cardiology practice.