Contact

  • Academic
    masadi@stanford.edu
    University - Student Department: Electrical Engineering Position: Graduate

All Publications

  • EchoAtlas: A Conversational, Multi-View Vision-Language Foundation Model for Echocardiography Interpretation and Clinical Reasoning. medRxiv : the preprint server for health sciences Chao, C. J., Asadi, M., Li, L., Ramasamy, G., Pecco, N., Wang, Y. C., Poterucha, T., Arsanjani, R., Kane, G., Oh, J. K., Banerjee, I., Langlotz, C., Fei-Fei, L., Adeli, E., Erickson, B. J. 2026

    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.

    View details for DOI 10.64898/2026.03.14.26348388

    View details for PubMedID 41891021

    View details for PubMedCentralID PMC13015684

  • EchoGraph system for automated quality assessment of echocardiography reports. NPJ digital medicine Chao, C. J., Delbrouck, J. B., Asadi, M., Banerjee, I., Farina, J. M., Galasso, F., Mahmoud, A. K., Abbas, M. T., Wang, Y. C., Arsanjani, R., Kane, G. C., Oh, J. K., Erickson, B. J., Fei-Fei, L., Adeli, E., Langlotz, C. 2025

    Abstract

    Generative AI needs automatic clinical text accuracy metrics, but none exist for echocardiography. To address this, we developed EchoGraph, a BERT-based model trained on 600 densely annotated echocardiography reports from the Mayo Clinic (2017), split 7:2:1 for training, validation, and testing, using a tailored schema with 48,256 entities and 29,731 relations annotated. Sixty random MIMIC-EchoNote reports were annotated (3672 entities and 2360 relations) for external validation. EchoGraph demonstrated strong performance predicting entities (micro F1 0.85) and relations (micro F1 0.70), maintaining performance on external validation (entity micro F1 0.80, relation micro F1 0.52). EchoGraph F1 score showed superior error sensitivity versus RadGraph F1, with 2.8-fold higher slope magnitude (-0.817 vs -0.291) and better variance explained (R2 = 0.803 vs 0.578). EchoGraph offers an effective solution for evaluating language model-based echocardiography applications, supporting more accurate AI-generated reports.

    View details for DOI 10.1038/s41746-025-02140-w

    View details for PubMedID 41372462

  • Synthetic Hands Meet Legacy Data: A Synthetic Dataset for Structured, Controllable, and Multimodal Evaluation Zhang, M., So, H. M., Asadi, M., Zhao, D., Liang, Y., Wang, S., Wetzstein, G., Song, K., Kim, D., IEEE COMPUTER SOC IEEE COMPUTER SOC. 2025: 466-477

    View details for DOI 10.1109/ICCVW69036.2025.00053

    View details for Web of Science ID 001740020100050