EchoAgent: Guideline-Centric Reasoning Agent for Echocardiography Measurement and Interpretation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Daghyani, Matin, Wang, Lyuyang, Hashemi, Nima, Medhat, Bassant, Abdelsamad, Baraa, Velez, Eros Rojas, Li, XiaoXiao, Tsang, Michael Y. C., Luong, Christina, Tsang, Teresa S. M., Abolmaesumi, Purang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915623931478016
author Daghyani, Matin
Wang, Lyuyang
Hashemi, Nima
Medhat, Bassant
Abdelsamad, Baraa
Velez, Eros Rojas
Li, XiaoXiao
Tsang, Michael Y. C.
Luong, Christina
Tsang, Teresa S. M.
Abolmaesumi, Purang
author_facet Daghyani, Matin
Wang, Lyuyang
Hashemi, Nima
Medhat, Bassant
Abdelsamad, Baraa
Velez, Eros Rojas
Li, XiaoXiao
Tsang, Michael Y. C.
Luong, Christina
Tsang, Teresa S. M.
Abolmaesumi, Purang
contents Purpose: Echocardiographic interpretation requires video-level reasoning and guideline-based measurement analysis, which current deep learning models for cardiac ultrasound do not support. We present EchoAgent, a framework that enables structured, interpretable automation for this domain. Methods: EchoAgent orchestrates specialized vision tools under Large Language Model (LLM) control to perform temporal localization, spatial measurement, and clinical interpretation. A key contribution is a measurement-feasibility prediction model that determines whether anatomical structures are reliably measurable in each frame, enabling autonomous tool selection. We curated a benchmark of diverse, clinically validated video-query pairs for evaluation. Results: EchoAgent achieves accurate, interpretable results despite added complexity of spatiotemporal video analysis. Outputs are grounded in visual evidence and clinical guidelines, supporting transparency and traceability. Conclusion: This work demonstrates the feasibility of agentic, guideline-aligned reasoning for echocardiographic video analysis, enabled by task-specific tools and full video-level automation. EchoAgent sets a new direction for trustworthy AI in cardiac ultrasound.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13948
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EchoAgent: Guideline-Centric Reasoning Agent for Echocardiography Measurement and Interpretation
Daghyani, Matin
Wang, Lyuyang
Hashemi, Nima
Medhat, Bassant
Abdelsamad, Baraa
Velez, Eros Rojas
Li, XiaoXiao
Tsang, Michael Y. C.
Luong, Christina
Tsang, Teresa S. M.
Abolmaesumi, Purang
Computer Vision and Pattern Recognition
Computation and Language
Machine Learning
Purpose: Echocardiographic interpretation requires video-level reasoning and guideline-based measurement analysis, which current deep learning models for cardiac ultrasound do not support. We present EchoAgent, a framework that enables structured, interpretable automation for this domain. Methods: EchoAgent orchestrates specialized vision tools under Large Language Model (LLM) control to perform temporal localization, spatial measurement, and clinical interpretation. A key contribution is a measurement-feasibility prediction model that determines whether anatomical structures are reliably measurable in each frame, enabling autonomous tool selection. We curated a benchmark of diverse, clinically validated video-query pairs for evaluation. Results: EchoAgent achieves accurate, interpretable results despite added complexity of spatiotemporal video analysis. Outputs are grounded in visual evidence and clinical guidelines, supporting transparency and traceability. Conclusion: This work demonstrates the feasibility of agentic, guideline-aligned reasoning for echocardiographic video analysis, enabled by task-specific tools and full video-level automation. EchoAgent sets a new direction for trustworthy AI in cardiac ultrasound.
title EchoAgent: Guideline-Centric Reasoning Agent for Echocardiography Measurement and Interpretation
topic Computer Vision and Pattern Recognition
Computation and Language
Machine Learning
url https://arxiv.org/abs/2511.13948