Echo-CoPilot: A Multiple-Perspective Agentic Framework for Reliable Echocardiography Interpretation
cs.AI, cs.CV, cs.LG, eess.IV
Submitted: 2025-12-06
Updated: 2026-09-13
Comments: Accepted to the 2nd Agentic AI for Medicine Workshop at MICCAI 2026
Code: https://github.com/moeinheidari7829/Echo-CoPilot
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: Echocardiography interpretation requires integrating multi-view temporal evidence with quantitative measurements and guideline-grounded reasoning, yet existing foundation-model pipelines largely
Terminology
Abstract
Echocardiography interpretation requires integrating multi-view temporal evidence with quantitative measurements and guideline-grounded reasoning, yet existing foundation-model pipelines largely solve isolated subtasks and fail when tool outputs are noisy or values fall near clinical cutoffs. We propose Echo-CoPilot, an end-to-end agentic framework that combines a multi-perspective workflow with knowledge-graph-guided measurement selection. Echo-CoPilot runs three independent ReAct-style agents, structural, pathological, and quantitative, that invoke specialized echocardiography tools to extract parameters while querying EchoKG to determine which measurements are required for the clinical question and which should be avoided. A self-contrast language model then compares the evidence-grounded perspectives, generates a discrepancy checklist, and re-queries EchoKG to apply the appropriate guideline thresholds and resolve conflicts, reducing hallucinated measurement selection and borderline flip-flops. On MIMICEchoQA, Echo-CoPilot provides higher accuracy compared to SOTA baselines and, under a stochasticity stress test, achieves higher reliability through more consistent conclusions and fewer answer changes across repeated runs. Our code is publicly available at https://github.com/moeinheidari7829/Echo-CoPilot.
Sources
- gpt-oss-120b & gpt-oss-20b Model Card
- Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers
- EchoAgent: Guideline-Centric Reasoning Agent for Echocardiography Measurement and Interpretation
- MedRAX: Medical Reasoning Agent for Chest X-ray
- A Comprehensive Approach to Carbon Dioxide Emission Analysis in High Human Development Index Countries using Statistical and Machine Learning Techniques
- MedReflect: Teaching Medical LLMs to Self-Improve via Reflective Correction
- Annealed adaptive importance sampling method in PINNs for solving high dimensional partial differential equations
- Point-Spread Function errors for weak lensing - density cross-correlations. Application to UNIONS
- Euclid preparation. Sensitivity to non-standard particle dark matter model
- MedGemma Technical Report
- How Well Can General Vision-Language Models Learn Medicine By Watching Public Educational Videos?
- ReAct: Synergizing Reasoning and Acting in Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection