Evidence-Based Actor-Verifier Reasoning for Echocardiographic Agents
This work addresses the problem of template shortcuts and spurious explanations in echocardiography VLM-based agents for clinical decision support, representing an incremental improvement over existing methods.
The paper tackles the challenge of automated intelligent analysis of echocardiographic data by proposing EchoTrust, an evidence-driven Actor-Verifier framework that produces structured intermediate representations for more reliable and interpretable decision-making in clinical applications.
Echocardiography plays an important role in the screening and diagnosis of cardiovascular diseases. However, automated intelligent analysis of echocardiographic data remains challenging due to complex cardiac dynamics and strong view heterogeneity. In recent years, visual language models (VLM) have opened a new avenue for building ultrasound understanding systems for clinical decision support. Nevertheless, most existing methods formulate this task as a direct mapping from video and question to answer, making them vulnerable to template shortcuts and spurious explanations. To address these issues, we propose EchoTrust, an evidence-driven Actor-Verifier framework for trustworthy reasoning in echocardiography VLM-based agents. EchoTrust produces a structured intermediate representation that is subsequently analyzed by distinct roles, enabling more reliable and interpretable decision-making for high-stakes clinical applications.