Salvato in:
Dettagli Bibliografici
Autori principali: Huang, Peng, Wang, Yiming, Chen, Yineng, Gui, Liangqiao, Guo, Hui, Peng, Bo, Hu, Shu, Wu, Xi, Connie, Tsao, Zhu, Hongtu, Prabhakaran, Balakrishnan, Wang, Xin
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.06347
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911574387589120
author Huang, Peng
Wang, Yiming
Chen, Yineng
Gui, Liangqiao
Guo, Hui
Peng, Bo
Hu, Shu
Wu, Xi
Connie, Tsao
Zhu, Hongtu
Prabhakaran, Balakrishnan
Wang, Xin
author_facet Huang, Peng
Wang, Yiming
Chen, Yineng
Gui, Liangqiao
Guo, Hui
Peng, Bo
Hu, Shu
Wu, Xi
Connie, Tsao
Zhu, Hongtu
Prabhakaran, Balakrishnan
Wang, Xin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06347
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Evidence-Based Actor-Verifier Reasoning for Echocardiographic Agents
Huang, Peng
Wang, Yiming
Chen, Yineng
Gui, Liangqiao
Guo, Hui
Peng, Bo
Hu, Shu
Wu, Xi
Connie, Tsao
Zhu, Hongtu
Prabhakaran, Balakrishnan
Wang, Xin
Computer Vision and Pattern Recognition
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.
title Evidence-Based Actor-Verifier Reasoning for Echocardiographic Agents
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.06347