Scholarlink

<p>Fluorescein fundus angiography (FFA) is essential for diagnosing retinal vascular diseases, yet its interpretation is expertise-intensive. Here, we present <b>Clin-FFA-VLM</b>, a multimodal vision–language framework that mirrors retina specialists’ cognitive workflow by decomposing FFA interpretation into three stages: lesion-aware visual perception, clinical report generation, and diagnostic decision support. Trained and tested on a multi-center dataset of 13,178 FFA images with expert label, 21,717 FFA images with 1790 clinical reports and diagnosis across 7 retinal diseases, Clin-FFA-VLM achieves an F1 of 0.834 for lesion detection, an entity-level F1 of 0.73 for report generation, and a diagnostic F1 of 0.77 by jointly reasoning over images and self-generated reports. External validation across two independent hospitals confirmed its generalizability (F1 of 0.78 and 0.70). In a prospective reader study with 200 FFA cases, Clin-FFA-VLM significantly improved diagnostic accuracy for medical students and residents (<i>p</i> &lt; 0.05), bridging the gap between automated systems and clinical practice.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A clinician aligned vision language framework for stepwise interpretation in fundus fluorescein angiography

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月12日

查看全文
  • Zichang Su,
  • Xiaocong Liu,
  • Bingtao Guan,
  • An Shao,
  • Xindi Liu,
  • Yan Yan,
  • Ziyao Luo,
  • Zhikang Li,
  • Yufeng Xu,
  • Jian Wu,
  • Xiaoling Huang,
  • Juan Ye

摘要

Fluorescein fundus angiography (FFA) is essential for diagnosing retinal vascular diseases, yet its interpretation is expertise-intensive. Here, we present Clin-FFA-VLM, a multimodal vision–language framework that mirrors retina specialists’ cognitive workflow by decomposing FFA interpretation into three stages: lesion-aware visual perception, clinical report generation, and diagnostic decision support. Trained and tested on a multi-center dataset of 13,178 FFA images with expert label, 21,717 FFA images with 1790 clinical reports and diagnosis across 7 retinal diseases, Clin-FFA-VLM achieves an F1 of 0.834 for lesion detection, an entity-level F1 of 0.73 for report generation, and a diagnostic F1 of 0.77 by jointly reasoning over images and self-generated reports. External validation across two independent hospitals confirmed its generalizability (F1 of 0.78 and 0.70). In a prospective reader study with 200 FFA cases, Clin-FFA-VLM significantly improved diagnostic accuracy for medical students and residents (p < 0.05), bridging the gap between automated systems and clinical practice.