Scholarlink

<p>Computational analysis of histopathological specimens holds promise in identifying biomarkers, elucidating disease mechanisms, and streamlining clinical diagnosis. However, the application of deep learning techniques in vascular pathology remains underexplored. Here, we present a comprehensive evaluation of deep learning-based approaches to analyze digital whole-slide images of abdominal aortic aneurysm samples from 369 patients from three European centers. Deep learning demonstrated robust performance in predicting inflammatory characteristics, particularly in the adventitia, as well as fibrosis grade and remaining elastic fibers in the tunica media from Hematoxylin and Eosin (HE)-stained slides (mean AUC &gt; 0.70 in two external test cohorts). Models trained on Elastica van Gieson (EvG)-stained slides overall performed similar to models trained on HE-stained WSI for detection of calcification and fibrosis. For prediction of inflammatory parameters, HE-trained models performed considerably superior to EvG-trained models. Overall, this study represents the first comprehensive evaluation of computational pathology in vascular disease and has the potential to contribute to improved understanding of abdominal aortic aneurysm pathophysiology and personalization of treatment strategies, particularly when integrated with radiological phenotypes and clinical outcomes.</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

Histopathological evaluation of abdominal aortic aneurysms with deep learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月16日

查看全文
  • Fiona R. Kolbinger,
  • Omar S. M. El Nahhas,
  • Maja Carina Nackenhorst,
  • Christine Brostjan,
  • Wolf Eilenberg,
  • Albert Busch,
  • Jakob Nikolas Kather

摘要

Computational analysis of histopathological specimens holds promise in identifying biomarkers, elucidating disease mechanisms, and streamlining clinical diagnosis. However, the application of deep learning techniques in vascular pathology remains underexplored. Here, we present a comprehensive evaluation of deep learning-based approaches to analyze digital whole-slide images of abdominal aortic aneurysm samples from 369 patients from three European centers. Deep learning demonstrated robust performance in predicting inflammatory characteristics, particularly in the adventitia, as well as fibrosis grade and remaining elastic fibers in the tunica media from Hematoxylin and Eosin (HE)-stained slides (mean AUC > 0.70 in two external test cohorts). Models trained on Elastica van Gieson (EvG)-stained slides overall performed similar to models trained on HE-stained WSI for detection of calcification and fibrosis. For prediction of inflammatory parameters, HE-trained models performed considerably superior to EvG-trained models. Overall, this study represents the first comprehensive evaluation of computational pathology in vascular disease and has the potential to contribute to improved understanding of abdominal aortic aneurysm pathophysiology and personalization of treatment strategies, particularly when integrated with radiological phenotypes and clinical outcomes.