Scholarlink

<p>Psoriasis and eczema are chronic inflammatory skin diseases with overlapping histopathological features, which often lead to diagnostic uncertainty even among experienced dermatopathologists. To address this challenge, we developed a computer-assisted diagnostic framework that combines the Virchow foundation model, pretrained on 1.5 million whole-slide images, with multi-instance learning (MIL) to classify psoriasis and eczema from digitized histopathology slides. Using an internal dataset (<i>n</i> = 40) and an external validation cohort (<i>n</i> = 40), equally balanced between both conditions and annotated by board-certified dermatopathologists, our best-performing configuration (Virchow + CLAM) achieved 85% accuracy, a macro-averaged F1 score of 0.80, and an AUC of 0.81 on the external cohort. This substantially outperformed baseline convolutional neural networks, which reached 61% accuracy, and models relying solely on pretrained feature extractors without MIL, which achieved an average accuracy of 68.8%. In a reader study on the same external cohort, individual dermatopathologist accuracies ranged from 47.5 to 70.0%, with a majority-vote consensus accuracy of 62.5%; our method outperformed both the average individual reader and the consensus under histology-only conditions. Furthermore, the model generates attention heatmaps that provide supportive visual context by highlighting regions associated with model predictions. Importantly, this study is designed as a methodological proof-of-concept conducted under controlled, histology-only conditions and is not intended for direct clinical deployment. Rather than demonstrating clinical readiness, it illustrates the potential of domain-specific foundation models combined with MIL for addressing diagnostically challenging inflammatory dermatoses.</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

Vision transformer-based diagnosis of psoriasis and eczema in whole-slide histology

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月20日

查看全文
  • Luis Carlos Rivera Monroy,
  • Anne Petzold,
  • Melissa Sari,
  • Katharina Breininger,
  • Andreas Maier,
  • Julio Vera-Gonzalez,
  • Michael Erdmann,
  • Stefan Schliep,
  • Konstantin Drexler,
  • Dennis Niebel,
  • Stephan Schreml,
  • Kinan M. Hayani,
  • Valentin Aebischer,
  • Stephan A. Braun,
  • Paul Schmidle,
  • Dieter Metze,
  • Michael Sticherling,
  • Carola Berking,
  • Elias A. T. Koch,
  • Markus V. Heppt

摘要

Psoriasis and eczema are chronic inflammatory skin diseases with overlapping histopathological features, which often lead to diagnostic uncertainty even among experienced dermatopathologists. To address this challenge, we developed a computer-assisted diagnostic framework that combines the Virchow foundation model, pretrained on 1.5 million whole-slide images, with multi-instance learning (MIL) to classify psoriasis and eczema from digitized histopathology slides. Using an internal dataset (n = 40) and an external validation cohort (n = 40), equally balanced between both conditions and annotated by board-certified dermatopathologists, our best-performing configuration (Virchow + CLAM) achieved 85% accuracy, a macro-averaged F1 score of 0.80, and an AUC of 0.81 on the external cohort. This substantially outperformed baseline convolutional neural networks, which reached 61% accuracy, and models relying solely on pretrained feature extractors without MIL, which achieved an average accuracy of 68.8%. In a reader study on the same external cohort, individual dermatopathologist accuracies ranged from 47.5 to 70.0%, with a majority-vote consensus accuracy of 62.5%; our method outperformed both the average individual reader and the consensus under histology-only conditions. Furthermore, the model generates attention heatmaps that provide supportive visual context by highlighting regions associated with model predictions. Importantly, this study is designed as a methodological proof-of-concept conducted under controlled, histology-only conditions and is not intended for direct clinical deployment. Rather than demonstrating clinical readiness, it illustrates the potential of domain-specific foundation models combined with MIL for addressing diagnostically challenging inflammatory dermatoses.