Scholarlink

<p>Intraoperative frozen section analysis is critical for evaluating tumor malignancy, assessing surgical margins, and informing real-time clinical decisions. However, limitations such as inconsistent slide quality, diagnostic variability, and time constraints challenge its reliability in routine workflows. To address these issues, we collected a real-world dataset of 4,667 hematoxylin and eosin-stained whole slide images (WSIs) from intraoperative consultations spanning diverse organ types. A Vision Transformer (ViT)-based model enhanced with a Soft Mixture of Experts (Soft MoE) module was developed to perform binary classification (benign vs. malignant) under weak supervision using only slide-level labels. The proposed model achieved excellent performance on the test set (AUC = 0.957, sensitivity = 0.817, specificity = 0.961), and demonstrated consistent diagnostic utility across common and rare tissue types. Instance-level heatmap visualizations revealed consistent visual alignment with diagnostic tumor regions, supporting model interpretability. Importantly, the model enables local inference on standard clinical hardware (e.g., GPU with 24 GB memory), making it feasible for real-world deployment. These findings suggest that Soft MoE-ViT offers a practical and interpretable solution for AI-assisted intraoperative pathology.</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

Pan-cancer frozen section classification using a soft mixture of experts vision transformer under weak supervision

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月24日

查看全文
  • Jingpeng Wu,
  • Moxuan Yang,
  • Jiacheng Li,
  • Peiyu Sun,
  • Xingqi Zhi,
  • Shuhao Wang,
  • Dingrong Zhong

摘要

Intraoperative frozen section analysis is critical for evaluating tumor malignancy, assessing surgical margins, and informing real-time clinical decisions. However, limitations such as inconsistent slide quality, diagnostic variability, and time constraints challenge its reliability in routine workflows. To address these issues, we collected a real-world dataset of 4,667 hematoxylin and eosin-stained whole slide images (WSIs) from intraoperative consultations spanning diverse organ types. A Vision Transformer (ViT)-based model enhanced with a Soft Mixture of Experts (Soft MoE) module was developed to perform binary classification (benign vs. malignant) under weak supervision using only slide-level labels. The proposed model achieved excellent performance on the test set (AUC = 0.957, sensitivity = 0.817, specificity = 0.961), and demonstrated consistent diagnostic utility across common and rare tissue types. Instance-level heatmap visualizations revealed consistent visual alignment with diagnostic tumor regions, supporting model interpretability. Importantly, the model enables local inference on standard clinical hardware (e.g., GPU with 24 GB memory), making it feasible for real-world deployment. These findings suggest that Soft MoE-ViT offers a practical and interpretable solution for AI-assisted intraoperative pathology.