Scholarlink

Background <p>The prevention of cervical cancer relies on the accurate histopathological grading of its precursor lesions, particularly Squamous Intraepithelial Lesions (SIL), which can progress to Squamous Cell Carcinoma (SCC) if left undiagnosed or misclassified. However, the diagnostic evaluation of these lesions is often hindered by subjective interpretation, resulting in significant inter-observer variability. This inconsistency directly affects clinical decisions and emphasizes the urgent need for an objective, standardized diagnostic tool</p> Methods <p>To address this issue, we developed an AI framework that mimics the diagnostic workflow of expert pathologists by integrating two core innovations. First, a domain-specific feature extractor, <i>CerviScan-ViT</i>, captures subtle patterns in the tissue architecture critical for distinguishing SIL from normal tissue and identifying high-risk lesions. Second, a reinforcement learning agent, <i>SmartPatchRL</i>, intelligently navigates whole slide images (WSIs) to perform a policy-driven search for diagnostically critical regions, enhancing both efficiency and focus.</p> Results <p>Validated in a multi-center, prospective and retrospective setting, our framework sets a new performance benchmark, achieving 90.6% accuracy during the testing phase and demonstrating robust generalization to external data. Notably, the model’s interpretable heatmaps highlight its ability to focus on true lesion-defining features while effectively disregarding slide preparation artifacts that often lead to over-grading in traditional models.</p> Conclusion <p>This work offers a highly accurate, generalizable, and trustworthy solution poised to standardize SIL and SCC grading and improve the reliability of cervical cancer screening, ultimately aiding in early detection and prevention of both SIL and SCC.</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

Reinforcement learning–based WSI diagnostic system for cervical squamous cell carcinoma and precancerous lesions

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月26日

查看全文
  • Xi Deng,
  • Taojie Zhu,
  • Yizhi Wang,
  • Bin Hu,
  • Huaitian Yuan,
  • Deshui Yu,
  • Fanyi Zeng,
  • Zirui Huang,
  • Xiupeng Jia,
  • Youliang Gao,
  • Yonghong He,
  • Wenying Yu,
  • Yan Liu,
  • Tian Guan

摘要

Background

The prevention of cervical cancer relies on the accurate histopathological grading of its precursor lesions, particularly Squamous Intraepithelial Lesions (SIL), which can progress to Squamous Cell Carcinoma (SCC) if left undiagnosed or misclassified. However, the diagnostic evaluation of these lesions is often hindered by subjective interpretation, resulting in significant inter-observer variability. This inconsistency directly affects clinical decisions and emphasizes the urgent need for an objective, standardized diagnostic tool

Methods

To address this issue, we developed an AI framework that mimics the diagnostic workflow of expert pathologists by integrating two core innovations. First, a domain-specific feature extractor, CerviScan-ViT, captures subtle patterns in the tissue architecture critical for distinguishing SIL from normal tissue and identifying high-risk lesions. Second, a reinforcement learning agent, SmartPatchRL, intelligently navigates whole slide images (WSIs) to perform a policy-driven search for diagnostically critical regions, enhancing both efficiency and focus.

Results

Validated in a multi-center, prospective and retrospective setting, our framework sets a new performance benchmark, achieving 90.6% accuracy during the testing phase and demonstrating robust generalization to external data. Notably, the model’s interpretable heatmaps highlight its ability to focus on true lesion-defining features while effectively disregarding slide preparation artifacts that often lead to over-grading in traditional models.

Conclusion

This work offers a highly accurate, generalizable, and trustworthy solution poised to standardize SIL and SCC grading and improve the reliability of cervical cancer screening, ultimately aiding in early detection and prevention of both SIL and SCC.