Scholarlink

Background <p>Advancements in digital pathology and computer technology have spurred artificial intelligence in histopathology, but the complexity of whole slide images (WSIs) poses challenges for manual annotation and traditional supervised learning.</p> Methods <p>We propose the Sample-Positive (SP) technique, which utilizes adjacent tissue morphology in WSIs to effectively sample positive examples. By integrating pathological prior information that reflects spatial adjacency of similar tissues with self-supervised learning (SSL) frameworks like SimCLR, MoCo-v3, and SinCLR, we developed an SSL method for WSI. We validated this approach on a dataset of 65 lung squamous cell carcinoma (LSCC) cases, covering four histological categories: necrosis, tumor, stroma, and epithelium. Performance was benchmarked against supervised models and original SSL frameworks using fine-tuning and linear evaluation, with metrics including accuracy (Acc), AUC, and F1 score.</p> Results <p>Our proposed SP technique outperformed baseline SSL methods in fine-tuning and linear evaluation tasks on the LSCC dataset. SPSimCLR and SPMoCo-v3 achieved the highest F1 scores, with SPSimCLR (0.9132) showing a 0.7% improvement over SimCLR (0.9067) and SPMoCo-v3 (0.9133) a 0.5% improvement over MoCo-v3 (0.9088) in fine-tuning, and SinCLR (0.9074) performs comparably to the original SSL methods. In linear evaluation, SPSimCLR (0.9082) improved F1 scores by 1.0% over SimCLR (0.8978), and SPMoCo-v3 (0.9060) improved by 1.2% over MoCo-v3 (0.8942), and SinCLR(0.9021) is surpass the original SSL methods. Ablation studies revealed that overlapping sampling slightly outperformed non-overlapping sampling, and that models trained on patches with single tissue types performed better than those trained on patches containing multiple tissue types.</p> Conclusions <p>Overall, combining the SP technique with contrastive learning shows significant improvements in distinguishing histological categories in LSCC, making it effective for WSIs of non-diffuse cancers.</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 contrastive learning method integrating pathological prior information for effective differentiation of histological categories in lung squamous cell carcinoma

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月17日

查看全文
  • Mingci Huang,
  • Weijin Xiao,
  • Gen Lin,
  • Chao Li,
  • Haipeng Xu,
  • Yunjian Huang,
  • Shengjia Chen,
  • Chuanben Chen,
  • Yang Sun,
  • Qiaofeng Zhong

摘要

Background

Advancements in digital pathology and computer technology have spurred artificial intelligence in histopathology, but the complexity of whole slide images (WSIs) poses challenges for manual annotation and traditional supervised learning.

Methods

We propose the Sample-Positive (SP) technique, which utilizes adjacent tissue morphology in WSIs to effectively sample positive examples. By integrating pathological prior information that reflects spatial adjacency of similar tissues with self-supervised learning (SSL) frameworks like SimCLR, MoCo-v3, and SinCLR, we developed an SSL method for WSI. We validated this approach on a dataset of 65 lung squamous cell carcinoma (LSCC) cases, covering four histological categories: necrosis, tumor, stroma, and epithelium. Performance was benchmarked against supervised models and original SSL frameworks using fine-tuning and linear evaluation, with metrics including accuracy (Acc), AUC, and F1 score.

Results

Our proposed SP technique outperformed baseline SSL methods in fine-tuning and linear evaluation tasks on the LSCC dataset. SPSimCLR and SPMoCo-v3 achieved the highest F1 scores, with SPSimCLR (0.9132) showing a 0.7% improvement over SimCLR (0.9067) and SPMoCo-v3 (0.9133) a 0.5% improvement over MoCo-v3 (0.9088) in fine-tuning, and SinCLR (0.9074) performs comparably to the original SSL methods. In linear evaluation, SPSimCLR (0.9082) improved F1 scores by 1.0% over SimCLR (0.8978), and SPMoCo-v3 (0.9060) improved by 1.2% over MoCo-v3 (0.8942), and SinCLR(0.9021) is surpass the original SSL methods. Ablation studies revealed that overlapping sampling slightly outperformed non-overlapping sampling, and that models trained on patches with single tissue types performed better than those trained on patches containing multiple tissue types.

Conclusions

Overall, combining the SP technique with contrastive learning shows significant improvements in distinguishing histological categories in LSCC, making it effective for WSIs of non-diffuse cancers.