A Contrastive Learning Method Integrating Pathological Prior Information for Effective Differentiation of Histological Categories in Lung Squamous Cell Carcinoma

Abstract

BackgroundAdvancements 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.MethodsWe propose the Sample-Positive (SP) technique, which utilizes adjacent tissue morphology in WSIs to effectively sample positive examples. By integrating pathological prior information with 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.ResultsOur 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(0.9133) is match 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(0.9133) 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.ConclusionsOverall, 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.SignificanceThis paper provides a solution for precision oncology through the development of algorithms.

Note:
Funding declaration: This work was financially supported by the Joint Funds for the Innovation of Science and Technology, Fujian Province (Grant number: 2023Y9441), Natural Science Foundation of Fujian Province (Grant number: 2023J05241), Youth Science and Technology Project of Fujian Provincial Health Commission (Grant number: 2023QNA055), and Major Scientific Research Program for Young and Middle-aged Health Professionals of Fujian Province, China (Grant number: 2022ZQNZD008).

Conflict of Interests: All the authors declare no conflicts of interest.

Ethical Approval: This study was performed in accordance with the Declaration of Helsinki, and approved by the Institutional Review Board of Fujian Cancer Hospital (No. SQ2021-137-01).

Keywords: Self-supervised learning (SSL), sample-positive (SP) technique, lung squamous cell carcinoma, whole slide images (WSI), contrastive learning, pathological prior information