SGCL: Spatial guided contrastive learning on whole-slide pathological images

Tiancheng Lin, Zhimiao Yu, Zengchao Xu, Hongyu Hu, Yi Xu, Chang Wen Chen

Abstract: Highlights•Two intrinsic properties behind the WSIs are leveraged for designing the pretext tasks.•A novel self-supervised learning method is proposed for whole-slide pathological images.•A new loss function is proposed and validated via a theoretical analysis.•The proposed method achieves state-of-the-art performance on multiple datasets and tasks.