Timezone: »

 
Poster
SCL-WC: Cross-Slide Contrastive Learning for Weakly-Supervised Whole-Slide Image Classification
Xiyue Wang · Jinxi Xiang · Jun Zhang · Sen Yang · Zhongyi Yang · Ming-Hui Wang · Jing Zhang · Wei Yang · Junzhou Huang · Xiao Han

@

Weakly-supervised whole-slide image (WSI) classification (WSWC) is a challenging task where a large number of unlabeled patches (instances) exist within each WSI (bag) while only a slide label is given. Despite recent progress for the multiple instance learning (MIL)-based WSI analysis, the major limitation is that it usually focuses on the easy-to-distinguish diagnosis-positive regions while ignoring positives that occupy a small ratio in the entire WSI. To obtain more discriminative features, we propose a novel weakly-supervised classification method based on cross-slide contrastive learning (called SCL-WC), which depends on task-agnostic self-supervised feature pre-extraction and task-specific weakly-supervised feature refinement and aggregation for WSI-level prediction. To enable both intra-WSI and inter-WSI information interaction, we propose a positive-negative-aware module (PNM) and a weakly-supervised cross-slide contrastive learning (WSCL) module, respectively. The WSCL aims to pull WSIs with the same disease types closer and push different WSIs away. The PNM aims to facilitate the separation of tumor-like patches and normal ones within each WSI. Extensive experiments demonstrate state-of-the-art performance of our method in three different classification tasks (e.g., over 2% of AUC in Camelyon16, 5% of F1 score in BRACS, and 3% of AUC in DiagSet). Our method also shows superior flexibility and scalability in weakly-supervised localization and semi-supervised classification experiments (e.g., first place in the BRIGHT challenge). Our code will be available at https://github.com/Xiyue-Wang/SCL-WC.

Keywords: contrastive learning · Histopathology · Multiple Instance Learning · Whole slide image

Author Information

Xiyue Wang (Sichuan University)
Jinxi Xiang (Tencent AI Lab)
Jun Zhang (Tencent AI Lab)
Sen Yang (Sichuan University)
Zhongyi Yang (Xi'an Jiaotong University)
Ming-Hui Wang (Santa Clara University)
Jing Zhang (National University of Singapore)
Wei Yang (Tencent AI Lab)
Junzhou Huang (University of Texas at Arlington / Tencent AI Lab)
Xiao Han (Harvard University)

More from the Same Authors