Weakly Semi-supervised Whole Slide Image Classification by Two-level Cross Consistency Supervision

2025-04-16

AI Summary

This paper addresses the practical challenge of weakly semi-supervised whole-slide image (WSI) classification, where only a scarce number of WSIs are available with costly bag-level annotations—rendering conventional semi-supervised learning inapplicable. Method: We formally define this novel task as Weakly Semi-Supervised WSI Classification (WSWC) and propose CroCo, a dual-branch heterogeneous architecture integrating bidirectional consistency supervision (across bag- and instance-levels), cross-level regularization, unsupervised contrastive learning, and collaborative training—all within a multiple-instance learning (MIL) framework. Contribution/Results: Evaluated on four public benchmarks, CroCo achieves state-of-the-art classification accuracy using only 5% bag-level labels, while simultaneously delivering interpretable instance-level localization—thereby enhancing both diagnostic efficiency and reliability in computational pathology.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Computer Vision: Segmentation
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Machine learning and data science for the Web

Abstract

Computer-aided Whole Slide Image (WSI) classification has the potential to enhance the accuracy and efficiency of clinical pathological diagnosis. It is commonly formulated as a Multiple Instance Learning (MIL) problem, where each WSI is treated as a bag and the small patches extracted from the WSI are considered instances within that bag. However, obtaining labels for a large number of bags is a costly and time-consuming process, particularly when utilizing existing WSIs for new classification tasks. This limitation renders most existing WSI classification methods ineffective. To address this issue, we propose a novel WSI classification problem setting, more aligned with clinical practice, termed Weakly Semi-supervised Whole slide image Classification (WSWC). In WSWC, a small number of bags are labeled, while a significant number of bags remain unlabeled. The MIL nature of the WSWC problem, coupled with the absence of patch labels, distinguishes it from typical semi-supervised image classification problems, making existing algorithms for natural images unsuitable for directly solving the WSWC problem. In this paper, we present a concise and efficient framework, named CroCo, to tackle the WSWC problem through two-level Cross Consistency supervision. CroCo comprises two heterogeneous classifier branches capable of performing both instance classification and bag classification. The fundamental idea is to establish cross-consistency supervision at both the bag-level and instance-level between the two branches during training. Extensive experiments conducted on four datasets demonstrate that CroCo achieves superior bag classification and instance classification performance compared to other comparative methods when limited WSIs with bag labels are available. To the best of our knowledge, this paper presents for the first time the WSWC problem and gives a successful resolution.

Problem

• Addresses weakly semi-supervised WSI classification with limited labeled data
• Proposes two-level cross consistency supervision for instance and bag classification
• Improves accuracy in clinical pathological diagnosis with fewer labeled WSIs

Innovation

• Two-level Cross Consistency supervision framework
• Heterogeneous classifier branches for instance and bag classification
• Weakly Semi-supervised WSI classification with limited labels