Weakly Supervised Contrastive Learning for Histopathology Patch Embeddings

2026-02-10

AI Summary

This work addresses the challenge of learning effective feature representations from whole-slide images in digital pathology, where instance-level annotations are scarce. To this end, we propose WeakSupCon, a weakly supervised contrastive learning framework that, for the first time, integrates contrastive learning into weakly supervised multiple instance learning (MIL). Leveraging only slide-level labels, WeakSupCon effectively separates image patches of different classes in the embedding space without requiring instance-level pseudo-labels. By combining self-supervised pretraining with deep feature embeddings, our method significantly outperforms existing self-supervised contrastive learning approaches on three public datasets, leading to substantial improvements in downstream MIL classification performance.

Technology Category

• Machine Learning: Unsupervised & Self-Supervised Learning
• Computer Vision: Representation Learning for Vision
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Digital histopathology whole slide images (WSIs) provide gigapixel-scale high-resolution images that are highly useful for disease diagnosis. However, digital histopathology image analysis faces significant challenges due to the limited training labels, since manually annotating specific regions or small patches cropped from large WSIs requires substantial time and effort. Weakly supervised multiple instance learning (MIL) offers a practical and efficient solution by requiring only bag-level (slide-level) labels, while each bag typically contains multiple instances (patches). Most MIL methods directly use frozen image patch features generated by various image encoders as inputs and primarily focus on feature aggregation. However, feature representation learning for encoder pretraining in MIL settings has largely been neglected. In our work, we propose a novel feature representation learning framework called weakly supervised contrastive learning (WeakSupCon) that incorporates bag-level label information during training. Our method does not rely on instance-level pseudo-labeling, yet it effectively separates patches with different labels in the feature space. Experimental results demonstrate that the image features generated by our WeakSupCon method lead to improved downstream MIL performance compared to self-supervised contrastive learning approaches in three datasets. Our related code is available at github.com/BzhangURU/Paper_WeakSupCon_for_MIL

Problem

• weakly supervised learning
• contrastive learning
• histopathology
• multiple instance learning
• feature representation

Innovation

• Weakly Supervised Contrastive Learning
• Multiple Instance Learning
• Histopathology
• Patch Embeddings
• Bag-level Labels