Weakly Supervised Contrastive Learning for Histopathology Patch Embeddings

TL;DR

This paper introduces WeakSupCon, a weakly supervised contrastive learning framework that enhances feature representations for histopathology image analysis, improving multiple instance learning performance without requiring detailed annotations.

Contribution

The paper presents a novel weakly supervised contrastive learning method that leverages slide-level labels to improve patch feature representations for MIL in histopathology.

Findings

WeakSupCon outperforms self-supervised contrastive methods in downstream tasks.

Improved patch embeddings lead to better MIL classification accuracy.

Method is effective across multiple histopathology datasets.

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