CLASS-M: Adaptive stain separation-based contrastive learning with pseudo-labeling for histopathological image classification

TL;DR

This paper introduces CLASS-M, a semi-supervised contrastive learning model for histopathological image classification that leverages adaptive stain separation and pseudo-labeling to improve patch-level accuracy without extensive labeled datasets.

Contribution

The paper presents a novel semi-supervised model combining stain separation, contrastive learning, and pseudo-labeling for histopathological image classification, reducing the need for extensive annotations.

Findings

CLASS-M outperforms state-of-the-art models on two datasets.

Adaptive stain separation improves patch-level feature learning.

Pseudo-labeling with MixUp enhances classification accuracy.

Abstract

Histopathological image classification is an important task in medical image analysis. Recent approaches generally rely on weakly supervised learning due to the ease of acquiring case-level labels from pathology reports. However, patch-level classification is preferable in applications where only a limited number of cases are available or when local prediction accuracy is critical. On the other hand, acquiring extensive datasets with localized labels for training is not feasible. In this paper, we propose a semi-supervised patch-level histopathological image classification model, named CLASS-M, that does not require extensively labeled datasets. CLASS-M is formed by two main parts: a contrastive learning module that uses separated Hematoxylin and Eosin images generated through an adaptive stain separation process, and a module with pseudo-labels using MixUp. We compare our model with other state-of-the-art models on two clear cell renal cell carcinoma datasets. We demonstrate that our CLASS-M model has the best performance on both datasets. Our code is available at github.com/BzhangURU/Paper_CLASS-M/tree/main