Stain Based Contrastive Co-training for Histopathological Image Analysis

TL;DR

This paper introduces a semi-supervised learning method for histopathology image classification that uses contrastive co-training with separate color channel views, improving accuracy over existing methods.

Contribution

It presents a novel co-training framework leveraging color deconvolution to create independent views, combined with contrastive loss, for semi-supervised histopathology image analysis.

Findings

Improved classification accuracy over state-of-the-art methods

Effective use of color deconvolution for view separation

Demonstrated on renal and prostate carcinoma datasets

Abstract

We propose a novel semi-supervised learning approach for classification of histopathology images. We employ strong supervision with patch-level annotations combined with a novel co-training loss to create a semi-supervised learning framework. Co-training relies on multiple conditionally independent and sufficient views of the data. We separate the hematoxylin and eosin channels in pathology images using color deconvolution to create two views of each slide that can partially fulfill these requirements. Two separate CNNs are used to embed the two views into a joint feature space. We use a contrastive loss between the views in this feature space to implement co-training. We evaluate our approach in clear cell renal cell and prostate carcinomas, and demonstrate improvement over state-of-the-art semi-supervised learning methods.