Stain Based Contrastive Co-training for Histopathological Image Analysis

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