CLASS-M: Adaptive stain separation-based contrastive learning with pseudo-labeling for histopathological image classification
This addresses the problem of limited labeled data for local prediction in medical image analysis, offering an incremental improvement over existing methods.
The paper tackles patch-level histopathological image classification by proposing CLASS-M, a semi-supervised model that uses adaptive stain separation-based contrastive learning and pseudo-labeling with MixUp, achieving the best performance on two clear cell renal cell carcinoma datasets.
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