SRA: A Novel Method to Improve Feature Embedding in Self-supervised Learning for Histopathological Images

TL;DR

It is demonstrated that the proposed SRA-MoCo v3 always outperforms the standard MoCo v3 across various downstream tasks and achieves comparable or superior performance to other foundation models pre-trained on significantly larger histopathology datasets.

Abstract

Self-supervised learning has become a cornerstone in various areas, particularly histopathological image analysis. Image augmentation plays a crucial role in self-supervised learning, as it generates variations in image samples. However, traditional image augmentation techniques often overlook the unique characteristics of histopathological images. In this paper, we propose a new histopathology-specific image augmentation method called stain reconstruction augmentation (SRA). We integrate our SRA with MoCo v3, a leading model in self-supervised contrastive learning, along with our additional contrastive loss terms, and call the new model SRA-MoCo v3. We demonstrate that our SRA-MoCo v3 always outperforms the standard MoCo v3 across various downstream tasks and achieves comparable or superior performance to other foundation models pre-trained on significantly larger histopathology datasets.

Figures (6)

• Figure 1: Patch examples from various datasets.
• Figure 2: The pipeline of our SRA-MoCo v3. We integrate our Stain Reconstruction Augmentation (SRA) as well as additional contrastive loss terms (CL3 and CL4) into MoCo v3.
• Figure 3: Examples of augmentations by SRA with different target strengths of H channel and E channel.
• Figure 4: Demonstration of stain reconstruction augmentation (SRA). Single stain images are shown in both RGB space and OD space. The augmentations are performed on each stain channel independently. There is a probability of p that only single channel is adopted.
• Figure 5: Patch examples from different classes and different datasets.