SRA: A Novel Method to Improve Feature Embedding in Self-supervised Learning for Histopathological Images
This work addresses a domain-specific problem for histopathological image analysis by introducing an incremental improvement in self-supervised learning through tailored augmentation.
The paper tackles the problem of traditional image augmentation overlooking unique characteristics in histopathological images by proposing a histopathology-specific augmentation method called stain reconstruction augmentation (SRA), integrated with MoCo v3 and additional contrastive loss terms, resulting in SRA-MoCo v3 outperforming standard MoCo v3 across various downstream tasks and achieving comparable or superior performance to other foundation models pre-trained on larger datasets.
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.