Self supervised contrastive learning for digital histopathology
This work addresses the scarcity of labeled datasets in medical image analysis by providing a method to learn effective features from unlabeled histopathology images, which is valuable for researchers and practitioners in the field.
This paper applies SimCLR, a contrastive self-supervised learning method, to digital histopathology by pretraining on 57 unlabeled datasets. The learned features, when used with linear classifiers, outperform ImageNet pretrained networks, boosting F1 scores on downstream tasks by over 28% on average.
Unsupervised learning has been a long-standing goal of machine learning and is especially important for medical image analysis, where the learning can compensate for the scarcity of labeled datasets. A promising subclass of unsupervised learning is self-supervised learning, which aims to learn salient features using the raw input as the learning signal. In this paper, we use a contrastive self-supervised learning method called SimCLR that achieved state-of-the-art results on natural-scene images and apply this method to digital histopathology by collecting and pretraining on 57 histopathology datasets without any labels. We find that combining multiple multi-organ datasets with different types of staining and resolution properties improves the quality of the learned features. Furthermore, we find using more images for pretraining leads to a better performance in multiple downstream tasks. Linear classifiers trained on top of the learned features show that networks pretrained on digital histopathology datasets perform better than ImageNet pretrained networks, boosting task performances by more than 28% in F1 scores on average. These findings may also be useful when applying newer contrastive techniques to histopathology data. Pretrained PyTorch models are made publicly available at https://github.com/ozanciga/self-supervised-histopathology.