Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology
This work significantly improves the performance of weakly-supervised machine learning models for histopathology, making advanced diagnostic tools more accessible by reducing the need for extensive, costly expert annotations.
The authors addressed the challenge of weak supervision in histopathology by proposing to train an in-domain feature extractor using MoCo v2, a self-supervised learning algorithm. This approach improved the weakly-supervised state of the art on Camelyon16 from 91.4% to 98.7% AUC, nearly closing the gap with strongly-supervised models (99.3% AUC).
One of the biggest challenges for applying machine learning to histopathology is weak supervision: whole-slide images have billions of pixels yet often only one global label. The state of the art therefore relies on strongly-supervised model training using additional local annotations from domain experts. However, in the absence of detailed annotations, most weakly-supervised approaches depend on a frozen feature extractor pre-trained on ImageNet. We identify this as a key weakness and propose to train an in-domain feature extractor on histology images using MoCo v2, a recent self-supervised learning algorithm. Experimental results on Camelyon16 and TCGA show that the proposed extractor greatly outperforms its ImageNet counterpart. In particular, our results improve the weakly-supervised state of the art on Camelyon16 from 91.4% to 98.7% AUC, thereby closing the gap with strongly-supervised models that reach 99.3% AUC. Through these experiments, we demonstrate that feature extractors trained via self-supervised learning can act as drop-in replacements to significantly improve existing machine learning techniques in histology. Lastly, we show that the learned embedding space exhibits biologically meaningful separation of tissue structures.