Learning Representations with Contrastive Self-Supervised Learning for Histopathology Applications

TL;DR

This paper investigates how contrastive self-supervised learning can be adapted for histopathology images, highlighting the importance of dataset-specific considerations to improve tissue classification performance and reduce annotation efforts.

Contribution

The study provides an in-depth analysis of contrastive learning in histopathology, emphasizing view generation and hyper-parameter tuning tailored to this domain.

Findings

Contrastive learning can reduce annotation effort in digital pathology.

Dataset characteristics significantly influence the effectiveness of contrastive methods.

Proper calibration of views and hyper-parameters is crucial for optimal performance.

Abstract

Unsupervised learning has made substantial progress over the last few years, especially by means of contrastive self-supervised learning. The dominating dataset for benchmarking self-supervised learning has been ImageNet, for which recent methods are approaching the performance achieved by fully supervised training. The ImageNet dataset is however largely object-centric, and it is not clear yet what potential those methods have on widely different datasets and tasks that are not object-centric, such as in digital pathology. While self-supervised learning has started to be explored within this area with encouraging results, there is reason to look closer at how this setting differs from natural images and ImageNet. In this paper we make an in-depth analysis of contrastive learning for histopathology, pin-pointing how the contrastive objective will behave differently due to the characteristics of histopathology data. We bring forward a number of considerations, such as view generation for the contrastive objective and hyper-parameter tuning. In a large battery of experiments, we analyze how the downstream performance in tissue classification will be affected by these considerations. The results point to how contrastive learning can reduce the annotation effort within digital pathology, but that the specific dataset characteristics need to be considered. To take full advantage of the contrastive learning objective, different calibrations of view generation and hyper-parameters are required. Our results pave the way for realizing the full potential of self-supervised learning for histopathology applications.