Strength in Diversity: Understanding the impacts of diverse training sets for self-supervised pre-training in histology

Self-supervised learning (SSL) has demonstrated success in computer vision tasks for natural images, and recently histopathological images, where there is limited availability of annotations. Despite this, there has been limited research into how the diversity of source data used for SSL tasks impacts performance. This study quantifies changes to downstream classification of metastatic tissue in lymph node sections of the PatchCamelyon dataset when datasets from different domains (natural images, textures, histology) are used for SSL pre-training. We show that for cases with limited training data, using diverse datasets from different domains for SSL pre-training can achieve comparable performance when compared to SSL pre-training on the target dataset.