Self-supervised learning for skin cancer diagnosis with limited training data

Cancer diagnosis is a well-studied problem in machine learning since early detection of cancer is often the determining factor in prognosis. Supervised deep learning achieves excellent results in cancer image classification, usually through transfer learning. However, these models require large amounts of labelled data and for several types of cancer, large labelled datasets do not exist. In this paper, we demonstrate that a model pre-trained using a self-supervised learning algorithm known as Barlow Twins can outperform the conventional supervised transfer learning pipeline. We juxtapose two base models: i) pretrained in a supervised fashion on ImageNet; ii) pretrained in a self-supervised fashion on ImageNet. Both are subsequently fine tuned on a small labelled skin lesion dataset and evaluated on a large test set. We achieve a mean test accuracy of 70\% for self-supervised transfer in comparison to 66\% for supervised transfer. Interestingly, boosting performance further is possible by self-supervised pretraining a second time (on unlabelled skin lesion images) before subsequent fine tuning. This hints at an alternative path to collecting more labelled data in settings where this is challenging - namely just collecting more unlabelled images. Our framework is applicable to cancer image classification models in the low-labelled data regime.