Deep learning-based classification of dermatological lesions given a limited amount of labelled data

Background Artificial intelligence (AI) techniques are promising in early diagnosis of skin diseases. However, a precondition for their success is the access to large-scaled annotated data. Until now, obtaining this data has only been feasible with very high personnel and financial resources. Objectives The aim of this study was to overcome the obstacle caused by the scarcity of labelled data. Methods To simulate the scenario of label shortage, we discarded a proportion of labels of the training set. The training set consisted of both labelled and unlabelled images. We then leveraged a self-supervised learning technique to pretrain the AI model on the unlabelled images. Next, we fine-tuned the pretrained model on the labelled images. Results When the images in the training dataset were fully labelled, the self-supervised pretrained model achieved 95.7% of accuracy, 91.7% of precision and 90.7% of sensitivity. When only 10% of the data were labelled, the model could still yield 87.7% of accuracy, 81.7% of precision and 68.6% of sensitivity. In addition, we also empirically verified that the AI model and dermatologists are consistent in visually inspecting the skin images. Conclusions The experimental results demonstrate the great potential of the self-supervised learning in alleviating the scarcity of annotated data