Paper ID: 2401.00692

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

Hamish Haggerty, Rohitash Chandra

Early cancer detection is crucial for prognosis, but many cancer types lack large labelled datasets required for developing deep learning models. This paper investigates self-supervised learning (SSL) as an alternative to the standard supervised pre-training on ImageNet data for scenarios with limited training data using the ResNet-50 deep learning model. We first demonstrate that SSL pre-training on ImageNet (via the Barlow Twins SSL algorithm) outperforms supervised pre-training (SL) using a skin lesion dataset with limited training samples. We then consider further SSL pre-training (of the two ImageNet pre-trained models) on task-specific datasets, where our implementation is motivated by supervised transfer learning. The SSL significantly enhances initially SL pre-trained models, closing the performance gap with initially SSL pre-trained ones. Surprisingly, further pre-training on just the limited fine-tuning data achieves this performance equivalence. We implement a linear probe training strategy in the RestNet-50 model, and our experiments reveal that improvement stems from enhanced feature extraction. We find that minimal further SSL pre-training on task-specific data can be as effective as large-scale SSL pre-training on ImageNet for medical image classification tasks with limited labelled data. We validate these results on an oral cancer histopathology dataset, suggesting broader applicability across medical imaging domains facing labelled data scarcity.

Submitted: Jan 1, 2024