Big Self-Supervised Models Advance Medical Image Classification

Citations Over TimeTop 1% of 2021 papers

Abstract

Self-supervised pretraining followed by supervised fine-tuning has seen success in image recognition, especially when labeled examples are scarce, but has received limited attention in medical image analysis. This paper studies the effectiveness of self-supervised learning as a pre-training strategy for medical image classification. We conduct experiments on two distinct tasks: dermatology condition classification from digital camera images and multi-label chest X-ray classification, and demonstrate that self-supervised learning on ImageNet, followed by additional self-supervised learning on unlabeled domain-specific medical images significantly improves the accuracy of medical image classifiers. We introduce a novel Multi-Instance Contrastive Learning (MICLe) method that uses multiple images of the underlying pathology per patient case, when available, to construct more informative positive pairs for self-supervised learning. Combining our contributions, we achieve an improvement of 6.7% in top-1 accuracy and an improvement of 1.1% in mean AUC on dermatology and chest X-ray classification respectively, outperforming strong supervised baselines pretrained on ImageNet. In addition, we show that big self-supervised models are robust to distribution shift and can learn efficiently with a small number of labeled medical images.

Related Papers

• → A review on image classification of remote sensing using deep learning(2017)28 cited
• → [Research progress in medical imaging based on deep learning of neural network].(2019)7 cited
• → Empowering Imbalanced Data in Supervised Learning: A Semi-supervised Learning Approach(2014)5 cited
• → A safe semi-supervised kernel minimum squared error algorithm(2015)
• Deep Learning based Medical Imaging Analysis(2020)