A survey of the impact of self-supervised pretraining for diagnostic tasks in medical X-ray, CT, MRI, and ultrasound

Abstract

Self-supervised pretraining has been observed to be effective at improving feature representations for transfer learning, leveraging large amounts of unlabelled data. This review summarizes recent research into its usage in X-ray, computed tomography, magnetic resonance, and ultrasound imaging, concentrating on studies that compare self-supervised pretraining to fully supervised learning for diagnostic tasks such as classification and segmentation. The most pertinent finding is that self-supervised pretraining generally improves downstream task performance compared to full supervision, most prominently when unlabelled examples greatly outnumber labelled examples. Based on the aggregate evidence, recommendations are provided for practitioners considering using self-supervised learning. Motivated by limitations identified in current research, directions and practices for future study are suggested, such as integrating clinical knowledge with theoretically justified self-supervised learning methods, evaluating on public datasets, growing the modest body of evidence for ultrasound, and characterizing the impact of self-supervised pretraining on generalization.

Improving the Generalizability and Performance of an Ultrasound Deep Learning Model Using Limited Multicenter Data for Lung Sliding Artifact Identification

“…Future work by our group will investigate additional techniques to combat against poor generalizability of DL models in the setting of scarcely available labelled medical data. One area of interest is using self-supervised pretraining, which has demonstrated promise in improving task performance compared to full supervised learning for multiple medical imaging modalities including ultrasound [ 50 ]. This technique is particularly useful in the case when unlabeled examples vastly outnumber labelled examples.…”