Evaluating the Robustness of Self-Supervised Learning in Medical Imaging
This addresses robustness issues for medical imaging practitioners, but it is incremental as it builds on existing self-supervised methods.
The paper tackled the problem of robustness in self-supervised learning for medical imaging, finding that networks trained this way have superior robustness and generalizability compared to fully-supervised learning, with consistent results in pneumonia detection in X-rays and multi-organ segmentation in CT.
Self-supervision has demonstrated to be an effective learning strategy when training target tasks on small annotated data-sets. While current research focuses on creating novel pretext tasks to learn meaningful and reusable representations for the target task, these efforts obtain marginal performance gains compared to fully-supervised learning. Meanwhile, little attention has been given to study the robustness of networks trained in a self-supervised manner. In this work, we demonstrate that networks trained via self-supervised learning have superior robustness and generalizability compared to fully-supervised learning in the context of medical imaging. Our experiments on pneumonia detection in X-rays and multi-organ segmentation in CT yield consistent results exposing the hidden benefits of self-supervision for learning robust feature representations.