Although supervised learning has enabled high performance for image segmentation, it requires a large amount of labeled training data, which can be difficult to obtain in the medical imaging field. Self-supervised learning (SSL) methods involving pretext tasks have shown promise in overcoming this requirement by first pretraining models using unlabeled data. In this work, we evaluate the efficacy of two SSL methods (inpainting-based pretext tasks of context prediction and context restoration) for CT and MRI image segmentation in label-limited scenarios, and investigate the effect of implementation design choices for SSL on downstream segmentation performance. We demonstrate that optimally trained and easy-to-implement inpainting-based SSL segmentation models can outperform classically supervised methods for MRI and CT tissue segmentation in label-limited scenarios, for both clinically-relevant metrics and the traditional Dice score.
@article{arxiv.2210.07936,
title = {Data-Limited Tissue Segmentation using Inpainting-Based Self-Supervised Learning},
author = {Jeffrey Dominic and Nandita Bhaskhar and Arjun D. Desai and Andrew Schmidt and Elka Rubin and Beliz Gunel and Garry E. Gold and Brian A. Hargreaves and Leon Lenchik and Robert Boutin and Akshay S. Chaudhari},
journal= {arXiv preprint arXiv:2210.07936},
year = {2022}
}