Localized Region Contrast for Enhancing Self-supervised Learning in Medical Image Segmentation

Recent advancements in self-supervised learning have demon- strated that effective visual representations can be learned from unla- beled images. This has led to increased interest in applying self-supervised learning to the medical domain, where unlabeled images are abundant and labeled images are difficult to obtain. However, most self-supervised learning approaches are modeled as image level discriminative or gen- erative proxy tasks, which may not capture the finer level representa- tions necessary for dense prediction tasks like multi-organ segmentation. In this paper, we propose a novel contrastive learning framework that integrates Localized Region Contrast (LRC) to enhance existing self- supervised pre-training methods for medical image segmentation. Our approach involves identifying Super-pixels by Felzenszwalb’s algorithm and performing local contrastive learning using a novel contrastive sam- pling loss. Through extensive experiments on three multi-organ segmen- tation datasets, we demonstrate that integrating LRC to an existing self-supervised method in a limited annotation setting significantly im- proves segmentation performance. Moreover, we show that LRC can also be applied to fully-supervised pre-training methods to further boost per- formance.