Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation
It tackles the problem of costly and scarce labeled data in medical imaging for researchers and practitioners, but is incremental as a review paper.
This paper surveys deep semi-supervised learning methods for medical image segmentation, addressing the challenge of limited expert annotations, and summarizes technical innovations and empirical results to inspire further research.
Medical image segmentation is a fundamental and critical step in many image-guided clinical approaches. Recent success of deep learning-based segmentation methods usually relies on a large amount of labeled data, which is particularly difficult and costly to obtain especially in the medical imaging domain where only experts can provide reliable and accurate annotations. Semi-supervised learning has emerged as an appealing strategy and been widely applied to medical image segmentation tasks to train deep models with limited annotations. In this paper, we present a comprehensive review of recently proposed semi-supervised learning methods for medical image segmentation and summarized both the technical novelties and empirical results. Furthermore, we analyze and discuss the limitations and several unsolved problems of existing approaches. We hope this review could inspire the research community to explore solutions for this challenge and further promote the developments in medical image segmentation field.