Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation

By Rushi Jiao, Yichi Zhang, Leiting Ding, Rong Cai, Jicong Zhang. Comput. Biol. Medicine, 2022

322 citations recorded by the source corpus.

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 summarize 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 can inspire the research community to explore solutions to this challenge and further advance the field of medical image segmentation.

Subfields: Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/6af5d19200646f1d8d9fce00e2b699b4af19364f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Ge Cui
2. Rushi Jiao
3. Ziyang Wang
4. Yichi Zhang
5. Zhenrong Shen
6. Jian-Qing Zheng
7. Lei Li
8. Yichi Zhang

Citations in the corpus

• Segment Anything Model for Medical Image Segmentation: Current Applications and Future Directions (2024, background): “Developing segmentation models for medical images typically demands domain-specific expertise to provide reliable and accurate annotations [91, 92], which raises expensive annotation costs compared to natural images.”
• Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation (2024, methodology): “This histogram further demonstrates that Mamba-UNet is more likely to provide prediction with high Dice-Coefficient performance.”