Related Experiment Video
Updated: Jul 6, 2025
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
2.8K
Learning with limited annotations: A survey on deep semi-supervised learning for medical image segmentation.
Rushi Jiao1, Yichi Zhang2, Le Ding3
1School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China; School of Engineering Medicine, Beihang University, Beijing, 100191, China; Shanghai Artificial Intelligence Laboratory, Shanghai, 200232, China.
Computers in Biology and Medicine
|December 29, 2023
Summary
This review explores semi-supervised learning for medical image segmentation, addressing the challenge of limited expert annotations. It summarizes recent methods, discusses limitations, and suggests future research directions.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Computer Vision
Background:
- Medical image segmentation is crucial for image-guided clinical applications.
- Deep learning models require extensive labeled data, which is scarce and expensive in medical imaging.
- Semi-supervised learning offers a solution by utilizing limited annotations.
Conclusions:
- Semi-supervised learning is a promising strategy for medical image segmentation with limited data.
- Further research is needed to address existing limitations and improve model robustness.
- This review aims to guide future research and development in the field.
