Complementary consistency semi-supervised learning for 3D left atrial image segmentation

A network based on complementary consistency training, CC-Net, has been proposed for semi-supervised left atrium image segmentation. CC-Net efficiently utilizes unlabeled data from the perspective of complementary information, addressing the limited ability of existing semi-supervised segmentation a...

Full description

Saved in:
Bibliographic Details
Published in:Computers in biology and medicine 2023-10, Vol.165, p.107368-107368, Article 107368
Main Authors: Huang, Hejun, Chen, Zuguo, Chen, Chaoyang, Lu, Ming, Zou, Ying
Format: Article
Language:English
Subjects:
Algorithms
Atria
Biology
Complementary auxiliary models
Complementary consistency
Consistency
Deep learning
Electrical engineering
Genetic algorithms
Image processing
Image segmentation
Information processing
Machine learning
Magnetic resonance imaging
Neural networks
Optimization algorithms
Perturbation
Principal components analysis
Semantics
Semi-supervised learning
Semi-supervised segmentation
Teaching methods
Uncertainty
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A network based on complementary consistency training, CC-Net, has been proposed for semi-supervised left atrium image segmentation. CC-Net efficiently utilizes unlabeled data from the perspective of complementary information, addressing the limited ability of existing semi-supervised segmentation algorithms to extract information from unlabeled data. The complementary symmetrical structure of CC-Net includes a main model and two auxiliary models. The complementary consistency is formed by the model-level perturbation between the main model and the auxiliary models, enforcing their consistency. The complementary information obtained by the two auxiliary models helps the main model effectively focus on ambiguous areas, while the enforced consistency between models facilitates the acquisition of low-uncertainty decision boundaries. CC-Net has been validated in two public datasets. Compared to current state-of-the-art algorithms under specific proportions of annotated data, CC-Net demonstrates the best performance in semi-supervised segmentation. Our code is publicly available at https://github.com/Cuthbert-Huang/CC-Net. •Effective use of unlabeled data from the perspective of complementary information.•The model consistency approach to learn complementary information.•An independent encoder structure for complementary consistency learning.•CC-Net show state-of-the-art semi-supervised segmentation performance.
ISSN:0010-4825
1879-0534
DOI:10.1016/j.compbiomed.2023.107368