Consistency and adversarial semi-supervised learning for medical image segmentation

Medical image segmentation based on deep learning has made enormous progress in recent years. However, the performance of existing methods generally heavily relies on a large amount of labeled data, which are commonly expensive and time-consuming to obtain. To settle above issue, in this paper, a no...

Full description

Saved in:
Bibliographic Details
Published in:Computers in biology and medicine Vol. 161; p. 107018
Main Authors: Tang, Yongqiang, Wang, Shilei, Qu, Yuxun, Cui, Zhihua, Zhang, Wensheng
Format: Journal Article
Language:English
Published: United States Elsevier Ltd 01.07.2023
Elsevier Limited
Subjects:
Adversarial learning
Brain tumors
Collaboration
Consistency
Datasets
Deep learning
Deep neural network
Discriminators
Glaucoma
Glioma
Image processing
Image segmentation
Internal Medicine
Mean teacher
Medical image segmentation
Medical imaging
Other
Semi-supervised learning
Skin diseases
Skin lesions
Training
Tumors
Deep neural network
Mean teacher
Adversarial learning
Semi-supervised learning
Medical image segmentation
ISSN:0010-4825, 1879-0534, 1879-0534
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Medical image segmentation based on deep learning has made enormous progress in recent years. However, the performance of existing methods generally heavily relies on a large amount of labeled data, which are commonly expensive and time-consuming to obtain. To settle above issue, in this paper, a novel semi-supervised medical image segmentation method is proposed, in which the adversarial training mechanism and the collaborative consistency learning strategy are introduced into the mean teacher model. With the adversarial training mechanism, the discriminator can generate confidence maps for unlabeled data, such that more reliable supervised information for the student network is exploited. In the process of adversarial training, we further propose a collaborative consistency learning strategy by which the auxiliary discriminator can assist the primary discriminator in achieving supervised information with higher quality. We extensively evaluate our method on three representative yet challenging medical image segmentation tasks: (1) skin lesion segmentation from dermoscopy images in the International Skin Imaging Collaboration (ISIC) 2017 dataset; (2) optic cup and optic disk (OC/OD) segmentation from fundus images in the Retinal Fundus Glaucoma Challenge (REFUGE) dataset; and (3) tumor segmentation from lower-grade glioma (LGG) tumors images. The experimental results validate the superiority and effectiveness of our proposal when compared with the state-of-the-art semi-supervised medical image segmentation methods. •Introduced adversarial mechanism can efficiently utilizing a small amount of labeled data and a large amount of unlabeled data.•Accurately segmenting medical images even with a small amount of labeled data.•Maintaining high performance across multiple medical image datasets.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0010-4825
1879-0534
1879-0534
DOI:10.1016/j.compbiomed.2023.107018