Semi-Supervised Representation Learning for Segmentation on Medical Volumes and Sequences

Benefiting from the massive labeled samples, deep learning-based segmentation methods have achieved great success for two dimensional natural images. However, it is still a challenging task to segment high dimensional medical volumes and sequences, due to the considerable efforts for clinical expert...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on medical imaging Vol. 42; no. 12; pp. 3972 - 3986
Main Authors: Chen, Zejian, Zhuo, Wei, Wang, Tianfu, Cheng, Jun, Xue, Wufeng, Ni, Dong
Format: Journal Article
Language:English
Published: United States IEEE 01.12.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Annotations
Biomedical imaging
Coders
contrastive learning
Datasets
Decoding
Deep learning
Feature maps
Humans
Image Processing, Computer-Assisted
Image segmentation
Male
Medical volume segmentation
Pelvis
Performance enhancement
Prostate
Representation learning
Representations
Segmentation
Semantics
semi-supervised
Semi-supervised learning
Supervised Machine Learning
Task analysis
Teaching methods
Training
ISSN:0278-0062, 1558-254X, 1558-254X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Benefiting from the massive labeled samples, deep learning-based segmentation methods have achieved great success for two dimensional natural images. However, it is still a challenging task to segment high dimensional medical volumes and sequences, due to the considerable efforts for clinical expertise to make large scale annotations. Self/semi-supervised learning methods have been shown to improve the performance by exploiting unlabeled data. However, they are still lack of mining local semantic discrimination and exploitation of volume/sequence structures. In this work, we propose a semi-supervised representation learning method with two novel modules to enhance the features in the encoder and decoder, respectively. For the encoder, based on the continuity between slices/frames and the common spatial layout of organs across subjects, we propose an asymmetric network with an attention-guided predictor to enable prediction between feature maps of different slices of unlabeled data. For the decoder, based on the semantic consistency between labeled data and unlabeled data, we introduce a novel semantic contrastive learning to regularize the feature maps in the decoder. The two parts are trained jointly with both labeled and unlabeled volumes/sequences in a semi-supervised manner. When evaluated on three benchmark datasets of medical volumes and sequences, our model outperforms existing methods with a large margin of 7.3% DSC on ACDC, 6.5% on Prostate, and 3.2% on CAMUS when only a few labeled data is available. Further, results on the M&M dataset show that the proposed method yields improvement without using any domain adaption techniques for data from unknown domain. Intensive evaluations reveal the effectiveness of representation mining, and superiority on performance of our method. The code is available at https://github.com/CcchenzJ/BootstrapRepresentation .
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0278-0062
1558-254X
1558-254X
DOI:10.1109/TMI.2023.3319973