Rethinking adversarial domain adaptation: Orthogonal decomposition for unsupervised domain adaptation in medical image segmentation.
Med Image Anal
; 82: 102623, 2022 11.
Article
in English
| MEDLINE | ID: covidwho-2042023
ABSTRACT
Medical image segmentation methods based on deep learning have made remarkable progress. However, such existing methods are sensitive to data distribution. Therefore, slight domain shifts will cause a decline of performance in practical applications. To relieve this problem, many domain adaptation methods learn domain-invariant representations by alignment or adversarial training whereas ignoring domain-specific representations. In response to this issue, this paper rethinks the traditional domain adaptation framework and proposes a novel orthogonal decomposition adversarial domain adaptation (ODADA) architecture for medical image segmentation. The main idea behind our proposed ODADA model is to decompose the input features into domain-invariant and domain-specific representations and then use the newly designed orthogonal loss function to encourage their independence. Furthermore, we propose a two-step optimization strategy to extract domain-invariant representations by separating domain-specific representations, fighting the performance degradation caused by domain shifts. Encouragingly, the proposed ODADA framework is plug-and-play and can replace the traditional adversarial domain adaptation module. The proposed method has consistently demonstrated effectiveness through comprehensive experiments on three publicly available datasets, including cross-site prostate segmentation dataset, cross-site COVID-19 lesion segmentation dataset, and cross-modality cardiac segmentation dataset. The source code is available at https//github.com/YonghengSun1997/ODADA.
Keywords
Full text:
Available
Collection:
International databases
Database:
MEDLINE
Main subject:
COVID-19
Type of study:
Randomized controlled trials
Limits:
Humans
Language:
English
Journal:
Med Image Anal
Journal subject:
Diagnostic Imaging
Year:
2022
Document Type:
Article
Affiliation country:
J.media.2022.102623
Similar
MEDLINE
...
LILACS
LIS