User: Guest  Login
Title:

Causality-Inspired Single-Source Domain Generalization for Medical Image Segmentation.

Document type:
Journal Article
Author(s):
Ouyang, Cheng; Chen, Chen; Li, Surui; Li, Zeju; Qin, Chen; Bai, Wenjia; Rueckert, Daniel
Abstract:
Deep learning models usually suffer from the domain shift issue, where models trained on one source domain do not generalize well to other unseen domains. In this work, we investigate the single-source domain generalization problem: training a deep network that is robust to unseen domains, under the condition that training data are only available from one source domain, which is common in medical imaging applications. We tackle this problem in the context of cross-domain medical image segmentati...     »
Journal title abbreviation:
IEEE Trans Med Imaging
Year:
2023
Journal volume:
42
Journal issue:
4
Pages contribution:
1095-1106
Fulltext / DOI:
doi:10.1109/TMI.2022.3224067
Pubmed ID:
http://view.ncbi.nlm.nih.gov/pubmed/36417741
Print-ISSN:
0278-0062
TUM Institution:
Institut für KI und Informatik in der Medizin
 BibTeX