Invariant Content Representation for Generalizable Medical Image Segmentation
Journal of Imaging Informatics in Medicine · 17.05.2024 · 37 (6) · 3193-3207
DOI: 10.1007/s10278-024-01088-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, online erschienen am 17.05.2024. Verfasst von Zhiming Cheng und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation, Hangzhou Dianzi University, Hangzhou, 310018, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Natural Science Foundation of Zhejiang Province, National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province.
Abstract (Originalsprache)
Domain generalization (DG) for medical image segmentation due to privacy preservation prefers learning from a single-source domain and expects good robustness on unseen target domains. To achieve this goal, previous methods mainly use data augmentation to expand the distribution of samples and learn invariant content from them. However, most of these methods commonly perform global augmentation, leading to limited augmented sample diversity. In addition, the style of the augmented image is more scattered than the source domain, which may cause the model to overfit the style of the source domain. To address the above issues, we propose an invariant content representation network (ICRN) to enhance the learning of invariant content and suppress the learning of variability styles. Specifically, we first design a gamma correction-based local style augmentation (LSA) to expand the distribution of samples by augmenting foreground and background styles, respectively. Then, based on the augmented samples, we introduce invariant content learning (ICL) to learn generalizable invariant content from both augmented and source-domain samples. Finally, we design domain-specific batch normalization (DSBN) based style adversarial learning (SAL) to suppress the learning of preferences for source-domain styles. Experimental results show that our proposed method improves by 8.74% and 11.33% in overall dice coefficient (Dice) and reduces 15.88 mm and 3.87 mm in overall average surface distance (ASD) on two publicly available cross-domain datasets, Fundus and Prostate, compared to the state-of-the-art DG methods. The code is available at https://github.com/ZMC-IIIM/ICRN-DG .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Automation, Hangzhou Dianzi University, Hangzhou, 310018, China.
- School of Cyberspace, Hangzhou Dianzi University, Hangzhou, 310018, China. shuaiwang.tai@gmail.com.
- Suzhou Research Institute of Shandong University, SuZhou, 215123, China. shuaiwang.tai@gmail.com.
- Lishui Institute of Hangzhou Dianzi Universitu, Lishui, 323010, China.
- School of Communication, Engineering, Hangzhou Dianzi Universitu, Hangzhou, 310018, China.
ORCID-Profile: Zhiming Cheng
Förderung
- Natural Science Foundation of Zhejiang Province
- National Natural Science Foundation of China
- Natural Science Foundation of Jiangsu Province
Zitieren
APA
Cheng, Z., Wang, S., Gao, Y., Zhu, Z., & Yan, C. (2024). Invariant Content Representation for Generalizable Medical Image Segmentation. Journal of Imaging Informatics in Medicine, 37(6), 3193-3207. https://doi.org/10.1007/s10278-024-01088-9
Vancouver
Cheng Z, Wang S, Gao Y, Zhu Z, Yan C. Invariant Content Representation for Generalizable Medical Image Segmentation. Journal of Imaging Informatics in Medicine. 2024;37(6):3193-3207. doi:10.1007/s10278-024-01088-9
BibTeX
@article{Cheng2024,
author = {Cheng, Zhiming and Wang, Shuai and Gao, Yuhan and Zhu, Zunjie and Yan, Chenggang},
title = {Invariant Content Representation for Generalizable Medical Image Segmentation},
journal = {Journal of Imaging Informatics in Medicine},
year = {2024},
volume = {37},
number = {6},
pages = {3193--3207},
doi = {10.1007/s10278-024-01088-9}
}
EUVIMED