A novel cross‐modal data augmentation method based on contrastive unpaired translation network for kidney segmentation in ultrasound imaging
Medical Physics · 2025
DOI: 10.1002/mp.17663 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, 2025. Verfasst von Shuaizi Guo und 9 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Information Engineering, Nanjing Tech University, Nanjing, China. Hauptthemen laut MEDLINE: Kidney, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: Natural Science Foundation of Jiangsu Province Youth Project, NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
Background
Kidney ultrasound (US) image segmentation is one of the key steps in computer‐aided diagnosis and treatment planning of kidney diseases. Recently, deep learning (DL) technology has demonstrated promising prospects in automatic kidney US segmentation. However, due to the poor quality, particularly the weak boundaries in kidney US imaging, obtaining accurate annotations for DL‐based segmentation methods remain a challenging and time‐consuming task. This issue can hinder the application of data‐hungry deep learning methods.
Purpose
In this paper, we explore a novel cross‐modal data augmentation method aimed at enhancing the performance of DL‐based segmentation networks on the limited labeled kidney US dataset.
Methods
In particular, we adopt a novel method based on contrastive unpaired translation network (CUT) to obtain simulated labeled kidney US images at a low cost from labeled abdomen computed tomography (CT) data and unlabeled kidney US images. To effectively improve the segmentation network performance, we propose an instance‐weighting training strategy that simultaneously captures useful information from both the simulated and real labeled kidney US images. We trained our generative networks on a dataset comprising 4418 labeled CT slices and 4594 unlabeled US images. For segmentation network, we used a dataset consisting of 4594 simulated and 100 real kidney US images for training, 20 images for validation, and 169 real images for testing. We compared the performance of our method to several state‐of‐the‐art approaches using the Wilcoxon signed‐rank test, and applied the Bonferroni method for multiple comparison correction.
Results
The experimental results show that we can synthesize accurate labeled kidney US images with a Fréchet inception distance of 52.52. Moreover, the proposed method achieves a segmentation accuracy of 0.9360 ± 0.0398 for U‐Net on normal kidney US images, and 0.7719 ± 0.2449 on the abnormal dataset, as measured by the dice similarity coefficient. When compared to other training strategies, the proposed method demonstrated statistically significant superiority, with all p ‐values being less than 0.01.
Conclusions
The proposed method can effectively improve the accuracy and generalization ability of kidney US image segmentation models with limited annotated training data.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Computer and Information Engineering, Nanjing Tech University, Nanjing, China.
- School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China.
- Carbon Medical Device Ltd, Shenzhen, China.
- Department of Surgery, Division of Pediatric Urology, The Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, USA.
- Center for Pediatric Clinical Effectiveness, The Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, USA.
- Department of Biostatistics, Epidemiology, and Informatics, The University of Pennsylvania, Philadelphia, Pennsylvania, USA.
Förderung
- Natural Science Foundation of Jiangsu Province Youth Project
- NIH HHS
- National Institutes of Health
Zitieren
APA
Guo, S., Sheng, X., Chen, H., Zhang, J., Peng, Q., Wu, M., Fischer, K., Tasian, G. E., Fan, Y., & Yin, S. (2025). A novel cross‐modal data augmentation method based on contrastive unpaired translation network for kidney segmentation in ultrasound imaging. Medical Physics. https://doi.org/10.1002/mp.17663
Vancouver
Guo S, Sheng X, Chen H, Zhang J, Peng Q, Wu M, et al. A novel cross‐modal data augmentation method based on contrastive unpaired translation network for kidney segmentation in ultrasound imaging. Medical Physics. 2025. doi:10.1002/mp.17663
BibTeX
@article{Guo2025,
author = {Guo, Shuaizi and Sheng, Xiangyu and Chen, Haijie and Zhang, Jie and Peng, Qinmu and Wu, Menglin and Fischer, Katherine and Tasian, Gregory E and Fan, Yong and Yin, Shi},
title = {A novel cross‐modal data augmentation method based on contrastive unpaired translation network for kidney segmentation in ultrasound imaging},
journal = {Medical Physics},
year = {2025},
doi = {10.1002/mp.17663}
}
EUVIMED