EUVIMEDPoznaj EUVIMED
Crossref

A novel cross‐modal data augmentation method based on contrastive unpaired translation network for kidney segmentation in ultrasound imaging

Shuaizi Guo, Xiangyu Sheng, Haijie Chen, Jie Zhang, Qinmu Peng, Menglin Wu, Katherine Fischer, Gregory E Tasian, Yong Fan, Shi Yin

Medical Physics · 2025

DOI: 10.1002/mp.17663 ↗

At a glance

Journal article in Medical Physics, 2025. Written by Shuaizi Guo and 9 co-authors. Institution: College of Computer and Information Engineering, Nanjing Tech University, Nanjing, China. Major MEDLINE topics: Kidney, Image Processing, Computer-Assisted. Cited 4 times so far (Crossref); 39 references. Funded by: Natural Science Foundation of Jiangsu Province Youth Project, NIH HHS, National Institutes of Health.

AbstraktSubjectsDane bibliograficzneCiteRelated studies

Abstract (original language)

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.

Subjects

MeSH terms (MEDLINE)

KidneyImage Processing, Computer-AssistedUltrasonographyHumansDeep Learning

Author keywords

CT datacontrastive unpaired translation networkcross‐modal data augmentationdeep learningkidney ultrasound image segmentation

Authors and institutions

  • 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.

Funding

  • Natural Science Foundation of Jiangsu Province Youth Project
  • NIH HHS
  • National Institutes of Health

Cite

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}
}
Start for free →