Exploration and performance analysis of deep learning applications in spermatic vein ultrasound segmentation
Biomedical Physics & Engineering Express · 01.04.2026 · 12 (2) · 025041
DOI: 10.1088/2057-1976/ae4eed ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomedical Physics & Engineering Express, online erschienen am 18.03.2026. Verfasst von Yunhao Hu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, People's Republic of China. Hauptthemen laut MEDLINE: Deep Learning, Image Processing, Computer-Assisted, Veins, Varicocele. Die Arbeit nennt 29 Literaturangaben. Gefördert von: Shanghai Municipal Hospital Development Center.
Abstract (Originalsprache)
Background
Varicocele is a common cause of male infertility, with ultrasound (US) serving as the primary diagnostic tool. Current practice relies on manual, subjective measurements of the spermatic vein, which are time-consuming and lack reproducibility. Developing automated tools is hindered by scarce annotated data and intrinsic US challenges like low contrast and high noise. Obejectives. This study aimed to: (1) develop and validate an efficient semi-automated annotation workflow; (2) establish the first performance benchmark for automated spermatic vein segmentation using deep learning; (3) critically evaluate the efficacy of state-of-the-art and customised segmentation models for this specific task.
Methods
We proposed a semi-automated pipeline using the Segment Anything Model (SAM) with clinician refinement. Using the resulting dataset, we conducted a comprehensive benchmark, evaluating a baseline U-Net, advanced models (U-Net++, Attention U-Net, and RPA-UNet), and a proposed U-Net with deep supervision (UNet-DS). All models were assessed via leave-one-patient-out cross-validation and statistical tests.
Results
The ‘SAM+clinician’ workflow showed excellent agreement with expert annotation (Dice Similarity Coefficient(DSC) = 92.66%; Kappa = 91.92%). In segmentation, the baseline U-Net achieved a mean DSC of 61.33%. Only Attention U-Net showed a statistically significant improvement ( p = 0.0391). UNet-DS attained the mean DSC (64.65%) but this was not statistically significant ( p = 0.0781). All models plateaued in a narrow range (DSC: 61%–65%), far below performance in mature US segmentation domains.
Conclusion
This work validates an efficient semi-automated annotation solution and establishes the first performance benchmark for this task. Results reveal a distinct performance ceiling, indicating the primary barrier is the inherent data limitations, not model architecture. Future breakthroughs require a shift towards bespoke, physics-informed algorithms rather than applying generic deep learning models.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, People's Republic of China.
- Department of Ultrasound, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, People's Republic of China.
ORCID-Profile: Yunhao Hu, Penglin Zou, Rongguo Yan
Förderung
- Shanghai Municipal Hospital Development Center
Zitieren
APA
Hu, Y., Zou, P., Yan, R., Zeng, X., & Wang, Q. (2026). Exploration and performance analysis of deep learning applications in spermatic vein ultrasound segmentation. Biomedical Physics & Engineering Express, 12(2), 025041. https://doi.org/10.1088/2057-1976/ae4eed
Vancouver
Hu Y, Zou P, Yan R, Zeng X, Wang Q. Exploration and performance analysis of deep learning applications in spermatic vein ultrasound segmentation. Biomedical Physics & Engineering Express. 2026;12(2):025041. doi:10.1088/2057-1976/ae4eed
BibTeX
@article{Hu2026,
author = {Hu, Yunhao and Zou, Penglin and Yan, Rongguo and Zeng, Xiyun and Wang, Qi},
title = {Exploration and performance analysis of deep learning applications in spermatic vein ultrasound segmentation},
journal = {Biomedical Physics & Engineering Express},
year = {2026},
volume = {12},
number = {2},
pages = {025041},
doi = {10.1088/2057-1976/ae4eed}
}
EUVIMED