A comparative analysis of U-Net-based architectures for robust segmentation of bladder cancer lesions in magnetic resonance imaging
Eurasian Journal of Medicine and Oncology · 27.10.2025 · 9 (4) · 268
DOI: 10.36922/ejmo025260276 ↗Kurz gefasst
Fachartikel in der Zeitschrift Eurasian Journal of Medicine and Oncology, online erschienen am 27.10.2025. Verfasst von Ishak Pacal und 1 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref).
Abstract (Originalsprache)
Introduction
Bladder cancer (BCa) represents a significant uro-oncological challenge due to its aggressive nature and high recurrence rates. Although magnetic resonance imaging (MRI) is a cornerstone modality in BCa management, the manual segmentation of lesions is time-consuming and suffers from low reproducibility due to inter- and intra-observer variability, morphological heterogeneity, and MRI artifacts.
Objective
This study aims to address these limitations by conducting a rigorous comparative evaluation of four distinct U-Net-based deep learning architectures.
Methods
The models were evaluated using the publicly available, multi-center FedBCa dataset, comprising 275 T2-weighted MRI scans from 228 patients. Using a standardized training protocol, performance was rigorously assessed with a suite of quantitative metrics, including the Dice coefficient, intersection over union (IoU), and Hausdorff distance, supplemented by qualitative visual comparison.
Results
Cross-scale mixer U-Net (CMUNet) achieved the best overall performance, yielding the highest Dice coefficient (0.7937), IoU (0.7033), and boundary delineation accuracy (Hausdorff distance: 8.4550 mm. Architectural trade-offs were evident: CMUNeXt was the most computationally efficient and offered the highest lesion sensitivity (0.9656), whereas Attention U-Net recorded the highest precision (0.8380).
Conclusion
CMUNet provides the most balanced and accurate performance for BCa segmentation. However, the optimal architecture choice is application-dependent; high-sensitivity models such as CMUNeXt are ideal for screening, while high-precision models like Attention U-Net are better suited for treatment planning. Deep learning models serve as powerful assistive tools to improve efficiency and objectivity in clinical workflows, though expert oversight remains essential. The top model’s accuracy approached, but did not surpass, the inter-rater reliability of human experts (Dice: 0.870).
Zitieren
APA
Pacal, I., & Cakmak, Y. (2025). A comparative analysis of U-Net-based architectures for robust segmentation of bladder cancer lesions in magnetic resonance imaging. Eurasian Journal of Medicine and Oncology, 9(4), 268. https://doi.org/10.36922/ejmo025260276
Vancouver
Pacal I, Cakmak Y. A comparative analysis of U-Net-based architectures for robust segmentation of bladder cancer lesions in magnetic resonance imaging. Eurasian Journal of Medicine and Oncology. 2025;9(4):268. doi:10.36922/ejmo025260276
BibTeX
@article{Pacal2025,
author = {Pacal, Ishak and Cakmak, Yigitcan},
title = {A comparative analysis of U-Net-based architectures for robust segmentation of bladder cancer lesions in magnetic resonance imaging},
journal = {Eurasian Journal of Medicine and Oncology},
year = {2025},
volume = {9},
number = {4},
pages = {268},
doi = {10.36922/ejmo025260276}
}
EUVIMED