Enhanced Pelvic CT Segmentation via Deep Learning: A Study on Loss Function Effects
Journal of Imaging Informatics in Medicine · 2025
DOI: 10.1007/s10278-025-01550-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, 2025. Verfasst von Elnaz Ghaedi und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Energy Engineering, Sharif University of Technology, Tehran, 8639-11365, Iran. Hauptthemen laut MEDLINE: Deep Learning, Tomography, X-Ray Computed, Pelvis, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Effective radiotherapy planning requires precise delineation of organs at risk (OARs), but the traditional manual method is laborious and subject to variability. This study explores using convolutional neural networks (CNNs) for automating OAR segmentation in pelvic CT images, focusing on the bladder, prostate, rectum, and femoral heads (FHs) as an efficient alternative to manual segmentation. Utilizing the Medical Open Network for AI (MONAI) framework, we implemented and compared U-Net, ResU-Net, SegResNet, and Attention U-Net models and explored different loss functions to enhance segmentation accuracy. Our study involved 240 patients for prostate segmentation and 220 patients for the other organs. The models' performance was evaluated using metrics such as the Dice similarity coefficient (DSC), Jaccard index (JI), and the 95th percentile Hausdorff distance (95thHD), benchmarking the results against expert segmentation masks. SegResNet outperformed all models, achieving DSC values of 0.951 for the bladder, 0.829 for the prostate, 0.860 for the rectum, 0.979 for the left FH, and 0.985 for the right FH (p < 0.05 vs. U-Net and ResU-Net). Attention U-Net also excelled, particularly for bladder and rectum segmentation. Experiments with loss functions on SegResNet showed that Dice loss consistently delivered optimal or equivalent performance across OARs, while DiceCE slightly enhanced prostate segmentation (DSC = 0.845, p = 0.0138). These results indicate that advanced CNNs, especially SegResNet, paired with optimized loss functions, provide a reliable, efficient alternative to manual methods, promising improved precision in radiotherapy planning.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Energy Engineering, Sharif University of Technology, Tehran, 8639-11365, Iran.
- Department of Energy Engineering, Sharif University of Technology, Tehran, 8639-11365, Iran. sahosseini@sharif.edu.
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, CH-1211, Switzerland.
Zitieren
APA
Ghaedi, E., Asadi, A., Hosseini, S. A., & Arabi, H. (2025). Enhanced Pelvic CT Segmentation via Deep Learning: A Study on Loss Function Effects. Journal of Imaging Informatics in Medicine. https://doi.org/10.1007/s10278-025-01550-2
Vancouver
Ghaedi E, Asadi A, Hosseini SA, Arabi H. Enhanced Pelvic CT Segmentation via Deep Learning: A Study on Loss Function Effects. Journal of Imaging Informatics in Medicine. 2025. doi:10.1007/s10278-025-01550-2
BibTeX
@article{Ghaedi2025,
author = {Ghaedi, Elnaz and Asadi, Ali and Hosseini, Seyed Abolfazl and Arabi, Hossein},
title = {Enhanced Pelvic CT Segmentation via Deep Learning: A Study on Loss Function Effects},
journal = {Journal of Imaging Informatics in Medicine},
year = {2025},
doi = {10.1007/s10278-025-01550-2}
}
EUVIMED