Deep-learning-based method for the segmentation of ureter and renal pelvis on non-enhanced CT scans
Scientific Reports · 30.08.2024 · 14 (1)
DOI: 10.1038/s41598-024-71066-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Scientific Reports, online erschienen am 30.08.2024. Verfasst von Xin Jin und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Marine Science and Technology, Shandong University, Qingdao, China. Hauptthemen laut MEDLINE: Deep Learning, Kidney Pelvis, Tomography, X-Ray Computed, Ureter. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
This study aimed to develop a deep-learning (DL) based method for three-dimensional (3D) segmentation of the upper urinary tract (UUT), including ureter and renal pelvis, on non-enhanced computed tomography (NECT) scans. A total of 150 NECT scans with normal appearance of the left UUT were chosen for this study. The dataset was divided into training (n = 130) and validation sets (n = 20). The test set contained 29 randomly chosen cases with computed tomography urography (CTU) and NECT scans, all with normal appearance of the left UUT. An experienced radiologist marked out the left renal pelvis and ureter on each scan. Two types of frameworks (entire and sectional) with three types of DL models (basic UNet, UNet3 + and ViT-UNet) were developed, and evaluated. The sectional framework with basic UNet model achieved the highest mean precision (85.5%) and mean recall (71.9%) on the test set compared to all other tested methods. Compared with CTU scans, this method had higher axial UUT recall than CTU (82.5% vs 69.1%, P < 0.01). This method achieved similar or better visualization of UUT than CTU in many cases, however, in some cases, it exhibited a non-ignorable false-positive rate. The proposed DL method demonstrates promising potential in automated 3D UUT segmentation on NECT scans. The proposed DL models could remarkably improve the efficiency of UUT reconstruction, and have the potential to save many patients from invasive examinations such as CTU. DL models could also serve as a valuable complement to CTU.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Marine Science and Technology, Shandong University, Qingdao, China.
- Department of Radiology, Second Hospital of Shandong University, Jinan, China.
- Department of Urology, Second Hospital of Shandong University, Jinan, China. zcj810616@sina.com.
ORCID-Profile: Yumeng Zhang
Zitieren
APA
Jin, X., Zhong, H., Zhang, Y., & Pang, G. D. (2024). Deep-learning-based method for the segmentation of ureter and renal pelvis on non-enhanced CT scans. Scientific Reports, 14(1). https://doi.org/10.1038/s41598-024-71066-2
Vancouver
Jin X, Zhong H, Zhang Y, Pang GD. Deep-learning-based method for the segmentation of ureter and renal pelvis on non-enhanced CT scans. Scientific Reports. 2024;14(1). doi:10.1038/s41598-024-71066-2
BibTeX
@article{Jin2024,
author = {Jin, Xin and Zhong, Hai and Zhang, Yumeng and Pang, Guo Dong},
title = {Deep-learning-based method for the segmentation of ureter and renal pelvis on non-enhanced CT scans},
journal = {Scientific Reports},
year = {2024},
volume = {14},
number = {1},
doi = {10.1038/s41598-024-71066-2}
}
EUVIMED