ORIGINAL RESEARCH article
Front. Med.
Sec. Nephrology
Optimized Urological Diagnostics based on Kidney Stone Detection in Clinical CT Imaging Using YOLOv8 Deep Learning Approach
Kavimbi Chipusu 1
Liuying He 2
Suo Shen 2
1. University of Saskatchewan, Saskatoon, Canada
2. Zhejiang Provincial People's Hospital Urology and Nephrology Center, Hangzhou, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Abstract
Kidney stone disease poses a growing global health challenge due to its increasing prevalence and potential for serious complications if left undiagnosed or untreated. Non-contrast computed tomography (CT) remains the gold standard for detecting renal calculi; however, the manual review of CT scans is time-consuming and prone to variability among radiologists. This study introduces the application of deep learning-based object detection model for automated kidney stone detection in abdominal CT images. Four state-of-the-art models, YOLOv8, YOLOv5, Faster R-CNN, and RetinaNet, were evaluated on a curated dataset of 4,000 annotated CT slices from both pre-and postsurgical patient groups. Performance metrics including mean Average Precision (mAP@0.5), precision, recall, false positive/negative rates, and inference speed were analyzed. YOLOv8 achieved a compelling balance between accuracy (mAP@0.91) and real-time inference capability (65 FPS), making it the most practical for clinical integration. While Faster R-CNN demonstrated superior localization accuracy (mAP@0.93), its slower inference speed limits its utility in time-sensitive environments. These findings highlight the potential of single-stage detectors, particularly YOLOv8, for enhancing diagnostic efficiency and consistency in urological imaging workflows.
Summary
Keywords
Clinical decision support, Kidney Stones, Medical Image Analysis, object detection, Real-time detection, YOLOv8
Received
09 September 2025
Accepted
17 February 2026
Copyright
© 2026 Chipusu, He and Shen. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Liuying He
Disclaimer
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.