Nephrolithiasis Detection and Classification Based on Supervised Machine Learning
DOI:
https://doi.org/10.47852/bonviewJDSIS52024777Keywords:
CT images, image processing techniques, effective stone detection, median filter, stone diseases, DWT feature extractionAbstract
In this paper, the author will provide an extensive exploration of the utilization of computed tomography (CT) image processing techniques for the detection of renal calculi. This is one of the most essential topics worldwide to detect the correct location of renal calculi. In the human system, the two kidneys play a crucial role in water purification and recycling. This research involves four steps: Graphic processing with a median filter, segmentation with the Otsu segmentation algorithm, nephrolithiasis detection, and discrete wavelet transform feature extraction and classification. Data from a large number of hospital patients were collected with CT scans, which diagnose renal calculi. This research studies advanced techniques to detect the extent, segment the area, and improve the detection of kidney stones or normal. This analysis helps locate the rocks through pixel analysis. The system also shows many stone patients. Specifically, the system was refined through a dataset of 1,200 X-ray images, a cubic support vector machine achieved 89.3% training accuracy with five-fold cross-validation to avoid overfitting, and an area under the curve close to 0.85, and the receiver operating characteristic curve is close to one. Its outstanding performance on unseen data led to a 90% testing accuracy, demonstrating its robustness using MATLAB and Python IDLE simulator
Received: 12 November 2024 | Revised: 3 March 2025 | Accepted: 10 June 2025
Conflicts of Interest
The author declares that he has no conflicts of interest to this work.
Data Availability Statement
The data that support the findings of this study are openly available
in GitHub at https://github.com/junaid-1013/Kidney-Stone-Detection,
https://github.com/muhammedtalo/Kidney_stone_detection, and in
Kaggle at https://www.kaggle.com/datasets/nazmul0087/ct-kidney-dataset-normal-cyst-tumor-and-stone.
Author Contribution Statement
Ei Phyu Sin Win: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Supervision, Project administration.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Author

This work is licensed under a Creative Commons Attribution 4.0 International License.