Abstract
The aim of this research is to detect kidney stones using U_Net, one of the most important and powerful deep neural networks for processing medical images taken from magnetic resonance imaging (MRI). This research focuses on locating kidney stones with high accuracy by processing and analyzing MRI images. The U_Net model was trained on a set of 1000 images to maximize the training potential for accurate results and analysis. The goal of this research is to help doctors in the speed of diagnosis and accurate localization. The induction methodology is summarized in several stages: data collection and processing, model design, model training, and then the stage of testing the efficiency of the system compared to other systems.

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright (c) 2025 Iraqi Journal of Intelligent Computing and Informatics (IJICI)