Employing Advanced Deep Learning Technology for the Detection of Kidney Stones in Unenhanced Computed Tomography (CT) Imaging: A Model-Based Approach

Abstract

Kidney stones are currently considered a very common disease and recent studies have shown a tendency for the incidence of this disease to increase in recent years. The disease is recognized as a serious threat to the population's health because it is associated with other serious illnesses that can greatly compromise people's quality of life. The development of technologies and strategies aimed at aiding the diagnosis and treatment of this disease has the potential to improve the quality and effectiveness of services provided by health professionals. Diagnosis based on medical images has been one of the main tools for diagnosing kidney stones and Deep Learning techniques have been widely proposed to perform this task. This study proposes a Deep Learning model for detecting kidney stones in computed tomography images. The model was trained with a dataset composed of images obtained from individuals who underwent examinations to analyze diseases in the urinary system. The model achieved an accuracy rate of 96.20% in its predictions and proved to be a suitable tool for treating the problem in question. The results obtained in this study demonstrate the potential of Deep Learning techniques as tools to help improve healthcare procedures related to imaging diagnosis.