Deep Learning-Based Kidney Disease Classification Using ResNet50: Enhancing Diagnostic Accuracy

Kidney disease is a significant global health issue affecting millions, with various abnormalities, such as stones and cysts, that are often preventable or curable. However, these conditions can progress to more severe forms, including kidney tumors or chronic kidney disease (CKD). Early detection of CKD is crucial to prevent disease progression, thereby reducing mortality rates and treatment costs. This study aims to develop a deep learning model capable of accurately detecting and classifying multiple kidney abnormalities in computed tomography (CT) scans. Using the ResNet-50 architecture, the model was trained to distinguish between healthy kidneys and three specific abnormalities—cysts, tumors, and stones—with a high classification accuracy of 99.6%. The results demonstrate the model’s potential as a valuable tool in early kidney disease diagnosis, enhancing clinical decision-making and patient outcomes