Kidney Stone Detection using Machine Learning

This study explores various automated approaches for detecting kidney stones using CT scan images, focusing on deep learning and image processing techniques [1]​. One approach leverages the XResNet152 deep learning architecture, involving preprocessing, data augmentation, and extensive training to achieve high accuracy in distinguishing stones from normal structures [2]​. Another method emphasizes image processing techniques such as segmentation, histogram analysis, and adaptive super pixel techniques, effectively identifying kidney stones using MATLAB for image enhancement and analysis [3]​. A hybrid model combining Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) is also introduced, providing precise classification of stones, cysts, and tumours by reducing noise and accurately distinguishing stones from normal tissues [4]​. Additionally, an extended study using a 3D U-Net architecture and CNN classifier achieved a sensitivity of 0.86 and an AUC of 0.95, highlighting the effectiveness of the Res U-Net model for precise and reliable kidney stone detection.