This project aims at classification of kidney stones through ML and DL approaches on computed tomographies. We worked with a variety of models which included basic model Support Vector Machine (SVM), logistic regression, a deep learning model Convolutional Neural Networks (CNN), deep learning models ResNet EfficientNet, MobileNet V2. The models were trained and tested using a set of CT scan images of selected patients that were arranged appropriately to identify their specialties in feature extraction as well as categorization. A comparative analysis was done in order to identify which outperformed the others in accuracy, time and model generalization. The results show that it is possible to achieve highly accurate and efficient methods of detection of kidney stones in medical images using deep learning algorithms, including but not limited to EfficientNet and MobileNet V2.