Kidney Stone Detection Using Deep Learning Model Kidney Stone Detection Using Deep Learning Model Kidney Stone Detection Using Deep Learning Model

Detection of kidney stones from CT scan images has great importance in medical diagnosis. However, this is time-consuming and might be prone to human error, since the doctors need to go through every scan manually. In this respect, the current study proposes the use of a technique for automatic kidney stone detection using a CNN integrated with a Flask-based web application. The preprocessing of abdominal CT images includes resizing, normalizing, and augmenting to maintain consistency in quality and enhance the learning ability of the model. The proposed CNN is trained to classify images into two classes, namely “Stone” and “Normal.” Once the training is over, the model is saved and deployed in a lightweight web interface where users can upload CT images and get instant predictions. It also contains a statistics module showing accuracy analysis live from the results generated during testing. This would give crystal-clear insight into the model’s performance and reliability. Experimental observations have given sufficient evidence that deep learning integrated with a simple web framework presents a practical, efficient, and accessible solution to support the early detection of kidney stones.