The incidence of kidney stones is common in hospitals and in the diagnostic centers. Early recognition of stones prevents the occurrence of additional health issues. Kidney stones are normally diagnosed by use of CT scans, ultrasound images or X-ray images in normal practice. Clinicians usually analyze these images and the analysis can be quite different based on the clarity of the image and personal experience. This paper presents a description of a basic kidney stone analysis system based on a web. The renal image provided by the user is optimized to enhance the view of stone regions. The convolutional neural network is applied to verify the image of kidney stones. In case of a stone that appears, it is followed with an image that will help to calculate the approximate size of a stone and its location in the kidney region. According to the size obtained, the basic treatment-related information is presented as a reference. It is written in the Django framework and has an interface that uploads images and displays results in a simple interface. The objective of the system is to guide preliminary analysis and save the manual work routinely, whereas clinical judgments remain in the hands of the medical professionals.
Siva et al. (2026) studied this question.