KIDNEY STONE DETECTION USING IMAGE SEGMENTATION

Abstract: The need for computer-aided medical diagnostics has grown in recent years as the population's need for medical care has risen. Because to advancements in imaging technology, Computed Tomography (CT) image-based diagnosis has become commonplace due to its cheap cost, reliability, and non-invasive nature. Images of the anomaly, such as a tumour, cyst, stone, etc., are analysed using feature extraction, analysis, and pattern recognition methods to locate the problem. The imaging technique of kidney-urinary-belly computed tomography (KUB CT) has the power to enhance kidney stone screening. As the population's need for medical care has increased, so has the demand for computer-aided medical diagnostics. Computed Tomography (CT) image-based diagnosis has grown widespread as a result of advances in imaging technology because of its low cost, dependability, and non-invasive nature. In order to identify the issue, feature extraction, analysis, and pattern recognition algorithms are used to analyse images of the anomaly, such as a tumour, cyst, stone, etc. The imaging method known as kidney-urinary-belly computed tomography (KUB CT) has the potential to improve the detection and prognosis of kidney stones. This study (CLAHE) focuses on effective computer-assisted medical diagnosis using KUB CT kidney images using contrast-limited adaptive diagram equal sign. Success depends on many factors, including segmentation, feature selection, reference database size, computational performance, etc.

Keywords: kidney stones, computed tomography, image processing