Multiple kidney disease prediction using deep learning algorithm

Renal calculus, also known as renal disease formation, is a condition in which crystals form in the urine as a result of a chemical concentration or hereditary vulnerability. Even infants are susceptible to kidney illness, and yet the majority of kidney disease cases go unnoticed, especially in cases where significant abdominal pain or an irregular urine color is present. Furthermore, frequent symptoms of renal disease include fever, discomfort, and nausea, which can be mistaken for other illnesses. Kidney disease diagnosis is critical, especially in the early stages, to allow for intervention or appropriate medical therapy. Kidney disease reduces kidney function and causes dilatation of the kidneys when it is present or recurs. This paper describes a method for detecting kidney disorders using various image processing stages. The first phase is image pre-processing with filters, in which the image is smoothed and noise is removed. Next, the image segmentation is performed on the preprocessed image using guided active contour method. Then using Back propagation neural network algorithm to identify the diseases in kidney images. Experimental results show that the proposed deep learning provides improved accuracy in disease prediction.