Chronic Kidney Diseases (CKD) are a major health issue and about 10% of the population worldwide are affected by CKDs, as a consequence of this millions of people die each year. Alongside that it has been estimated that the number of cases of kidney failures will increase abnormally in developing countries as time passes. Our work will provide all those at risk a quick and accurate way to detect CKDs that are caused by kidney Cysts, Stones or Tumor. We have made performance comparisons of different deep learning algorithms that can detect such CKDs from CT-Radiography scans and compared their performances to figure out which is the best way to identify it. The algorithms that we have worked on in our project include VGG16, ResNet50, MobileNetV2 and InceptionV3. The inclusion of Deep Learning in a field such as kidney disease detection can help speed up the detection process of the diseases and even help with early detection.

From our extensive research we have come to the conclusion that it is possible to detect kidney cysts, stones and tumors using deep learning algorithms in an accurate manner. Among the models we have tested, the best performing model was MobileNetV2 and the worst performing was ResNet50 with the other models performing well enough to a satisfactory level.