Kidney Stone Detection from CT images using Probabilistic Neural Network(PNN) and Watershed Algorithm

kidney stones scientifically known as renal calculus or nephrolith consist of dense crystal masses generally originate in the kidneys and pass through the urinary tract which includes urethra, bladder and ureters. Genetic, dietary and environmental causes can be associated with the occurrence and severity of kidney stones. Imaging studies play a vital part in the treatment of kidney stone patients. CT is a precise diagnostic procedure for gastrointestinal illnesses. In essence, CT sends x-rays in small pieces that are saved on the screen as photographs from the body. The proposed method involves the diagnosis of kidney stones using image processing techniques such as pre-processing,segmentation,feature extraction and classification etc. In the initial stage the salt and pepper noise is removed by using a 3x3 median filter and discrete wavelet transform (DWT).K-Means clustering algorithm is used after segmenting the kidney stones using the watershed segmentation algorithm. The key objective of this study is to extract the features of segmented kidney stones by using the Grey level co-occurrence matrix(GLCM) and classify it using Probabilistic Neural Network (PNN) .The results we got indicate that 194 and 107 as the maximum sensitivity and maximum specificity point which was higher than the conventional renal calculus detection approaches.Also our proposed framework achieves an overall accuracy of 86.8%.