International Journal of Computer Applications (0975 – 8887) Volume 164 – No 9, April 2017 1 Kidney Tumor Segmentation and Classification on Abdominal CT Scans Bansari Shah Student of Computer Engineering K J Somaiya COE Vidyavihar Charmi Sawla Student of Computer Engineering K J Somaiya COE Vidyavihar Shraddha Bhanushali Student of Computer Engineering K J Somaiya COE Vidyavihar Poonam Bhogale Assistant Professor of Computer Engineering K J Somaiya COE Vidyavihar ABSTRACT This paper, deals with systematic study of simple segmentation and classification algorithms for kidney tumor using Computed Tomography images. Tumors are of different types having different characteristics and also have different treatment. It becomes very important to detect the tumor and classify it at the early stage so that appropriate treatment can be planned. This CT scans are visually examined by the physician for detection and diagnosis of kidney tumor. However this method lacks accuracy and detection of size of the tumor. So to overcome this, a computer aided segmentation technique has been proposed, which extracts the tumor part from the kidney, further on which feature extraction method is performed for extracting certain features and the type of tumor i.e. malignant or benign is displayed by using simple classifiers . General Terms Algorithms, Kidney Tumor, Computed Tomography scans, Process. Keywords Pre-processing, Fuzzy C-means, Grey Level Co-occurrence Matrix, K Nearest Neighbour classifier, Support Vector Machine classifier 1. INTRODUCTION Human body consists of myriad number of cells[5]. For a body to remain healthy, cells grow and divide in orderly fashion. When cell growth becomes uncontrollable the extra mass of cell transforms into tumor. CT scans and MRI are used for identification of tumor[5]. The goal of the system is to detect tumor by incorporating image processing, pattern analysis, and computer vision techniques for enhancement, segmentation and classification for kidney diagnosis, as shown in Fig 1.. This system can be used by radiologists and healthcare specialists[1,2,9,10]. The system is expected to improve the sensitivity, specificity, and efficiency of kidney tumor screening. Tumor segmentation is done by fuzzy c- means algorithm , extraction of features is implemented by grey level co-occurrence matrix method (GLCM) and finally classification of tumor if it is benign or malignant is obtained by support vector machine tool (SVM) and k nearest neighbour classifier (KNN). Fig 1: Block Diagram Of Proposed System 2. SEGMENTATION 2.1 Fuzzy C-Means Clustering Algorithm A. Fuzzy Clustering The fuzzy logic is used to process data by giving the partial membership value to each pixel in the image. The membership value of the fuzzy set ranges between 0 and 1. Fuzzy clustering is a multi valued logic system that uses