AN EFFICIENT BRAIN TUMOR DETECTION USINGMODIFIED K-MEANS CLUSTERING BASED ON SVM

Automatic defects detection in MR images is very important in many diagnostic and curative applications. Because of high quantity data in MR images and blurred boundaries, tumor segmentation and classification is very hard. This work has introduced one automatic brain tumor detection method to increase the accuracy and to decreases the diagnosis time. The main goal is to classify the tissues into normal, benign and malignant. In MR images, the amount of data is too much for manual clarification and analysis. In Medical imaging system, brain tumor segmentation in magnetic resonance imaging (MRI) has become an emergent research area in the field for past few years. In diagnosis method detecting the location and size of tumor places a vital role. This method consists of four stages, pre-processing of MR images, feature selection, feature extraction, classification and clustering. Image segmentation is based on Watershed Transform and Feature extraction is based on GLCM. Support vector machine (SVM) is employed to classify the Normal and Abnormal brain. After that, support vector machine (SVM) result is compared with probabilistic neutral network to show the efficiency. At last if the output is abnormal it moves to k-means clustering.