A Novel Hybrid Approach Using Kmeans Clustering and Threshold filter for Brain Tumor
Detection S. S. Mankikar · 2013
Medical imaging makes use of the technology to disclose the internal structure of the human body. By means of medical imaging modalities patient's life can be better through a accurate and quick treatment without any side effects. The foremost purpose of this paper is to develop an automated framework that can accurately classify a tumor from abnormal tissues. In this paper, we put forward a hybrid framework that uses the K-means clustering followed by Threshold filter to track down the tumor objects in magnetic resonance (MR) brain images. The main concept in this hybrid framework is to separate the position of tumor objects from other items of an MR image by using Kmeans clustering and Threshold filter. Experiments reveal that the method can successfully achieve segmentation for MR brain images to help pathologists distinguish exactly lesion size and region.