Segmentation Of Brain Tumor And Its Area Measurement Using Gradient Vector Flow Deformable Model For MR Images

Abstract

Detection and treatment planning of a brain tumor in human brain is a challenging task. Various types of tumors with different characteristics required different treatment planning. The survey on brain tumor cancer proves that, most of the people who have brain tumors were died due to the inaccurate diagnosis of brain tumor. In general, the MR images of the brain which are acquired from the MRI scanner are used as the data for the segmentation and classification of brain tumors. In order to differentiate normal and abnormal tumors it is required to segment the MR images of the brain. Due to the diversity and complexity and of MR images, the Gradient Vector Flow (GVF) Deformable model is applied for the segmentation of brain tumor. The experimental results shows that the proposed GVF has got improved segmentation accuracy, less computational complexity and fast convergence towards the object boundary. After the segmentation, the binary image is obtained by thresholding technique to measure its area for the tumor classification.