Segmentation of Brain MRI Image with GVF Snake Model

Medical image segmentation is the foundation and research focus in the medical image processing field. In this paper the normalized GVF Snake model combines with traditional edge detection is proposed for the brain MRI image semiautomatic segmentation. The thinning Canny result is used to calculate the edge map gradient of the GVF snake model. Then the normalized GVF snake model deforms with the manual initial contour. Simulation results show that this method can extract the boundary of the tumor accurately, and the method can overcome the problem that traditional GVF snake cannot efficient converge to the weak boundary. The method has positive significance in practical applications.