Segmentation of Magnetic Resonance Images Using Discrete Curve Evolution and Fuzzy Clustering

The region clustering of a magnetic resonance imaging (MRI) image is more complicate than a computed topography (CT) image because a MRI image composes of three components such as Tl -weighted, T2-weighted, and proton density (PD) in each layer. However, the MRI images provide more detail than the CT images. Therefore, we propose a technique of the region clustering of MRI image by using fuzzy c-means (PCM). The fuzzy c-means algorithm is an iterative operation, that is very time-consuming and makes the algorithm impractical for using in image segmentation. To cope with this problem, the discrete curve evolution (DCE) technique is applied to find the actual cluster center to refine the initial value of the fuzzy c-means algorithm, which reduces the convergence time. In experimental results, the proposed technique provides the same segmentation accuracy as the fuzzy c-means technique. Moreover, this technique takes lower computational time comparing to the previous method.