Research Of MRI Brain Images Segmentation

Three different methods for MRI brain image segmentation are proposed in this paper.The first segmentation method in this paper is based on watershed algorithm, fuzzy clustering algorithm, Minimum Covariance Determinant (MCD) estimator and k-Nearest Neighbor (kNN) classifier. Firstly, watershed algorithm is applied to brain tissues as an initial segmenting method. Normally, result of classical watershed algorithm on gray-scale textured images such as tissue images is over-segmentation. The following procedure is a merging process for the over-segmentation regions using Fuzzy C-Means algorithm. But there are still some regions which are not divided completely due to the low contrast in them. We exploite a method base on Minimum Covariance Determinant (MCD) estimator to detect the regions needed segmentation again, and then partition them by a supervised k-Nearest Neighbor (kNN) classifier. This integrated approach yields a robust and precise segmentation. The efficacy of the proposed algorithm is validated using extensive experiments.Kohonen's competitive learning network is a two-layer feedforward network, and has been used in brain MRI image segmentation. However, most brain MRI images always present overlapping gray-scale intensities for different tissues. In the second segmentation method of this paper, fuzzy methods are integrated with Kohonen's competitive algorithm to overcome this problem (F_KCL). Moreover, in order to enhancing the robustness to noise and outliers, a kernel induced method is exploited in our study to measure the distance between the input vector and the weights. The efficacy of our approach is validated by extensive experiments using both simulated and real MRI images.The third algorithm in this paper is a modified FCM algorithm for MRI image segmentation. MRI images always contain a significant amount of noise which makes accurate segmentation difficult. The proposed method incorporates both the local spatial context and the non-local information into the conventional Fuzzy c-means (FCM) cluster algorithm using a novel dissimilarity index in place of the usual distance metric. The efficacy of the proposed algorithm is demonstrated by extensive segmentation experiments using both simulated and real MR images and by comparison with other published algorithms.