Medical image segmentation has become an essential technique in clinical and research-oriented applications.MRI provides accurate anatomical brain images without use of ionizing radiation. For clinical use, the estimated values must be reliable and accurate,but many techniques fail on these criteria in an unrestricted clinical environment. Automated Magnetic Resonance Imaging (MRI) segmentation systems classify brain voxels into one of three main tissue types such as Gray Matter (GM), White Matter (WM) and Cerebro-Spinal Fluid (CSF). Volumetric analysis of different parts of the brain is useful in assessing the progress or remission of various diseases such as Alzheimer's disease, epilepsy, multiple sclerosis, and schizophrenia. In the existing methods segmentation was done based on the intensity value of the voxels. Thus using intensity information alone has proven to be insufficient for a reliable automated segmentation of the brain tissues. Hence an adaptive mean-shift methodology is utilized in order to classify brain voxels where the MRI image space is represented by a high-dimensional feature space that includes multimodal intensity features as well as spatial features. This proposed method clusters the joint spatial-intensity feature space thus extracting a representative set of high-density points within the feature space otherwise known as modes. The resultant output of an Adaptive means shift consists of several modes. A mode pruning step is undergone to reduce the number of modes. After the pruning step, intensity based clustering technique such as K-means algorithm is used for the classification of tissues. In this paper instead of K-means algorithm, Fuzzy C-means algorithm is implemented in order to achieve better segmentation. The final output consists of three regions which are used for the analysis of various neural diseases. It is shown to perform well in comparison to other state-of-the-art methods without the use of a preregistered statistical brain atlas.
原文链接
分享
引用
