Contents I. Introduction
In the field of medical image processing the improvement of segmentation methods to accelerate image understanding is an important progress. The objective of segmentation is to make simpler and/or alteration of the presentation of an image into something that is more significant & simpler to examine. Identification of the shapes, location, intensity & other properties in medical images needs expertise because of the growing data availability & feature complexity [1]. Reliable measurement of these adjustments can be accomplished by utilizing image segmentation. A number of investigators have created techniques to automate such measurements by segmentation. Then again, some of these techniques do not exploit the multispectral information of the MRI signal. As Fuzzy c-means (FCM) clustering is an unsupervised method, it has been effectively employed to feature analysis, clustering, & classifier designs in fields, for example, astronomy, geology, medical imaging, target recognition, & image segmentation [2], [3]. An image can be presented in different feature spaces, & the FCM algorithm classifies the image by grouping similar data points in the feature space into clusters. This clustering is accomplished by iteratively minimizing a cost function that is reliant on the distance of the pixels to the cluster centers in the feature domain [4].
