Fuzzy-Neuro Logic in Segmentation of MRI Images

Image segmentation is an important process to extract information from complex medical images. Segmentation has wide application in medical field. The main objective of image segmentation is to partition an image into mutually exclusive and exhausted regions such that each region of interest is spatially contiguous and the pixels within the region are homogeneous with respect to a predefined criterion. Widely used homogeneity criteria include values of intensity, texture, color, range, surface normal and surface curvatures. During the past, many researchers in the field of medical imaging and soft computing have made significant survey in the field of image segmentation. Several diagnostics are based proper segmentation of the digitized image. Segmentation of medical images is needed for applications involving estimation of the boundary of an object, classification of tissue abnormalities, shape analysis, contour detection. In particular Fuzzy-Neuro logic segmentation algorithm is used to provide satisfactory results compared to K-means, Fuzzy C-Means, Neural Network and Fuzzy logic. This paper aims to develop an improved method of segmentation using Fuzzy-Neuro logic to detect various tissues like white matter, gray matter; cerebral spinal fluid and tumor for a given magnetic resonance image data set. In particular Fuzzy-Neuro logic segmentation algorithm is used to provide satisfactory results compared to K-means, Fuzzy C-Means, Neural Network and Fuzzy logic.