Effect Of Noise over MRI Segmentation Techniques

Abstract

this approach is basically used to compare the extracted patterns of internal body tissues which were affected
by various noises during acquisition. Segmentation is a computational intelligence discipline which has emerged as a
valuable tool for disease analysis, new knowledge discovery and autonomous decision making. The raw, unlabeled data
from the MRI image can be clustered first and after that segmentation can be applied in order to obtain the pattern or
outlook of a particular organ or tissue so that diagnosticians can use them for diagnosing and finally analyzing the
tissues. There are various algorithms which are used to solve this problem. In this paper two important segmentation
algorithms namely centroid based K-Means and representative object based FCM (Fuzzy C-Means) clustering
algorithms are compared. These algorithms are applied to the MRI image of thoracic cavity and performance is
evaluated on the basis of the efficiency they provide when they are affected by various types of noises.