|International Journal of Applied Information Systems|
|Foundation of Computer Science (FCS), NY, USA|
|Volume 5 - Number 2|
|Year of Publication: 2013|
|Authors: A. Ramaswamy Reddy, E. V. Prasad, L. S. S. Reddy|
A. Ramaswamy Reddy, E. V. Prasad, L. S. S. Reddy . Abnormality Detection of Brain MR Image Segmentation using Iterative Conditional Mode Algorithm. International Journal of Applied Information Systems. 5, 2 ( January 2013), 56-66. DOI=10.5120/ijais12-450767
In medical image processing, Brain MR Image segmentation is a typical problem for researcher to extract information without loss of details with good resolution. In this paper, we propose a novel method of segmentation using Iterative Conditional Model (ICM) algorithm and Markov random field (MRF) model to detect the abnormality in MR images. The lowest energy label making is allowed by ICM and processed for all iterations. This method supports high compressed relation between label and boundary MRFs. The study of steadily takes will consider all conditions of a discontinues (single edge) existing in a 3 X 3 kernel also including problematical prior information about the interaction between label and boundary. The model is tested with 5 images and the segmentation evaluation is carry out by using objective evaluation criteria namely Jaccard Coefficient (JC) and Volumetric Similarity (VS), Variation of Information (VOI), Global Consistency Error (GCE) and Probabilistic Rand Index (PRI). The performance evaluation of segmented images is carried out by using image quality metrics. The simulated results proposed by using T1 weighted images are compared with the existing models.