Automatic Segmentation Approach Based Data Aggregation for the Classification of Brain Tissues

摘要

The paper presents a study and an evaluation of a novel unsupervised segmentation technique based aggregation approach and some of possibility theory concepts. Firstly, the MPFCM (Modified Possibilistic Fuzzy C-Means) algorithm is used to extract information from each of MR images modalities. In second step, an obtained data are combined with an operator in order to exploiting the uncertainty and ambiguity in the images. Finally, the segmented image is constructed using a decision rule. The efficiency of the proposed method is demonstrated by segmentation experiments using simulated MR images with different noise levels.