Brain extraction using isodata clustering algorithm aided by histogram analysis

Magnetic resonance (MR) imaging has a broad application in diagnosis and detection process of different brain related diseases. Manual analysis of MR images is a cumbersomeand time consuming task. In order to automatically analyze the brain tissue accurately, non-brain compartments must be removed from magnetic resonance images. This task is known as brain extraction or skull stripping. In this study a brain extraction method is proposed. The proposed method formulatessegmentation problem as a clustering problem and its core component is isodata clustering algorithm. Application of isodataalgorithm reveals five distinct clusters. Two of these clusters contain voxels belonging to tissues of interest and three of thembelongs to non-brain compartments. In order to produce an accurate brain mask, isodata cluster representatives are initialized by histogram analysis of MR volume of the brain.These representatives are mods of histogram of MR volume. The second stage of the proposed method leads to produce moreaccurate brain mask by somehow removing outliers. In this case, isodata algorithm performs better. Performance of the proposedmethod is measured by popular performance measures such as Dice similarity coefficient (Dice), Jaccard similarity index (J),sensitivity, and specificity. The proposed method outperforms BET, BSE, and HWA as popular methods by Dice = 0.959 (0.008) and J = 0.921 (0.168). These results are obtained based on BrainWeb dataset.

Keywords:

brain extraction , skull stripping , histogram analysis , isodata clustering , MRI