Maximize uniformity summation heuristic (MUSH): a highly accurate simple method for intracranial delineation

A common procedure performed by many groups in the analysis of neuroimaging data is separating the brain from other tissues. This procedure is often utilized both by volumetric studies as well as functional imaging studies. Regardless of the intent, an accurate, robust method of identifying the brain or cranial vault is imperative. While this is a common requirement, there are relatively few tools to perform this task. Most of these tools require a T1 weighted image and are therefore not able to accurately define a region that includes surface CSF. In this paper, we have developed a novel brain extraction technique termed Maximize Uniformity by Summation Heuristic (MUSH) optimization. The algorithm was designed for extraction of the brain and surface CSF from a multi-modal magnetic resonance (MR) imaging study. The method forms a linear combination of multi-modal MR imaging data to make the signal intensity within the brain as uniform as possible. The resulting image is thresholded and simple morphological operators are utilized to generate the resulting representation of the brain. The resulting method was applied to a sample of 20 MR brain scans and compared to the results generated by 3dSkullStrip, 3dIntracranial, BET, and BET2. The average Jaccard metrics for the twenty subjects was 0.66 (BET), 0.61 (BET2), 0.88 (3dIntracranial), 0.91 (3dSkullStrip), and 0.94 (MUSH).