BEaST: Brain extraction based on nonlocal segmentation technique

• Published in: NeuroImage (Orlando, Fla.) Fla.), 2012-02, Vol.59 (3), p.2362-2373
• Main Authors: Eskildsen, Simon F., Coupé, Pierrick, Fonov, Vladimir, Manjón, José V., Leung, Kelvin K., Guizard, Nicolas, Wassef, Shafik N., Østergaard, Lasse Riis, Collins, D. Louis
• Format: Article
• Language: English
• Subjects: Academic libraries; Adolescent; Adult; Algorithms; Alzheimer's disease; Applications; BET; Bioengineering; Brain; Brain - anatomy & histology; Brain extraction; Brain Mapping; Brain Mapping - methods; Computer Science; Computers; Databases, Factual; Engineering Sciences; False Negative Reactions; False Positive Reactions; Female; Humans; Image Processing, Computer-Assisted; Image Processing, Computer-Assisted - methods; Image Processing, Computer-Assisted - statistics & numerical data; Life Sciences; Machine Learning; Magnetic Resonance Imaging; Magnetic Resonance Imaging - methods; Magnetic Resonance Imaging - statistics & numerical data; Male; Medical Imaging; Medical research; Methods; MRI; Multi-resolution; Neurons and Cognition; Patch-based segmentation; Pharmaceutical industry; Quality Control; Reference Standards; Registration; Reproducibility of Results; Signal and Image Processing; Skull stripping; Software; Statistics; Studies; Young Adult
• ISSN: 1053-8119; 1095-9572
• DOI: 10.1016/j.neuroimage.2011.09.012

Brain extraction is an important step in the analysis of brain images. The variability in brain morphology and the difference in intensity characteristics due to imaging sequences make the development of a general purpose brain extraction algorithm challenging. To address this issue, we propose a new robust method (BEaST) dedicated to produce consistent and accurate brain extraction. This method is based on nonlocal segmentation embedded in a multi-resolution framework. A library of 80 priors is semi-automatically constructed from the NIH-sponsored MRI study of normal brain development, the International Consortium for Brain Mapping, and the Alzheimer's Disease Neuroimaging Initiative databases. In testing, a mean Dice similarity coefficient of 0.9834±0.0053 was obtained when performing leave-one-out cross validation selecting only 20 priors from the library. Validation using the online Segmentation Validation Engine resulted in a top ranking position with a mean Dice coefficient of 0.9781±0.0047. Robustness of BEaST is demonstrated on all baseline ADNI data, resulting in a very low failure rate. The segmentation accuracy of the method is better than two widely used publicly available methods and recent state-of-the-art hybrid approaches. BEaST provides results comparable to a recent label fusion approach, while being 40 times faster and requiring a much smaller library of priors.