Robust skull stripping using multiple MR image contrasts insensitive to pathology

• Published in: NeuroImage (Orlando, Fla.) Vol. 146; pp. 132 - 147
• Main Authors: Roy, Snehashis, Butman, John A., Pham, Dzung L.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.02.2017; Elsevier Limited
• Subjects: Accuracy; Algorithms; Alzheimer's disease; Atlases as Topic; Brain - anatomy & histology; Brain - diagnostic imaging; Brain - pathology; Brain cancer; Brain extraction; Brain Mapping; Brain research; Brain tumors; Cerebrospinal fluid; Contrast Media; Databases, Factual; Datasets; Humans; Image Enhancement; Image processing; Image Processing, Computer-Assisted; Magnetic Resonance Imaging; Masks; Mental disorders; Morphology; Movement disorders; Neural networks; Neuroimaging; Non-local; Patches; Pathology; Pattern Recognition, Automated; Pharmaceutical industry; R&D; Registration; Research & development; Schizophrenia; Segmentation; Skull; Skull - anatomy & histology; Skull - diagnostic imaging; Skull - pathology; Skull stripping; Sparsity; Traumatic brain injury; Atlas; Non-local; Segmentation; Sparsity; Skull stripping; Brain extraction; Patches

Automatic skull-stripping or brain extraction of magnetic resonance (MR) images is often a fundamental step in many neuroimage processing pipelines. The accuracy of subsequent image processing relies on the accuracy of the skull-stripping. Although many automated stripping methods have been proposed...