Bayesian convolutional neural network based MRI brain extraction on nonhuman primates

• Published in: NeuroImage (Orlando, Fla.) Vol. 175; pp. 32 - 44
• Main Authors: Zhao, Gengyan, Liu, Fang, Oler, Jonathan A., Meyerand, Mary E., Kalin, Ned H., Birn, Rasmus M.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 15.07.2018; Elsevier Limited
• Subjects: Accuracy; Algorithms; Animals; Automation; Bayes Theorem; Bayesian analysis; Brain - diagnostic imaging; Brain extraction; Brain research; CNN; CRF; Deep Learning; Female; Image processing; Image Processing, Computer-Assisted - methods; Laboratories; Macaca mulatta; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Medical imaging; Methods; Monkeys & apes; Morphology; MRI; Nervous system; Neural networks; Neuroimaging; Neuroimaging - methods; Neurosciences; NMR; Nonhuman primates; Nuclear magnetic resonance; Primates; Registration; Segmentation; Software; Statistical analysis; Watersheds; Deep learning; CNN; MRI; CRF; Nonhuman primates; Brain extraction

Brain extraction or skull stripping of magnetic resonance images (MRI) is an essential step in neuroimaging studies, the accuracy of which can severely affect subsequent image processing procedures. Current automatic brain extraction methods demonstrate good results on human brains, but are often fa...