biostudies-literatureWang XIntramural NIH HHSCalifornia National Primate Research CenterNIA NIH HHSMedical Research CouncilNIMH NIH HHSNational Natural Science Foundation of ChinaNational Institute of Mental HealthNational Institutes of HealthWellcome TrustNIH HHS118001https://www.ebi.ac.uk/biostudies/studies/S-EPMC8529630biostudies-literatureUnknown235Brain extraction (a.k.a. skull stripping) is a fundamental step in the neuroimaging pipeline as it can affect the accuracy of downstream preprocess such as image registration, tissue classification, etc. Most brain extraction tools have been designed for and applied to human data and are often challenged by non-human primates (NHP) data. Amongst recent attempts to improve performance on NHP data, deep learning models appear to outperform the traditional tools. However, given the minimal sample size of most NHP studies and notable variations in data quality, the deep learning models are very rarely applied to multi-site samples in NHP imaging. To overcome this challenge, we used a transfer-learning framework that leverages a large human imaging dataset to pretrain a convolutional neural network (i.e. U-Net Model), and then transferred this to NHP data using a small NHP training sample. The resulting transfer-learning model converged faster and achieved more accurate performance than a similar U-Net Model trained exclusively on NHP samples. We improved the generalizability of the model by upgrading the transfer-learned model using additional training datasets from multiple research sites in the Primate Data-Exchange (PRIME-DE) consortium. Our final model outperformed brain extraction routines from popular MRI packages (AFNI, FSL, and FreeSurfer) across a heterogeneous sample from multiple sites in the PRIME-DE with less computational cost (20 s~10 min). We also demonstrated the transfer-learning process enables the macaque model to be updated for use with scans from chimpanzees, marmosets, and other mammals (e.g. pig). Our model, code, and the skull-stripped mask repository of 136 macaque monkeys are publicly available for unrestricted use by the neuroimaging community at https://github.com/HumanBrainED/NHP-BrainExtraction.NeuroImageU-net model for brain extraction: Trained on humans for transfer to non-human primates.PMC8529630R01MH046729R01 MH081884R01MH121735ZIA MH002918108089/Z/15/ZRF1MH117428RF1 MH117428P50 MH084051R01 MH101555RF1MH117040R01 AG0475963177117481571300R01MH101555RF1 MH117040ZIAMH002918R01 MH12173581527901R01 MH046729MR/M023990/1P50MH084051P51OD011107R01MH081884P50 MH109429R01 MH111439R24MH114806MR/ M023990/1P51 OD011107R01-MH111439P50-MH109429R24 MH114806Cho JWKalin NHFox ASAi LLi XHMilham MPRuss BEKorchmaros AEvans ACOmelchenko ASchroeder CEXu TSawiak SBenn RAWang XRajamani NCraddock RCWang ZMessinger AGarcia-Saldivar PfalseU-net model for brain extraction: Trained on humans for transfer to non-human primates.Brain extraction (a.k.a. skull stripping) is a fundamental step in the neuroimaging pipeline as it can affect the accuracy of downstream preprocess such as image registration, tissue classification, etc. Most brain extraction tools have been designed for and applied to human data and are often challenged by non-human primates (NHP) data. Amongst recent attempts to improve performance on NHP data, deep learning models appear to outperform the traditional tools. However, given the minimal sample size of most NHP studies and notable variations in data quality, the deep learning models are very rarely applied to multi-site samples in NHP imaging. To overcome this challenge, we used a transfer-learning framework that leverages a large human imaging dataset to pretrain a convolutional neural network (i.e. U-Net Model), and then transferred this to NHP data using a small NHP training sample. The resulting transfer-learning model converged faster and achieved more accurate performance than a similar U-Net Model trained exclusively on NHP samples. We improved the generalizability of the model by upgrading the transfer-learned model using additional training datasets from multiple research sites in the Primate Data-Exchange (PRIME-DE) consortium. Our final model outperformed brain extraction routines from popular MRI packages (AFNI, FSL, and FreeSurfer) across a heterogeneous sample from multiple sites in the PRIME-DE with less computational cost (20 s~10 min). We also demonstrated the transfer-learning process enables the macaque model to be updated for use with scans from chimpanzees, marmosets, and other mammals (e.g. pig). Our model, code, and the skull-stripped mask repository of 136 macaque monkeys are publicly available for unrestricted use by the neuroimaging community at https://github.com/HumanBrainED/NHP-BrainExtraction.2021-01-01T00:00:00Z2021 Jul2025-04-19T21:38:11.834Z2025-04-19T21:38:11.834ZS-EPMC85296303378913710.1016/j.neuroimage.2021.118001