Knowledge-guided robust MRI brain extraction for diverse large-scale neuroimaging studies on humans and non-human primates

Yaping Wang, Jingxin Nie, Pew Thian Yap, Gang Li, Feng Shi, Xiujuan Geng, Lei Guo, Dinggang Shen

Research output: Contribution to journalArticle

58 Citations (Scopus)

Abstract

Accurate and robust brain extraction is a critical step in most neuroimaging analysis pipelines. In particular, for the largescale multi-site neuroimaging studies involving a significant number of subjects with diverse age and diagnostic groups, accurate and robust extraction of the brain automatically and consistently is highly desirable. In this paper, we introduce population-specific probability maps to guide the brain extraction of diverse subject groups, including both healthy and diseased adult human populations, both developing and aging human populations, as well as non-human primates. Specifically, the proposed method combines an atlas-based approach, for coarse skull-stripping, with a deformable-surfacebased approach that is guided by local intensity information and population-specific prior information learned from a set of real brain images for more localized refinement. Comprehensive quantitative evaluations were performed on the diverse large-scale populations of ADNI dataset with over 800 subjects (55-90 years of age, multi-site, various diagnosis groups), OASIS dataset with over 400 subjects (18-96 years of age, wide age range, various diagnosis groups), and NIH pediatrics dataset with 150 subjects (5-18 years of age, multi-site, wide age range as a complementary age group to the adult dataset). The results demonstrate that our method consistently yields the best overall results across almost the entire human life span, with only a single set of parameters. To demonstrate its capability to work on non-human primates, the proposed method is further evaluated using a rhesus macaque dataset with 20 subjects. Quantitative comparisons with popularly used state-of-the-art methods, including BET, Two-pass BET, BET-B, BSE, HWA, ROBEX and AFNI, demonstrate that the proposed method performs favorably with superior performance on all testing datasets, indicating its robustness and effectiveness.

Original languageEnglish
Article numbere77810
JournalPLoS One
Volume9
Issue number1
DOIs
Publication statusPublished - 2014 Jan 29

Fingerprint

Neuroimaging
Magnetic resonance imaging
Primates
Brain
brain
Population
Pediatrics
human population
Age Groups
Pipelines
Atlases
Aging of materials
methodology
Macaca mulatta
Skull
Datasets
skull
Testing

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

Knowledge-guided robust MRI brain extraction for diverse large-scale neuroimaging studies on humans and non-human primates. / Wang, Yaping; Nie, Jingxin; Yap, Pew Thian; Li, Gang; Shi, Feng; Geng, Xiujuan; Guo, Lei; Shen, Dinggang.

In: PLoS One, Vol. 9, No. 1, e77810, 29.01.2014.

Research output: Contribution to journalArticle

Wang, Yaping ; Nie, Jingxin ; Yap, Pew Thian ; Li, Gang ; Shi, Feng ; Geng, Xiujuan ; Guo, Lei ; Shen, Dinggang. / Knowledge-guided robust MRI brain extraction for diverse large-scale neuroimaging studies on humans and non-human primates. In: PLoS One. 2014 ; Vol. 9, No. 1.
@article{d34c3a4b26214bdb9efc60473e1abf19,
title = "Knowledge-guided robust MRI brain extraction for diverse large-scale neuroimaging studies on humans and non-human primates",
abstract = "Accurate and robust brain extraction is a critical step in most neuroimaging analysis pipelines. In particular, for the largescale multi-site neuroimaging studies involving a significant number of subjects with diverse age and diagnostic groups, accurate and robust extraction of the brain automatically and consistently is highly desirable. In this paper, we introduce population-specific probability maps to guide the brain extraction of diverse subject groups, including both healthy and diseased adult human populations, both developing and aging human populations, as well as non-human primates. Specifically, the proposed method combines an atlas-based approach, for coarse skull-stripping, with a deformable-surfacebased approach that is guided by local intensity information and population-specific prior information learned from a set of real brain images for more localized refinement. Comprehensive quantitative evaluations were performed on the diverse large-scale populations of ADNI dataset with over 800 subjects (55-90 years of age, multi-site, various diagnosis groups), OASIS dataset with over 400 subjects (18-96 years of age, wide age range, various diagnosis groups), and NIH pediatrics dataset with 150 subjects (5-18 years of age, multi-site, wide age range as a complementary age group to the adult dataset). The results demonstrate that our method consistently yields the best overall results across almost the entire human life span, with only a single set of parameters. To demonstrate its capability to work on non-human primates, the proposed method is further evaluated using a rhesus macaque dataset with 20 subjects. Quantitative comparisons with popularly used state-of-the-art methods, including BET, Two-pass BET, BET-B, BSE, HWA, ROBEX and AFNI, demonstrate that the proposed method performs favorably with superior performance on all testing datasets, indicating its robustness and effectiveness.",
author = "Yaping Wang and Jingxin Nie and Yap, {Pew Thian} and Gang Li and Feng Shi and Xiujuan Geng and Lei Guo and Dinggang Shen",
year = "2014",
month = "1",
day = "29",
doi = "10.1371/journal.pone.0077810",
language = "English",
volume = "9",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "1",

}

TY - JOUR

T1 - Knowledge-guided robust MRI brain extraction for diverse large-scale neuroimaging studies on humans and non-human primates

AU - Wang, Yaping

AU - Nie, Jingxin

AU - Yap, Pew Thian

AU - Li, Gang

AU - Shi, Feng

AU - Geng, Xiujuan

AU - Guo, Lei

AU - Shen, Dinggang

PY - 2014/1/29

Y1 - 2014/1/29

N2 - Accurate and robust brain extraction is a critical step in most neuroimaging analysis pipelines. In particular, for the largescale multi-site neuroimaging studies involving a significant number of subjects with diverse age and diagnostic groups, accurate and robust extraction of the brain automatically and consistently is highly desirable. In this paper, we introduce population-specific probability maps to guide the brain extraction of diverse subject groups, including both healthy and diseased adult human populations, both developing and aging human populations, as well as non-human primates. Specifically, the proposed method combines an atlas-based approach, for coarse skull-stripping, with a deformable-surfacebased approach that is guided by local intensity information and population-specific prior information learned from a set of real brain images for more localized refinement. Comprehensive quantitative evaluations were performed on the diverse large-scale populations of ADNI dataset with over 800 subjects (55-90 years of age, multi-site, various diagnosis groups), OASIS dataset with over 400 subjects (18-96 years of age, wide age range, various diagnosis groups), and NIH pediatrics dataset with 150 subjects (5-18 years of age, multi-site, wide age range as a complementary age group to the adult dataset). The results demonstrate that our method consistently yields the best overall results across almost the entire human life span, with only a single set of parameters. To demonstrate its capability to work on non-human primates, the proposed method is further evaluated using a rhesus macaque dataset with 20 subjects. Quantitative comparisons with popularly used state-of-the-art methods, including BET, Two-pass BET, BET-B, BSE, HWA, ROBEX and AFNI, demonstrate that the proposed method performs favorably with superior performance on all testing datasets, indicating its robustness and effectiveness.

AB - Accurate and robust brain extraction is a critical step in most neuroimaging analysis pipelines. In particular, for the largescale multi-site neuroimaging studies involving a significant number of subjects with diverse age and diagnostic groups, accurate and robust extraction of the brain automatically and consistently is highly desirable. In this paper, we introduce population-specific probability maps to guide the brain extraction of diverse subject groups, including both healthy and diseased adult human populations, both developing and aging human populations, as well as non-human primates. Specifically, the proposed method combines an atlas-based approach, for coarse skull-stripping, with a deformable-surfacebased approach that is guided by local intensity information and population-specific prior information learned from a set of real brain images for more localized refinement. Comprehensive quantitative evaluations were performed on the diverse large-scale populations of ADNI dataset with over 800 subjects (55-90 years of age, multi-site, various diagnosis groups), OASIS dataset with over 400 subjects (18-96 years of age, wide age range, various diagnosis groups), and NIH pediatrics dataset with 150 subjects (5-18 years of age, multi-site, wide age range as a complementary age group to the adult dataset). The results demonstrate that our method consistently yields the best overall results across almost the entire human life span, with only a single set of parameters. To demonstrate its capability to work on non-human primates, the proposed method is further evaluated using a rhesus macaque dataset with 20 subjects. Quantitative comparisons with popularly used state-of-the-art methods, including BET, Two-pass BET, BET-B, BSE, HWA, ROBEX and AFNI, demonstrate that the proposed method performs favorably with superior performance on all testing datasets, indicating its robustness and effectiveness.

UR - http://www.scopus.com/inward/record.url?scp=84896373761&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896373761&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0077810

DO - 10.1371/journal.pone.0077810

M3 - Article

VL - 9

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 1

M1 - e77810

ER -