Dataset Information

Brain extraction from cerebral MRI volume using a hybrid level set based active contour neighborhood model.

ABSTRACT: BACKGROUND: The extraction of brain tissue from cerebral MRI volume is an important pre-procedure for neuroimage analyses. The authors have developed an accurate and robust brain extraction method using a hybrid level set based active contour neighborhood model. METHODS: The method uses a nonlinear speed function in the hybrid level set model to eliminate boundary leakage. When using the new hybrid level set model an active contour neighborhood model is applied iteratively in the neighborhood of brain boundary. A slice by slice contour initial method is proposed to obtain the neighborhood of the brain boundary. The method was applied to the internet brain MRI data provided by the Internet Brain Segmentation Repository (IBSR). RESULTS: In testing, a mean Dice similarity coefficient of 0.95±0.02 and a mean Hausdorff distance of 12.4±4.5 were obtained when performing our method across the IBSR data set (18 × 1.5 mm scans). The results obtained using our method were very similar to those produced using manual segmentation and achieved the smallest mean Hausdorff distance on the IBSR data. CONCLUSIONS: An automatic method of brain extraction from cerebral MRI volume was achieved and produced competitively accurate results.

SUBMITTER: Jiang S

PROVIDER: S-EPMC3639852 | biostudies-other | 2013

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Brain extraction from cerebral MRI volume using a hybrid level set based active contour neighborhood model.

Jiang Shaofeng S Zhang Weirui W Wang Yu Y Chen Zhen Z

Biomedical engineering online 20130412

<h4>Background</h4>The extraction of brain tissue from cerebral MRI volume is an important pre-procedure for neuroimage analyses. The authors have developed an accurate and robust brain extraction method using a hybrid level set based active contour neighborhood model.<h4>Methods</h4>The method uses a nonlinear speed function in the hybrid level set model to eliminate boundary leakage. When using the new hybrid level set model an active contour neighborhood model is applied iteratively in the ne ...[more]

PMID: 23587217

Similar Datasets

Project description:ImportanceIdentifying risk factors for brain atrophy during the aging process can help direct new preventive approaches for dementia and cognitive decline. The association of neighborhood socioeconomic disadvantage with brain volume in this context is not well known.ObjectiveTo test whether neighborhood-level socioeconomic disadvantage is associated with decreased brain volume in a cognitively unimpaired population enriched for Alzheimer disease risk.Design, setting, and participantsThis study, conducted from January 6, 2010, to January 17, 2019, at an academic research neuroimaging center, used cross-sectional data on 951 participants from 2 large, ongoing cohort studies of Alzheimer disease (Wisconsin Registry for Alzheimer's Prevention and Wisconsin Alzheimer's Disease Research Center clinical cohort). Participants were cognitively unimpaired based on National Institute on Aging-Alzheimer's Association workgroup diagnostic criteria for mild cognitive impairment and Alzheimer disease, confirmed through a consensus diagnosis panel. The cohort was enriched for Alzheimer disease risk based on family history of dementia. Statistical analysis was performed from April 3 to September 27, 2019.Main outcomes and measuresThe Area Deprivation Index, a geospatially determined index of neighborhood-level disadvantage, and cardiovascular disease risk indices were calculated for each participant. Linear regression models were fitted to test associations between relative neighborhood-level disadvantage (highest 20% based on state of residence) and hippocampal and total brain tissue volume, as assessed by magnetic resonance imaging.ResultsIn the primary analysis of 951 participants (637 women [67.0%]; mean [SD] age, 63.9 [8.1] years), living in the 20% most disadvantaged neighborhoods was associated with 4.1% lower hippocampal volume (β = -317.44; 95% CI, -543.32 to -91.56; P = .006) and 2.0% lower total brain tissue volume (β = -20 959.67; 95% CI, -37 611.92 to -4307.43; P = .01), after controlling for intracranial volume, individual-level educational attainment, age, and sex. Robust propensity score-matched analyses determined that this association was not due to racial/ethnic or demographic characteristics. Cardiovascular risk score, examined in a subsample of 893 participants, mediated this association for total brain tissue but not for hippocampal volume.Conclusions and relevanceFor cognitively unimpaired individuals, living in the most disadvantaged neighborhoods was associated with significantly lower cerebral volumes, after controlling for maximal premorbid (total intracranial) volume. This finding suggests an association of community socioeconomic context, distinct from individual-level socioeconomic status, with brain volume during aging. Cardiovascular risk mediated this association for total brain tissue volume but not for hippocampal volume, suggesting that neighborhood-level disadvantage may be associated with these 2 outcomes via distinct biological pathways.

Dataset Information

Brain extraction from cerebral MRI volume using a hybrid level set based active contour neighborhood model.

Publications

Brain extraction from cerebral MRI volume using a hybrid level set based active contour neighborhood model.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets