A Comparative Analysis of MRI Automated Segmentation of Subcortical Brain Volumes in a Large Dataset of Elderly Subjects

In this study, we perform a comparative analysis of automated image segmentation of subcortical structures in the elderly brain. Manual segmentation is very time-consuming and automated methods are gaining importance as a clinical tool for diagnosis. The two most commonly used software libraries for...

Full description

Saved in:
Bibliographic Details
Published in:Neuroinformatics (Totowa, N.J.) N.J.), 2022, Vol.20 (1), p.63-72
Main Authors: Gomez-Ramirez, Jaime, Quilis-Sancho, Javier, Fernandez-Blazquez, Miguel A.
Format: Article
Language:English
Subjects:
Aged
Aging
Algorithms
Alzheimer's disease
Amygdala
Atrophy
Automation
Big Data
Bioinformatics
Biomedical and Life Sciences
Biomedicine
Brain - diagnostic imaging
Brain - pathology
Brain research
Comparative analysis
Computational Biology/Bioinformatics
Computer Appl. in Life Sciences
Datasets
Dementia
Globus pallidus
Humans
Image processing
Image Processing, Computer-Assisted - methods
Longitudinal studies
Magnetic resonance imaging
Magnetic Resonance Imaging - methods
Medical imaging
Morphology
Neuroimaging
Neuroimaging - methods
Neurology
Neurosciences
Nucleus accumbens
Older people
Original Article
Putamen
Segmentation
Software
Thalamus
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this study, we perform a comparative analysis of automated image segmentation of subcortical structures in the elderly brain. Manual segmentation is very time-consuming and automated methods are gaining importance as a clinical tool for diagnosis. The two most commonly used software libraries for brain segmentation -FreeSurfer and FSL- are put to work in a large dataset of 4,028 magnetic resonance imaging (MRI) scans collected for this study. We find a lack of linear correlation between the segmentation volume estimates obtained from FreeSurfer and FSL. On the other hand, FreeSurfer volume estimates tend to be larger thanFSL estimates of the areas putamen, thalamus, amygdala, caudate, pallidum, hippocampus, and accumbens. The characterization of the performance of brain segmentation algorithms in large datasets as the one presented here is a necessary step towards partially or fully automated end-to-end neuroimaging workflow both in clinical and research settings.
ISSN:1539-2791
1559-0089
DOI:10.1007/s12021-021-09520-z