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

• 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
• ISSN: 1539-2791; 1559-0089
• DOI: 10.1007/s12021-021-09520-z

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.