Brain volumes computed from magnetic resonance images have potential for assisting with the diagnosis of individual dementia patients, provided that they have low measurement error and high reliability. In this paper we describe and validate icobrain dm, an automatic tool that segments brain structures that are relevant for differential diagnosis of dementia, such as the hippocampi and cerebral lobes. Experiments were conducted in comparison to the widely used FreeSurfer software. The hippocampus segmentations were compared against manual segmentations, with significantly higher Dice coefficients obtained with icobrain dm (25-75th quantiles: 0.86-0.88) than with FreeSurfer (25-75th quantiles: 0.80-0.83). Other brain structures were also compared against manual delineations, with icobrain dm showing lower volumetric errors overall. Test-retest experiments show that the precision of all measurements is higher for icobrain dm than for FreeSurfer except for the parietal cortex volume. Finally, when comparing volumes obtained from Alzheimer's disease patients against age-matched healthy controls, all measures achieved high diagnostic performance levels when discriminating patients from cognitively healthy controls, with the temporal cortex volume measured by icobrain dm reaching the highest diagnostic performance level (area under the receiver operating characteristic curve = 0.99) in this dataset.
Struyfs, H, Sima, DM, Wittens, M, Ribbens, A, Pedrosa de Barros, N, Phan, TV, Ferraz Meyer, MI, Claes, L, Niemantsverdriet, E, Engelborghs, S, Van Hecke, W & Smeets, D 2020, 'Automated MRI volumetry as a diagnostic tool for Alzheimer's disease: Validation of icobrain dm', NeuroImage: Clinical, vol. 26, 102243. https://doi.org/10.1016/j.nicl.2020.102243
Struyfs, H., Sima, D. M., Wittens, M., Ribbens, A., Pedrosa de Barros, N., Phan, T. V., Ferraz Meyer, M. I., Claes, L., Niemantsverdriet, E., Engelborghs, S., Van Hecke, W., & Smeets, D. (2020). Automated MRI volumetry as a diagnostic tool for Alzheimer's disease: Validation of icobrain dm. NeuroImage: Clinical, 26, Article 102243. https://doi.org/10.1016/j.nicl.2020.102243
@article{e440d6c6ca7f4fe2b00d8e9cf1e75b07,
title = "Automated MRI volumetry as a diagnostic tool for Alzheimer's disease: Validation of icobrain dm",
abstract = "Brain volumes computed from magnetic resonance images have potential for assisting with the diagnosis of individual dementia patients, provided that they have low measurement error and high reliability. In this paper we describe and validate icobrain dm, an automatic tool that segments brain structures that are relevant for differential diagnosis of dementia, such as the hippocampi and cerebral lobes. Experiments were conducted in comparison to the widely used FreeSurfer software. The hippocampus segmentations were compared against manual segmentations, with significantly higher Dice coefficients obtained with icobrain dm (25-75th quantiles: 0.86-0.88) than with FreeSurfer (25-75th quantiles: 0.80-0.83). Other brain structures were also compared against manual delineations, with icobrain dm showing lower volumetric errors overall. Test-retest experiments show that the precision of all measurements is higher for icobrain dm than for FreeSurfer except for the parietal cortex volume. Finally, when comparing volumes obtained from Alzheimer's disease patients against age-matched healthy controls, all measures achieved high diagnostic performance levels when discriminating patients from cognitively healthy controls, with the temporal cortex volume measured by icobrain dm reaching the highest diagnostic performance level (area under the receiver operating characteristic curve = 0.99) in this dataset.",
keywords = "Alzheimer's disease (AD), Brain segmentation software, Dementia, Magnetic resonance imaging (MRI)",
author = "Hanne Struyfs and Sima, {Diana Maria} and Melissa Wittens and Annemie Ribbens and {Pedrosa de Barros}, Nuno and Phan, {Thanh V{\^a}n} and {Ferraz Meyer}, {Maria Ines} and Lene Claes and Ellis Niemantsverdriet and Sebastiaan Engelborghs and {Van Hecke}, Wim and Dirk Smeets",
note = "Copyright {\textcopyright} 2020 The Authors. Published by Elsevier Inc. All rights reserved.",
year = "2020",
doi = "10.1016/j.nicl.2020.102243",
language = "English",
volume = "26",
journal = "NeuroImage: Clinical",
issn = "2213-1582",
publisher = "Elsevier BV",
}