Cargando…

Local Brain-Age: A U-Net Model

We propose a new framework for estimating neuroimaging-derived “brain-age” at a local level within the brain, using deep learning. The local approach, contrary to existing global methods, provides spatial information on anatomical patterns of brain ageing. We trained a U-Net model using brain MRI sc...

Descripción completa

Detalles Bibliográficos
Autores principales: Popescu, Sebastian G., Glocker, Ben, Sharp, David J., Cole, James H.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8710767/
https://www.ncbi.nlm.nih.gov/pubmed/34966266
http://dx.doi.org/10.3389/fnagi.2021.761954
_version_ 1784623232990576640
author Popescu, Sebastian G.
Glocker, Ben
Sharp, David J.
Cole, James H.
author_facet Popescu, Sebastian G.
Glocker, Ben
Sharp, David J.
Cole, James H.
author_sort Popescu, Sebastian G.
collection PubMed
description We propose a new framework for estimating neuroimaging-derived “brain-age” at a local level within the brain, using deep learning. The local approach, contrary to existing global methods, provides spatial information on anatomical patterns of brain ageing. We trained a U-Net model using brain MRI scans from n = 3,463 healthy people (aged 18–90 years) to produce individualised 3D maps of brain-predicted age. When testing on n = 692 healthy people, we found a median (across participant) mean absolute error (within participant) of 9.5 years. Performance was more accurate (MAE around 7 years) in the prefrontal cortex and periventricular areas. We also introduce a new voxelwise method to reduce the age-bias when predicting local brain-age “gaps.” To validate local brain-age predictions, we tested the model in people with mild cognitive impairment or dementia using data from OASIS3 (n = 267). Different local brain-age patterns were evident between healthy controls and people with mild cognitive impairment or dementia, particularly in subcortical regions such as the accumbens, putamen, pallidum, hippocampus, and amygdala. Comparing groups based on mean local brain-age over regions-of-interest resulted in large effects sizes, with Cohen's d values >1.5, for example when comparing people with stable and progressive mild cognitive impairment. Our local brain-age framework has the potential to provide spatial information leading to a more mechanistic understanding of individual differences in patterns of brain ageing in health and disease.
format Online
Article
Text
id pubmed-8710767
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-87107672021-12-28 Local Brain-Age: A U-Net Model Popescu, Sebastian G. Glocker, Ben Sharp, David J. Cole, James H. Front Aging Neurosci Neuroscience We propose a new framework for estimating neuroimaging-derived “brain-age” at a local level within the brain, using deep learning. The local approach, contrary to existing global methods, provides spatial information on anatomical patterns of brain ageing. We trained a U-Net model using brain MRI scans from n = 3,463 healthy people (aged 18–90 years) to produce individualised 3D maps of brain-predicted age. When testing on n = 692 healthy people, we found a median (across participant) mean absolute error (within participant) of 9.5 years. Performance was more accurate (MAE around 7 years) in the prefrontal cortex and periventricular areas. We also introduce a new voxelwise method to reduce the age-bias when predicting local brain-age “gaps.” To validate local brain-age predictions, we tested the model in people with mild cognitive impairment or dementia using data from OASIS3 (n = 267). Different local brain-age patterns were evident between healthy controls and people with mild cognitive impairment or dementia, particularly in subcortical regions such as the accumbens, putamen, pallidum, hippocampus, and amygdala. Comparing groups based on mean local brain-age over regions-of-interest resulted in large effects sizes, with Cohen's d values >1.5, for example when comparing people with stable and progressive mild cognitive impairment. Our local brain-age framework has the potential to provide spatial information leading to a more mechanistic understanding of individual differences in patterns of brain ageing in health and disease. Frontiers Media S.A. 2021-12-13 /pmc/articles/PMC8710767/ /pubmed/34966266 http://dx.doi.org/10.3389/fnagi.2021.761954 Text en Copyright © 2021 Popescu, Glocker, Sharp and Cole. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Popescu, Sebastian G.
Glocker, Ben
Sharp, David J.
Cole, James H.
Local Brain-Age: A U-Net Model
title Local Brain-Age: A U-Net Model
title_full Local Brain-Age: A U-Net Model
title_fullStr Local Brain-Age: A U-Net Model
title_full_unstemmed Local Brain-Age: A U-Net Model
title_short Local Brain-Age: A U-Net Model
title_sort local brain-age: a u-net model
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8710767/
https://www.ncbi.nlm.nih.gov/pubmed/34966266
http://dx.doi.org/10.3389/fnagi.2021.761954
work_keys_str_mv AT popescusebastiang localbrainageaunetmodel
AT glockerben localbrainageaunetmodel
AT sharpdavidj localbrainageaunetmodel
AT colejamesh localbrainageaunetmodel