A deep learning model for brain age prediction using minimally preprocessed T1w images as input
Frontiers in Aging Neuroscience · 08.01.2024 · 15
DOI: 10.3389/fnagi.2023.1303036 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Aging Neuroscience, online erschienen am 08.01.2024. Verfasst von Caroline Dartora und 15 weiteren Autor:innen. Beteiligte Einrichtung: Division of Clinical Geriatrics, Center for Alzheimer Research, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockho…. Die Arbeit wurde bisher 51-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIA NIH HHS.
Abstract (Originalsprache)
Introduction
In the last few years, several models trying to calculate the biological brain age have been proposed based on structural magnetic resonance imaging scans (T1-weighted MRIs, T1w) using multivariate methods and machine learning. We developed and validated a convolutional neural network (CNN)-based biological brain age prediction model that uses one T1w MRI preprocessing step when applying the model to external datasets to simplify implementation and increase accessibility in research settings. Our model only requires rigid image registration to the MNI space, which is an advantage compared to previous methods that require more preprocessing steps, such as feature extraction.
Methods
We used a multicohort dataset of cognitively healthy individuals (age range = 32.0–95.7 years) comprising 17,296 MRIs for training and evaluation. We compared our model using hold-out (CNN1) and cross-validation (CNN2–4) approaches. To verify generalisability, we used two external datasets with different populations and MRI scan characteristics to evaluate the model. To demonstrate its usability, we included the external dataset’s images in the cross-validation training (CNN3). To ensure that our model used only the brain signal on the image, we also predicted brain age using skull-stripped images (CNN4).
Results
The trained models achieved a mean absolute error of 2.99, 2.67, 2.67, and 3.08 years for CNN1–4, respectively. The model’s performance in the external dataset was in the typical range of mean absolute error (MAE) found in the literature for testing sets. Adding the external dataset to the training set (CNN3), overall, MAE is unaffected, but individual cohort MAE improves (5.63–2.25 years). Salience maps of predictions reveal that periventricular, temporal, and insular regions are the most important for age prediction.
Discussion
We provide indicators for using biological (predicted) brain age as a metric for age correction in neuroimaging studies as an alternative to the traditional chronological age. In conclusion, using different approaches, our CNN-based model showed good performance using one T1w brain MRI preprocessing step. The proposed CNN model is made publicly available for the research community to be easily implemented and used to study ageing and age-related disorders.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Clinical Geriatrics, Center for Alzheimer Research, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden.
- Department of Surgical Sciences, Functional Pharmacology and Neuroscience, Uppsala University, Uppsala, Sweden.
- Department of Biomedical Engineering and Health Systems, KTH Royal Institute of Technology, Stockholm, Sweden.
- Facultad de Ciencias de la Salud, Universidad Fernando Pessoa Canarias, Las Palmas, España.
- Department of Neuroimaging, Centre for Neuroimaging Sciences, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom.
Förderung
- NIA NIH HHS
Zitieren
APA
Dartora, C., Marseglia, A., Mårtensson, G., Rukh, G., Dang, J., Muehlboeck, J. S., Wahlund, L. O., Moreno, R., Barroso, J., Ferreira, D., Schiöth, H. B., Westman, E., Alzheimer’s Disease Neuroimaging Initiative, Australian Imaging Biomarkers and Lifestyle Flagship Study of Ageing, Japanese Alzheimer’s Disease Neuroimaging Initiative, & AddNeuroMed Consortium (2024). A deep learning model for brain age prediction using minimally preprocessed T1w images as input. Frontiers in Aging Neuroscience, 15. https://doi.org/10.3389/fnagi.2023.1303036
Vancouver
Dartora C, Marseglia A, Mårtensson G, Rukh G, Dang J, Muehlboeck JS, et al. A deep learning model for brain age prediction using minimally preprocessed T1w images as input. Frontiers in Aging Neuroscience. 2024;15. doi:10.3389/fnagi.2023.1303036
BibTeX
@article{Dartora2024,
author = {Dartora, Caroline and Marseglia, Anna and Mårtensson, Gustav and Rukh, Gull and Dang, Junhua and Muehlboeck, J-Sebastian and Wahlund, Lars-Olof and Moreno, Rodrigo and Barroso, José and Ferreira, Daniel and Schiöth, Helgi B and Westman, Eric and Alzheimer’s Disease Neuroimaging Initiative, Alzheimer’s Disease Neuroimaging Initiative and Australian Imaging Biomarkers and Lifestyle Flagship Study of Ageing, Australian Imaging Biomarkers and Lifestyle Flagship Study of Ageing and Japanese Alzheimer’s Disease Neuroimaging Initiative, Japanese Alzheimer’s Disease Neuroimaging Initiative and AddNeuroMed Consortium, AddNeuroMed Consortium},
title = {A deep learning model for brain age prediction using minimally preprocessed T1w images as input},
journal = {Frontiers in Aging Neuroscience},
year = {2024},
volume = {15},
doi = {10.3389/fnagi.2023.1303036}
}
EUVIMED