A voxel-level approach to brain age prediction: A method to assess regional brain aging

Neha Gianchandani1,20000-0003-0822-4554, Mahsa Dibaji30009-0004-3166-7737, Johanna Ospel4,50000-0003-0029-6764, Fernando Vega10000-0003-0013-8133, Mariana Bento1,3,20000-0001-5125-0294, M. Ethan MacDonald1,3,4,20000-0001-5421-3536, Roberto Souza3,20000-0001-7824-5217
1: Department of Biomedical Engineering, University of Calgary, 2: Hotchkiss Brain Institute, University of Calgary, 3: Department of Electrical and Software Engineering, University of Calgary, 4: Department of Radiology, University of Calgary, 5: Department of Clinical Neurosciences, University of Calgary
Publication date: 2024/04/25
PDF · Code · arXiv


Brain aging is a regional phenomenon, a facet that remains relatively under-explored within the realm of brain age prediction research using machine learning methods. Voxel-level predictions can provide localized brain age estimates that can provide granular insights into the regional aging processes. This is essential to understand the differences in aging trajectories in healthy versus diseased subjects. In this work, a deep learning-based multitask model is proposed for voxel-level brain age prediction from T1-weighted magnetic resonance images. The proposed model outperforms the models existing in the literature and yields valuable clinical insights when applied to both healthy and diseased populations. Regional analysis is performed on the voxel-level brain age predictions to understand aging trajectories of known anatomical regions in the brain and show that there exist disparities in regional aging trajectories of healthy subjects compared to ones with underlying neurological disorders such as Dementia and more specifically, Alzheimer’s disease. Our code is available at https://github.com/nehagianchandani/Voxel-level-brain-age-prediction


voxel-level brain age prediction · T1-weighted MRI · regional brain aging · deep learning

Bibtex @article{melba:2024:007:gianchandani, title = "A voxel-level approach to brain age prediction: A method to assess regional brain aging", author = "Gianchandani, Neha and Dibaji, Mahsa and Ospel, Johanna and Vega, Fernando and Bento, Mariana and MacDonald, M. Ethan and Souza, Roberto", journal = "Machine Learning for Biomedical Imaging", volume = "2", issue = "April 2024 issue", year = "2024", pages = "761--795", issn = "2766-905X", doi = "https://doi.org/10.59275/j.melba.2024-4dg2", url = "https://melba-journal.org/2024:007" }
RISTY - JOUR AU - Gianchandani, Neha AU - Dibaji, Mahsa AU - Ospel, Johanna AU - Vega, Fernando AU - Bento, Mariana AU - MacDonald, M. Ethan AU - Souza, Roberto PY - 2024 TI - A voxel-level approach to brain age prediction: A method to assess regional brain aging T2 - Machine Learning for Biomedical Imaging VL - 2 IS - April 2024 issue SP - 761 EP - 795 SN - 2766-905X DO - https://doi.org/10.59275/j.melba.2024-4dg2 UR - https://melba-journal.org/2024:007 ER -

2024:007 cover