EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Brain Age Prediction: Deep Models Need a Hand to Generalize

Reza Rajabli iD, Mahdie Soltaninejad, Vladimir S Fonov, Danilo Bzdok, D Louis Collins

Human Brain Mapping · 2025

DOI: 10.1002/hbm.70254 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Human Brain Mapping, 2025. Verfasst von Reza Rajabli und 4 weiteren Autor:innen. Beteiligte Einrichtung: McConnell Brain Imaging Centre, Montréal Neurological Institute, McGill University, Montréal, Canada. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Brain, Deep Learning, Aging. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: La Fondation Famille Louise & André Charron, Fondation Brain Canada.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting brain age from T1‐weighted MRI is a promising marker for understanding brain aging and its associated conditions. While deep learning models have shown success in reducing the mean absolute error (MAE) of predicted brain age, concerns about robust and accurate generalization in new data limit their clinical applicability. The large number of trainable parameters, combined with limited medical imaging training data, contributes to this challenge, often resulting in a generalization gap where there is a significant discrepancy between model performance on training data versus unseen data. In this study, we assess a deep model, SFCN‐reg, based on the VGG‐16 architecture, and address the generalization gap through comprehensive preprocessing, extensive data augmentation, and model regularization. Using training data from the UK Biobank, we demonstrate substantial improvements in model performance. Specifically, our approach reduces the generalization MAE by 47% (from 5.25 to 2.79 years) in the Alzheimer's Disease Neuroimaging Initiative dataset and by 12% (from 4.35 to 3.75 years) in the Australian Imaging, Biomarker and Lifestyle dataset. Furthermore, we achieve up to 13% reduction in scan‐rescan error (from 0.80 to 0.70 years) while enhancing the model's robustness to registration errors. Feature importance maps highlight anatomical regions used to predict age. These results highlight the critical role of high‐quality preprocessing and robust training techniques in improving accuracy and narrowing the generalization gap, both necessary steps toward the clinical use of brain age prediction models. Our study makes valuable contributions to neuroimaging research by offering a potential pathway to improve the clinical applicability of deep learning models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingBrainDeep LearningAgingNeuroimagingHumansAgedMaleFemaleMiddle AgedAlzheimer DiseaseAged, 80 and over

Stichwörter der Autor:innen

T1‐weighted MRIbrain age predictiondeep learninggeneralizabilityrobustness

Autor:innen und Institutionen

  • McConnell Brain Imaging Centre, Montréal Neurological Institute, McGill University, Montréal, Canada.
  • Mila-Quebec Artificial Intelligence Institute, Montreal, Canada.

ORCID-Profile: Reza Rajabli

Förderung

  • La Fondation Famille Louise & André Charron
  • Fondation Brain Canada

Zitieren

APA

Rajabli, R., Soltaninejad, M., Fonov, V. S., Bzdok, D., & Collins, D. L. (2025). Brain Age Prediction: Deep Models Need a Hand to Generalize. Human Brain Mapping. https://doi.org/10.1002/hbm.70254

Vancouver

Rajabli R, Soltaninejad M, Fonov VS, Bzdok D, Collins DL. Brain Age Prediction: Deep Models Need a Hand to Generalize. Human Brain Mapping. 2025. doi:10.1002/hbm.70254

BibTeX
@article{Rajabli2025,
  author = {Rajabli, Reza and Soltaninejad, Mahdie and Fonov, Vladimir S and Bzdok, Danilo and Collins, D Louis},
  title = {Brain Age Prediction: Deep Models Need a Hand to Generalize},
  journal = {Human Brain Mapping},
  year = {2025},
  doi = {10.1002/hbm.70254}
}
Kostenlos starten →