JMIR Publications

ABSTRACT

Background:

Precise assessment of brain aging is crucial for early detection of neurodegenerative disorders and aiding clinical practice. Although T1-weighted MRI-based deep neural networks excel in this task, existing methods still have room for improvement in capturing local morphological variations across brain regions and preserving the inherent neurobiological topological structures.

Objective:

To develop and validate a deep learning framework that incorporates both brain connectivity and complexity for accurate brain aging estimation, aiming to facilitate early identification of neurodegenerative diseases.

Methods:

We utilized 5,889 T1-weighted MRI scans from the Alzheimer’s Disease Neuroimaging Initiative studies (ADNI) dataset. We proposed a novel Brain Vision Graph Neural Network (BVGN), which incorporated neurobiologically informed feature extraction modules and global association mechanisms for brain age estimation, aiming to provide a sensitive deep-learning-based imaging biomarker for early detection of mild cognitive impairment (MCI). The model’s performance was evaluated using Mean Absolute Error (MAE) against benchmark models, while its generalization capability was further validated on an external UK Biobank (UKB) dataset. We calculated the brain age gap across distinct cognitive states and conducted multiple logistic regressions to compare its discriminative capacity against conventional cognitive-related variables in distinguishing cognitively unimpaired (CN) and MCI. Longitudinal track, Cox regression and Kaplan-Meier plots were used to investigate the brain age gap’s longitudinal performance.

Results:

BVGN achieved an MAE of 2.15 years in the 5889 MRI scans from the ADNI dataset, surpassing current state-of-the-art approaches while obtaining interpretable saliency map and graph theory supported by medical evidence. Furthermore, its performance was validated on the UKB cohort (N=34,352) with an MAE of 2.49 years. The brain age gap derived from BVGN exhibited significant difference across cognitive states (CN vs. MCI vs. Alzheimer’s Disease (AD)) (P<.001), and demonstrated highest discriminative capacity between CN and MCI than general cognitive assessments, brain volume features and APOE4 carriage (area under the receiver operating characteristic curve (AUC) of 0.885 vs. AUC ranging from 0.646 to 0.815). Brain age gap exhibited clinical feasibility combined with FAQ, with improved discriminative capacity in models achieving lower MAEs (AUC of 0.945 vs. 0. 923 and 0.911; AUC of 0.935 vs. 0.900 and 0.881). An increasing brain age gap identified by BVGN may indicate underlying pathological changes in the CN to MCI progression, with each unit increase linked to a 55% (Hazard Ratio (HR) = 1.55, confidence-intervals (CI): 1.13-2.13, P = .006) higher risk of cognitive decline in CN individuals and a 29% (HR = 1.29, CI: 1.09-1.51, P = .002) increase in MCI individuals.

Conclusions:

BVGN offers a precise framework for brain aging assessment, demonstrates strong generalization on external large-scale dataset, and proposes novel interpretability strategies to elucidate multi-regional cooperative aging patterns. Brain age gap derived from BVGN is validated a sensitive biomarker for early identification of MCI and predicting cognitive decline, offering substantial potential for clinical applications. Clinical Trial: Not applicable.