MRI-Based Brain Age Estimation with Supervised Contrastive Learning of Continuous Representation

2025-11-26

AI Summary

Existing brain age estimation models struggle to capture the continuous, morphological evolution of the brain across the lifespan. To address this, we propose a supervised contrastive learning framework for brain age prediction from T1-weighted MRI. Our method introduces a novel Rank-N-Contrast loss that explicitly enforces ordinal relationships among anatomical features along the aging trajectory. Integrated with a ResNet backbone and Grad-CAM-based interpretability analysis, the model enhances regression representation quality and identifies age-sensitive neuroanatomical regions. On a small-scale dataset, it achieves a mean absolute error of 4.27 years (R² = 0.93), significantly outperforming conventional deep regression approaches. Furthermore, we demonstrate that predicted brain age gap—i.e., the deviation between estimated and chronological age—exhibits statistically significant correlations with clinical severity scores in Alzheimer’s disease and Parkinson’s disease, validating its potential as a biomarker for neurodegenerative disorders.

Technology Category

• Humans and AI: Brain-Sensing and Analysis
• Machine Learning: Learning Preferences or Rankings
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

MRI-based brain age estimation models aim to assess a subject's biological brain age based on information, such as neuroanatomical features. Various factors, including neurodegenerative diseases, can accelerate brain aging and measuring this phenomena could serve as a potential biomarker for clinical applications. While deep learning (DL)-based regression has recently attracted major attention, existing approaches often fail to capture the continuous nature of neuromorphological changes, potentially resulting in sub-optimal feature representation and results. To address this, we propose to use supervised contrastive learning with the recent Rank-N-Contrast (RNC) loss to estimate brain age based on widely used T1w structural MRI for the first time and leverage Grad-RAM to visually explain regression results. Experiments show that our proposed method achieves a mean absolute error (MAE) of 4.27 years and an $R^2$ of 0.93 with a limited dataset of training samples, significantly outperforming conventional deep regression with the same ResNet backbone while performing better or comparably with the state-of-the-art methods with significantly larger training data. Furthermore, Grad-RAM revealed more nuanced features related to age regression with the RNC loss than conventional deep regression. As an exploratory study, we employed the proposed method to estimate the gap between the biological and chronological brain ages in Alzheimer's Disease and Parkinson's disease patients, and revealed the correlation between the brain age gap and disease severity, demonstrating its potential as a biomarker in neurodegenerative disorders.

Problem

• Estimates biological brain age from MRI using supervised contrastive learning.
• Addresses suboptimal feature representation in deep learning regression models.
• Explores brain age gap as a biomarker for neurodegenerative diseases.

Innovation

• Supervised contrastive learning with RNC loss
• Grad-RAM for visual explanation of regression
• Estimates brain age from T1w MRI data