# Robust brain age estimation from structural MRI with contrastive learning

arXiv: https://arxiv.org/abs/2507.01794 · HTML: https://mlsanity.com/paper/2507.01794/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 46 references that are in the map.
- First posted on arXiv 2 Jul 2025.

## Builds on (most cited first, 25 of 25)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2104.14548/) (2021)
- [Rank-N-Contrast: Learning Continuous Representations for Regression](https://mlsanity.com/paper/2210.01189/) (2022)
- [Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker](https://mlsanity.com/paper/1612.02572/) (2016)
- [Contrastive Learning with Continuous Proxy Meta-Data for 3D MRI Classification](https://mlsanity.com/paper/2106.08808/) (2021)
- [Detect and Correct Bias in Multi-Site Neuroimaging Datasets](https://mlsanity.com/paper/2002.05049/) (2020)
- [Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects](https://mlsanity.com/paper/1910.04597/) (2019)
- [Unbiased Supervised Contrastive Learning](https://mlsanity.com/paper/2211.05568/) (2022)
- [Rethinking the Augmentation Module in Contrastive Learning: Learning Hierarchical Augmentation Invariance with Expanded Views](https://mlsanity.com/paper/2206.00227/) (2022)
- [Global-Local Transformer for Brain Age Estimation](https://mlsanity.com/paper/2109.01663/) (2021)
- [Contrastive learning for regression in multi-site brain age prediction](https://mlsanity.com/paper/2211.08326/) (2022)
- [Anatomical Foundation Models for Brain MRIs](https://mlsanity.com/paper/2408.07079/) (2024)
- [Integrating Prior Knowledge in Contrastive Learning with Kernel](https://mlsanity.com/paper/2206.01646/) (2022)
- [Conditional Alignment and Uniformity for Contrastive Learning with Continuous Proxy Labels](https://mlsanity.com/paper/2111.05643/) (2021)
- [Benchmarking CNN on 3D Anatomical Brain MRI: Architectures, Data Augmentation and Deep Ensemble Learning](https://mlsanity.com/paper/2106.01132/) (2021)
- [Learning to diagnose cirrhosis from radiological and histological labels with joint self and weakly-supervised pretraining strategies](https://mlsanity.com/paper/2302.08427/) (2023)
- [Contrastive Learning with Adaptive Neighborhoods for Brain Age Prediction on 3D Stiffness Maps](https://mlsanity.com/paper/2408.00527/) (2024)

## Abstract (arXiv)

Estimating brain age from structural MRI has emerged as a powerful tool for characterizing normative and pathological aging. In this work, we explore contrastive learning as a scalable and robust alternative to L1-supervised approaches for brain age estimation. We introduce a novel contrastive loss function, Lexp, and evaluate it across multiple public neuroimaging datasets comprising over 20,000 scans. Our experiments reveal four key findings. First, scaling pre-training on diverse, multi-site data consistently improves generalization performance, cutting external mean absolute error (MAE) nearly in half. Second, Lexp is robust to site-related confounds, maintaining low scanner-predictability as training size increases. Third, contrastive models reliably capture accelerated aging in patients with cognitive impairment and Alzheimer's disease, as shown through brain age gap analysis, ROC curves, and longitudinal trends. Lastly, unlike L1-supervised baselines, Lexp maintains a strong correlation between brain age accuracy and downstream diagnostic performance, supporting its potential as a foundation model for neuroimaging. These results position contrastive learning as a promising direction for building generalizable and clinically meaningful brain representations.