# Ordinal Classification with Distance Regularization for Robust Brain Age Prediction Source: [Ordinal Classification with Distance Regularization for Robust Brain Age Prediction]() Collection index: [llms.txt]() Data updated: 2025-12-22T10:41:12.241Z Authors: Jay Shah, Md Mahfuzur Rahman Siddiquee, Yi Su, Teresa Wu, Baoxin Li Published: 2023-10-25T20:39:07.000Z ## Abstract Age is one of the major known risk factors for Alzheimer's Disease (AD). Detecting AD early is crucial for effective treatment and preventing irreversible brain damage. Brain age, a measure derived from brain imaging reflecting structural changes due to aging, may have the potential to identify AD onset, assess disease risk, and plan targeted interventions. Deep learning-based regression techniques to predict brain age from magnetic resonance imaging (MRI) scans have shown great accuracy recently. However, these methods are subject to an inherent regression to the mean effect, which causes a systematic bias resulting in an overestimation of brain age in young subjects and underestimation in old subjects. This weakens the reliability of predicted brain age as a valid biomarker for downstream clinical applications. Here, we reformulate the brain age prediction task from regression to classification to address the issue of systematic bias. Recognizing the importance of preserving ordinal information from ages to understand aging trajectory and monitor aging longitudinally, we propose a novel ORdinal Distance Encoded Regularization (ORDER) loss that incorporates the order of age labels, enhancing the model's ability to capture age-related patterns. Extensive experiments and ablation studies demonstrate that this framework reduces systematic bias, outperforms state-of-art methods by statistically significant margins, and can better capture subtle differences between clinical groups in an independent AD dataset. Our implementation is publicly available at https://github.com/jaygshah/Robust-Brain-Age-Prediction. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Brain age estimation on Neonatal Out-of-domain](): Brain Age Estimation; Neonatal Out-of-domain; MAE: 0.16. - [Brain age estimation on Neonatal In-domain](): Brain Age Estimation; Neonatal In-domain; Mean Absolute Error (MAE): 0.05. - [Brain age estimation on Infant In-domain](): Brain Age Estimation; Infant In-domain; MAE: 0.32. - [Brain age estimation on Child In-domain](): Brain Age Estimation; Child In-domain; MAE: 1.28. - [Brain age estimation on Adult In-domain](): Brain Age Estimation; Adult In-domain; MAE: 3.82. - [Brain age estimation on Fetal Out-of-domain](): Brain Age Estimation; Fetal Out-of-domain; MAE: 0.25. - [Brain age estimation on Infant Out-of-domain](): Brain Age Estimation; Infant Out-of-domain; MAE: 0.42. - [Brain age estimation on Elderly Out-of-domain](): Brain Age Estimation; Elderly Out-of-domain; MAE: 36.73. - [Brain age estimation on Fetal In-domain](): Brain Age Estimation; Fetal In-domain; MAE: 0.21. - [Brain age estimation on Adult Out-of-domain](): Brain Age Estimation; Adult Out-of-domain; MAE: 30.07. - [Brain age estimation on Elderly In-domain](): Brain Age Estimation; Elderly In-domain; MAE: 8.92. - [Brain age estimation on Child Out-of-domain](): Brain Age Estimation; Child Out-of-domain; MAE: 7.56. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()