# Brain Age Estimation From MRI Using Cascade Networks with Ranking Loss Source: [Brain Age Estimation From MRI Using Cascade Networks with Ranking Loss]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:17:37.192Z Authors: Jian Cheng, Ziyang Liu, Hao Guan, Zhenzhou Wu, Haogang Zhu, Jiyang Jiang, Wei Wen, Dacheng Tao, Tao Liu Published: 2021-06-06T07:11:25.000Z ## Abstract Chronological age of healthy people is able to be predicted accurately using deep neural networks from neuroimaging data, and the predicted brain age could serve as a biomarker for detecting aging-related diseases. In this paper, a novel 3D convolutional network, called two-stage-age-network (TSAN), is proposed to estimate brain age from T1-weighted MRI data. Compared with existing methods, TSAN has the following improvements. First, TSAN uses a two-stage cascade network architecture, where the first-stage network estimates a rough brain age, then the second-stage network estimates the brain age more accurately from the discretized brain age by the first-stage network. Second, to our knowledge, TSAN is the first work to apply novel ranking losses in brain age estimation, together with the traditional mean square error (MSE) loss. Third, densely connected paths are used to combine feature maps with different scales. The experiments with $6586$ MRIs showed that TSAN could provide accurate brain age estimation, yielding mean absolute error (MAE) of $2.428$ and Pearson's correlation coefficient (PCC) of $0.985$, between the estimated and chronological ages. Furthermore, using the brain age gap between brain age and chronological age as a biomarker, Alzheimer's disease (AD) and Mild Cognitive Impairment (MCI) can be distinguished from healthy control (HC) subjects by support vector machine (SVM). Classification AUC in AD/HC and MCI/HC was $0.904$ and $0.823$, respectively. It showed that brain age gap is an effective biomarker associated with risk of dementia, and has potential for early-stage dementia risk screening. The codes and trained models have been released on GitHub: https://github.com/Milan-BUAA/TSAN-brain-age-estimation. ## 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 Adult In-domain](): Brain Age Estimation; Adult In-domain; MAE: 3.71. - [Brain age estimation on Child Out-of-domain](): Brain Age Estimation; Child Out-of-domain; MAE: 4.68. - [Brain age estimation on Fetal In-domain](): Brain Age Estimation; Fetal In-domain; MAE: 0.14. - [Brain age estimation on Elderly In-domain](): Brain Age Estimation; Elderly In-domain; MAE: 6.3. - [Brain age estimation on Neonatal In-domain](): Brain Age Estimation; Neonatal In-domain; Mean Absolute Error (MAE): 0.12. - [Brain age estimation on Fetal Out-of-domain](): Brain Age Estimation; Fetal Out-of-domain; MAE: 0.68. - [Brain age estimation on Neonatal Out-of-domain](): Brain Age Estimation; Neonatal Out-of-domain; MAE: 0.72. - [Brain age estimation on Infant In-domain](): Brain Age Estimation; Infant In-domain; MAE: 0.65. - [Brain age estimation on Child In-domain](): Brain Age Estimation; Child In-domain; MAE: 1.97. - [Brain age estimation on Infant Out-of-domain](): Brain Age Estimation; Infant Out-of-domain; MAE: 1.43. - [Brain age estimation on Adult Out-of-domain](): Brain Age Estimation; Adult Out-of-domain; MAE: 45.71. - [Brain age estimation on Elderly Out-of-domain](): Brain Age Estimation; Elderly Out-of-domain; MAE: 56.3. ## Original sources and implementation [Original paper]() [PDF]()