Enhancing brain age estimation under uncertainty: A spectral-normalized neural gaussian process approach utilizing 2.5D slicing

Brain age gap, the difference between estimated brain age and chronological age via magnetic resonance imaging, has emerged as a pivotal biomarker in the detection of brain abnormalities. While deep learning is accurate in estimating brain age, the absence of uncertainty estimation may pose risks in...

Full description

Saved in:
Bibliographic Details
Main Authors: Zeqiang Linli, Xingcheng Liang, Zhenhua Zhang, Kang Hu, Shuixia Guo
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:NeuroImage
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1053811925001867
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849699225187647488
author Zeqiang Linli
Xingcheng Liang
Zhenhua Zhang
Kang Hu
Shuixia Guo
author_facet Zeqiang Linli
Xingcheng Liang
Zhenhua Zhang
Kang Hu
Shuixia Guo
author_sort Zeqiang Linli
collection DOAJ
description Brain age gap, the difference between estimated brain age and chronological age via magnetic resonance imaging, has emerged as a pivotal biomarker in the detection of brain abnormalities. While deep learning is accurate in estimating brain age, the absence of uncertainty estimation may pose risks in clinical use. Moreover, current 3D brain age models are intricate, and using 2D slices hinders comprehensive dimensional data integration. Here, we introduced Spectral-normalized Neural Gaussian Process (SNGP) accompanied by 2.5D slice approach for seamless uncertainty integration in a single network with low computational expenses, and extra dimensional data integration without added model complexity. Subsequently, we compared different deep learning methods for estimating brain age uncertainty via the Pearson correlation coefficient, a metric that helps circumvent systematic underestimation of uncertainty during training. SNGP shows excellent uncertainty estimation and generalization on a dataset of 11 public datasets (N = 6327), with competitive predictive performance (MAE=2.95). Besides, SNGP demonstrates superior generalization performance (MAE=3.47) on an independent validation set (N = 301). Additionally, we conducted five controlled experiments to validate our method. Firstly, uncertainty adjustment in brain age estimation improved the detection of accelerated brain aging in adolescents with ADHD, with a 38% increase in effect size after adjustment. Secondly, the SNGP model exhibited OOD detection capabilities, showing significant differences in uncertainty across Asian and non-Asian datasets. Thirdly, the performance of DenseNet as a backbone for SNGP was slightly better than ResNeXt, attributed to DenseNet's feature reuse capability, with robust generalization on an independent validation set. Fourthly, site effect harmonization led to a decline in model performance, consistent with previous studies. Finally, the 2.5D slice approach significantly outperformed 2D methods, improving model performance without increasing network complexity. In conclusion, we present a cost-effective method for estimating brain age with uncertainty, utilizing 2.5D slicing for enhanced performance, showcasing promise for clinical applications.
format Article
id doaj-art-d7f26e4ba0694f70a2c5e9f00e2d861f
institution DOAJ
issn 1095-9572
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series NeuroImage
spelling doaj-art-d7f26e4ba0694f70a2c5e9f00e2d861f2025-08-20T03:18:41ZengElsevierNeuroImage1095-95722025-05-0131112118410.1016/j.neuroimage.2025.121184Enhancing brain age estimation under uncertainty: A spectral-normalized neural gaussian process approach utilizing 2.5D slicingZeqiang Linli0Xingcheng Liang1Zhenhua Zhang2Kang Hu3Shuixia Guo4School of Mathematics and Statistics, Guangdong University of Foreign Studies, Guangzhou, 510420, PR China; Laboratory of Language Engineering and Computing, Guangdong University of Foreign Studies, 510420, Guangzhou, PR China; MOE-LCSM, School of Mathematics and Statistics, Hunan Normal University, Changsha, 410006, PR ChinaSchool of Mathematics and Statistics, Guangdong University of Foreign Studies, Guangzhou, 510420, PR China; Laboratory of Language Engineering and Computing, Guangdong University of Foreign Studies, 510420, Guangzhou, PR ChinaSchool of Mathematics and Statistics, Guangdong University of Foreign Studies, Guangzhou, 510420, PR China; Laboratory of Language Engineering and Computing, Guangdong University of Foreign Studies, 510420, Guangzhou, PR ChinaSchool of Information Engineering, Wuhan Business University, Wuhan, 430056, PR ChinaMOE-LCSM, School of Mathematics and Statistics, Hunan Normal University, Changsha, 410006, PR China; Key Laboratory of Applied Statistics and Data Science, Hunan Normal University, College of Hunan Province, Changsha, 410006, PR ChinaBrain age gap, the difference between estimated brain age and chronological age via magnetic resonance imaging, has emerged as a pivotal biomarker in the detection of brain abnormalities. While deep learning is accurate in estimating brain age, the absence of uncertainty estimation may pose risks in clinical use. Moreover, current 3D brain age models are intricate, and using 2D slices hinders comprehensive dimensional data integration. Here, we introduced Spectral-normalized Neural Gaussian Process (SNGP) accompanied by 2.5D slice approach for seamless uncertainty integration in a single network with low computational expenses, and extra dimensional data integration without added model complexity. Subsequently, we compared different deep learning methods for estimating brain age uncertainty via the Pearson correlation coefficient, a metric that helps circumvent systematic underestimation of uncertainty during training. SNGP shows excellent uncertainty estimation and generalization on a dataset of 11 public datasets (N = 6327), with competitive predictive performance (MAE=2.95). Besides, SNGP demonstrates superior generalization performance (MAE=3.47) on an independent validation set (N = 301). Additionally, we conducted five controlled experiments to validate our method. Firstly, uncertainty adjustment in brain age estimation improved the detection of accelerated brain aging in adolescents with ADHD, with a 38% increase in effect size after adjustment. Secondly, the SNGP model exhibited OOD detection capabilities, showing significant differences in uncertainty across Asian and non-Asian datasets. Thirdly, the performance of DenseNet as a backbone for SNGP was slightly better than ResNeXt, attributed to DenseNet's feature reuse capability, with robust generalization on an independent validation set. Fourthly, site effect harmonization led to a decline in model performance, consistent with previous studies. Finally, the 2.5D slice approach significantly outperformed 2D methods, improving model performance without increasing network complexity. In conclusion, we present a cost-effective method for estimating brain age with uncertainty, utilizing 2.5D slicing for enhanced performance, showcasing promise for clinical applications.http://www.sciencedirect.com/science/article/pii/S1053811925001867Brain age estimationDeep learningUncertainty estimation
spellingShingle Zeqiang Linli
Xingcheng Liang
Zhenhua Zhang
Kang Hu
Shuixia Guo
Enhancing brain age estimation under uncertainty: A spectral-normalized neural gaussian process approach utilizing 2.5D slicing
NeuroImage
Brain age estimation
Deep learning
Uncertainty estimation
title Enhancing brain age estimation under uncertainty: A spectral-normalized neural gaussian process approach utilizing 2.5D slicing
title_full Enhancing brain age estimation under uncertainty: A spectral-normalized neural gaussian process approach utilizing 2.5D slicing
title_fullStr Enhancing brain age estimation under uncertainty: A spectral-normalized neural gaussian process approach utilizing 2.5D slicing
title_full_unstemmed Enhancing brain age estimation under uncertainty: A spectral-normalized neural gaussian process approach utilizing 2.5D slicing
title_short Enhancing brain age estimation under uncertainty: A spectral-normalized neural gaussian process approach utilizing 2.5D slicing
title_sort enhancing brain age estimation under uncertainty a spectral normalized neural gaussian process approach utilizing 2 5d slicing
topic Brain age estimation
Deep learning
Uncertainty estimation
url http://www.sciencedirect.com/science/article/pii/S1053811925001867
work_keys_str_mv AT zeqianglinli enhancingbrainageestimationunderuncertaintyaspectralnormalizedneuralgaussianprocessapproachutilizing25dslicing
AT xingchengliang enhancingbrainageestimationunderuncertaintyaspectralnormalizedneuralgaussianprocessapproachutilizing25dslicing
AT zhenhuazhang enhancingbrainageestimationunderuncertaintyaspectralnormalizedneuralgaussianprocessapproachutilizing25dslicing
AT kanghu enhancingbrainageestimationunderuncertaintyaspectralnormalizedneuralgaussianprocessapproachutilizing25dslicing
AT shuixiaguo enhancingbrainageestimationunderuncertaintyaspectralnormalizedneuralgaussianprocessapproachutilizing25dslicing