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...
Saved in:
| Main Authors: | , , , , |
|---|---|
| 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 |