Home > Research > Publications & Outputs > Robust Brain Age Estimation based on sMRI via N...

Electronic data

  • BrainAge_TNSRE_Final

    Rights statement: ©2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

    Accepted author manuscript, 1.99 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

Robust Brain Age Estimation based on sMRI via Nonlinear Age-Adaptive Ensemble Learning

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Robust Brain Age Estimation based on sMRI via Nonlinear Age-Adaptive Ensemble Learning. / Zhang, Zhaonian; Jiang, Richard; Zhang, Ce et al.
In: IEEE Transactions on Neural Systems and Rehabilitation Engineering , Vol. 30, 31.08.2022, p. 2146 - 2156.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Zhang, Z, Jiang, R, Zhang, C, Williams, B, Jiang, Z, Li, C-T, Chazot, PL, Pavese, N, Bouridane, A & Baghdadi, A 2022, 'Robust Brain Age Estimation based on sMRI via Nonlinear Age-Adaptive Ensemble Learning', IEEE Transactions on Neural Systems and Rehabilitation Engineering , vol. 30, pp. 2146 - 2156. https://doi.org/10.1109/TNSRE.2022.3190467

APA

Zhang, Z., Jiang, R., Zhang, C., Williams, B., Jiang, Z., Li, C-T., Chazot, P. L., Pavese, N., Bouridane, A., & Baghdadi, A. (2022). Robust Brain Age Estimation based on sMRI via Nonlinear Age-Adaptive Ensemble Learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering , 30, 2146 - 2156. https://doi.org/10.1109/TNSRE.2022.3190467

Vancouver

Zhang Z, Jiang R, Zhang C, Williams B, Jiang Z, Li C-T et al. Robust Brain Age Estimation based on sMRI via Nonlinear Age-Adaptive Ensemble Learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering . 2022 Aug 31;30:2146 - 2156. Epub 2022 Jul 13. doi: 10.1109/TNSRE.2022.3190467

Author

Zhang, Zhaonian ; Jiang, Richard ; Zhang, Ce et al. / Robust Brain Age Estimation based on sMRI via Nonlinear Age-Adaptive Ensemble Learning. In: IEEE Transactions on Neural Systems and Rehabilitation Engineering . 2022 ; Vol. 30. pp. 2146 - 2156.

Bibtex

@article{d97298e748c44602868ed41c4e94d042,
title = "Robust Brain Age Estimation based on sMRI via Nonlinear Age-Adaptive Ensemble Learning",
abstract = "Precise prediction on brain age is urgently needed by many bi-omedical areas including mental rehabilitation prognosis as well as various medicine or treatment trials. People began to realize that contrasting physical (real) age and predicted brain age can help to highlight brain issues and evaluate if patients{\textquoteright} brains are healthy or not. Such age prediction is often challenging for sin-gle model-based prediction, while the conditions of brains vary drastically over age. In this work, we present an age-adaptive ensemble model that is based on the combination of four differ-ent machine learning algorithms, including a support vector machine (SVR), a convolutional neural network (CNN) model, and the popular GoogLeNet and ResNet deep networks. The ensemble model proposed here is nonlinearly adaptive, where age is taken as a key factor in the nonlinear combination of various single-algorithm-based independent models. In our age-adaptive ensemble method, the weights of each model are learned automatically as nonlinear functions over age instead of fixed values, while brain age estimation is based on such an age-adaptive integration of various single models. The quality of the model is quantified by the mean absolute errors (MAE) and spearman correlation between the predicted age and the actual age, with the least MAE and the highest Spearman correlation representing the highest accuracy in age prediction. By testing on the Predictive Analysis Challenge 2019 (PAC 2019) dataset, our novel ensemble model has achieved a MAE down to 3.19, which is a significantly increased accuracy in this brain age competition. If deployed in the real world, our novel ensemble model having an improved accuracy could potentially help doc-tors to identify the risk of brain diseases more accurately and quickly, thus helping pharmaceutical companies develop drugs or treatments precisely, and potential offer a new powerful tool for researchers in the field of brain science.",
keywords = "Brain age, biomarks, ensemble deep learning, mental healthcare, rehabilitation",
author = "Zhaonian Zhang and Richard Jiang and Ce Zhang and Bryan Williams and Ziping Jiang and Chang-Tsun Li and Chazot, {Paul L} and Nicola Pavese and Ahmed Bouridane and A Baghdadi",
note = "{\textcopyright}2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.",
year = "2022",
month = aug,
day = "31",
doi = "10.1109/TNSRE.2022.3190467",
language = "English",
volume = "30",
pages = "2146 -- 2156",
journal = "IEEE Transactions on Neural Systems and Rehabilitation Engineering ",
issn = "1558-0210",
publisher = "IEEE Xplore",

}

RIS

TY - JOUR

T1 - Robust Brain Age Estimation based on sMRI via Nonlinear Age-Adaptive Ensemble Learning

AU - Zhang, Zhaonian

AU - Jiang, Richard

AU - Zhang, Ce

AU - Williams, Bryan

AU - Jiang, Ziping

AU - Li, Chang-Tsun

AU - Chazot, Paul L

AU - Pavese, Nicola

AU - Bouridane, Ahmed

AU - Baghdadi, A

N1 - ©2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2022/8/31

Y1 - 2022/8/31

N2 - Precise prediction on brain age is urgently needed by many bi-omedical areas including mental rehabilitation prognosis as well as various medicine or treatment trials. People began to realize that contrasting physical (real) age and predicted brain age can help to highlight brain issues and evaluate if patients’ brains are healthy or not. Such age prediction is often challenging for sin-gle model-based prediction, while the conditions of brains vary drastically over age. In this work, we present an age-adaptive ensemble model that is based on the combination of four differ-ent machine learning algorithms, including a support vector machine (SVR), a convolutional neural network (CNN) model, and the popular GoogLeNet and ResNet deep networks. The ensemble model proposed here is nonlinearly adaptive, where age is taken as a key factor in the nonlinear combination of various single-algorithm-based independent models. In our age-adaptive ensemble method, the weights of each model are learned automatically as nonlinear functions over age instead of fixed values, while brain age estimation is based on such an age-adaptive integration of various single models. The quality of the model is quantified by the mean absolute errors (MAE) and spearman correlation between the predicted age and the actual age, with the least MAE and the highest Spearman correlation representing the highest accuracy in age prediction. By testing on the Predictive Analysis Challenge 2019 (PAC 2019) dataset, our novel ensemble model has achieved a MAE down to 3.19, which is a significantly increased accuracy in this brain age competition. If deployed in the real world, our novel ensemble model having an improved accuracy could potentially help doc-tors to identify the risk of brain diseases more accurately and quickly, thus helping pharmaceutical companies develop drugs or treatments precisely, and potential offer a new powerful tool for researchers in the field of brain science.

AB - Precise prediction on brain age is urgently needed by many bi-omedical areas including mental rehabilitation prognosis as well as various medicine or treatment trials. People began to realize that contrasting physical (real) age and predicted brain age can help to highlight brain issues and evaluate if patients’ brains are healthy or not. Such age prediction is often challenging for sin-gle model-based prediction, while the conditions of brains vary drastically over age. In this work, we present an age-adaptive ensemble model that is based on the combination of four differ-ent machine learning algorithms, including a support vector machine (SVR), a convolutional neural network (CNN) model, and the popular GoogLeNet and ResNet deep networks. The ensemble model proposed here is nonlinearly adaptive, where age is taken as a key factor in the nonlinear combination of various single-algorithm-based independent models. In our age-adaptive ensemble method, the weights of each model are learned automatically as nonlinear functions over age instead of fixed values, while brain age estimation is based on such an age-adaptive integration of various single models. The quality of the model is quantified by the mean absolute errors (MAE) and spearman correlation between the predicted age and the actual age, with the least MAE and the highest Spearman correlation representing the highest accuracy in age prediction. By testing on the Predictive Analysis Challenge 2019 (PAC 2019) dataset, our novel ensemble model has achieved a MAE down to 3.19, which is a significantly increased accuracy in this brain age competition. If deployed in the real world, our novel ensemble model having an improved accuracy could potentially help doc-tors to identify the risk of brain diseases more accurately and quickly, thus helping pharmaceutical companies develop drugs or treatments precisely, and potential offer a new powerful tool for researchers in the field of brain science.

KW - Brain age

KW - biomarks

KW - ensemble deep learning

KW - mental healthcare

KW - rehabilitation

U2 - 10.1109/TNSRE.2022.3190467

DO - 10.1109/TNSRE.2022.3190467

M3 - Journal article

VL - 30

SP - 2146

EP - 2156

JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering

JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering

SN - 1558-0210

ER -