Brain age estimation using multi-feature-based networks

Xia Liu; Iman Beheshti; Weihao Zheng; Yongchao Li; Shan Li; Ziyang Zhao; Zhijun Yao; Bin Hu

doi:10.1016/j.compbiomed.2022.105285

Brain age estimation using multi-feature-based networks

Comput Biol Med. 2022 Apr:143:105285. doi: 10.1016/j.compbiomed.2022.105285. Epub 2022 Feb 5.

Authors

Xia Liu¹, Iman Beheshti², Weihao Zheng³, Yongchao Li³, Shan Li³, Ziyang Zhao³, Zhijun Yao⁴, Bin Hu⁵

Affiliations

¹ School of Computer Science, Qinghai Normal University, Xining, Qinghai Province, China.
² Department of Human Anatomy and Cell Science, University of Manitoba, Canada.
³ Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, China.
⁴ Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, China. Electronic address: yaozj@lzu.edu.cn.
⁵ School of Computer Science, Qinghai Normal University, Xining, Qinghai Province, China; Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, China; CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, China; Joint Research Center for Cognitive Neurosensor Technology of Lanzhou University & Institute of Semiconductors, Chinese Academy of Sciences, China; Engineering Research Center of Open Source Software and Real-Time System (Lanzhou University), Ministry of Education, Lanzhou, China. Electronic address: bh@lzu.edu.cn.

PMID: 35158116
DOI: 10.1016/j.compbiomed.2022.105285

Abstract

Studying brain aging improves our understanding in differentiating typical and atypical aging. Directly utilizing traditional morphological features for brain age estimation did not show significant performance in healthy controls (HCs), which may be due to the negligence of the information of structural similarities among cortical regions. For this issue, the multi-feature-based network (MFN) built upon morphological features can be employed to describe these similarities. Based on this, we hypothesized that the MFN is more efficient and robust than traditional morphological features in brain age estimating. In this work, we used six different types of morphological features (i.e., cortical volume, cortical thickness, curvature index, folding index, local gyrification index, and surface area) to build individual MFN for brain age estimation. The efficacy of MFN was estimated on 2501 HCs with T1-weighted structural magnetic resonance imaging (sMRI) data and compared with traditional morphological features. We attained a mean absolute error (MAE) of 3.73 years using the proposed method on an independent test set, whereas a mean absolute error of 5.30 years was derived from morphological features. Our experimental results demonstrated that the MFN is an efficient and robust metric for estimating brain age.

Keywords: Brain age; Multi-feature-based networks; Support vector regression; sMRI.