Low-Rank Tensor Fusion for Enhanced Deep Learning-Based Multimodal Brain Age Estimation

<b>Background/Objectives:</b> A multimodal brain age estimation model could provide enhanced insights into brain aging. However, effectively integrating multimodal neuroimaging data to enhance the accuracy of brain age estimation remains a challenging task. <b>Methods:</b> In...

Full description

Saved in:
Bibliographic Details
Main Authors: Xia Liu, Guowei Zheng, Iman Beheshti, Shanling Ji, Zhinan Gou, Wenkuo Cui
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Brain Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3425/14/12/1252
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850242025595600896
author Xia Liu
Guowei Zheng
Iman Beheshti
Shanling Ji
Zhinan Gou
Wenkuo Cui
author_facet Xia Liu
Guowei Zheng
Iman Beheshti
Shanling Ji
Zhinan Gou
Wenkuo Cui
author_sort Xia Liu
collection DOAJ
description <b>Background/Objectives:</b> A multimodal brain age estimation model could provide enhanced insights into brain aging. However, effectively integrating multimodal neuroimaging data to enhance the accuracy of brain age estimation remains a challenging task. <b>Methods:</b> In this study, we developed an innovative data fusion technique employing a low-rank tensor fusion algorithm, tailored specifically for deep learning-based frameworks aimed at brain age estimation. Specifically, we utilized structural magnetic resonance imaging (sMRI), diffusion tensor imaging (DTI), and magnetoencephalography (MEG) to extract spatial–temporal brain features with different properties. These features were fused using the low-rank tensor algorithm and employed as predictors for estimating brain age. <b>Results:</b> Our prediction model achieved a desirable prediction accuracy on the independent test samples, demonstrating its robust performance. <b>Conclusions:</b> The results of our study suggest that the low-rank tensor fusion algorithm has the potential to effectively integrate multimodal data into deep learning frameworks for estimating brain age.
format Article
id doaj-art-5923ad0879f54d9dae784efc1a813b7d
institution OA Journals
issn 2076-3425
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Brain Sciences
spelling doaj-art-5923ad0879f54d9dae784efc1a813b7d2025-08-20T02:00:24ZengMDPI AGBrain Sciences2076-34252024-12-011412125210.3390/brainsci14121252Low-Rank Tensor Fusion for Enhanced Deep Learning-Based Multimodal Brain Age EstimationXia Liu0Guowei Zheng1Iman Beheshti2Shanling Ji3Zhinan Gou4Wenkuo Cui5School of Management Science and Information Engineering, Hebei University of Economics and Businesses, Shijiazhuang 050061, ChinaSchool of Computer Science and Technology, Harbin Institute of Technology, Weihai 264209, ChinaDepartment of Human Anatomy and Cell Science, University of Manitoba, Winnipeg, MB R3T 2N2, CanadaInstitute of Mental Health, Jining Medical University, Jining 272111, ChinaSchool of Management Science and Information Engineering, Hebei University of Economics and Businesses, Shijiazhuang 050061, ChinaSchool of Management Science and Information Engineering, Hebei University of Economics and Businesses, Shijiazhuang 050061, China<b>Background/Objectives:</b> A multimodal brain age estimation model could provide enhanced insights into brain aging. However, effectively integrating multimodal neuroimaging data to enhance the accuracy of brain age estimation remains a challenging task. <b>Methods:</b> In this study, we developed an innovative data fusion technique employing a low-rank tensor fusion algorithm, tailored specifically for deep learning-based frameworks aimed at brain age estimation. Specifically, we utilized structural magnetic resonance imaging (sMRI), diffusion tensor imaging (DTI), and magnetoencephalography (MEG) to extract spatial–temporal brain features with different properties. These features were fused using the low-rank tensor algorithm and employed as predictors for estimating brain age. <b>Results:</b> Our prediction model achieved a desirable prediction accuracy on the independent test samples, demonstrating its robust performance. <b>Conclusions:</b> The results of our study suggest that the low-rank tensor fusion algorithm has the potential to effectively integrate multimodal data into deep learning frameworks for estimating brain age.https://www.mdpi.com/2076-3425/14/12/1252brain agespatial–temporalmultimodallow-rank tensor fusionmachine learningdeep learning
spellingShingle Xia Liu
Guowei Zheng
Iman Beheshti
Shanling Ji
Zhinan Gou
Wenkuo Cui
Low-Rank Tensor Fusion for Enhanced Deep Learning-Based Multimodal Brain Age Estimation
Brain Sciences
brain age
spatial–temporal
multimodal
low-rank tensor fusion
machine learning
deep learning
title Low-Rank Tensor Fusion for Enhanced Deep Learning-Based Multimodal Brain Age Estimation
title_full Low-Rank Tensor Fusion for Enhanced Deep Learning-Based Multimodal Brain Age Estimation
title_fullStr Low-Rank Tensor Fusion for Enhanced Deep Learning-Based Multimodal Brain Age Estimation
title_full_unstemmed Low-Rank Tensor Fusion for Enhanced Deep Learning-Based Multimodal Brain Age Estimation
title_short Low-Rank Tensor Fusion for Enhanced Deep Learning-Based Multimodal Brain Age Estimation
title_sort low rank tensor fusion for enhanced deep learning based multimodal brain age estimation
topic brain age
spatial–temporal
multimodal
low-rank tensor fusion
machine learning
deep learning
url https://www.mdpi.com/2076-3425/14/12/1252
work_keys_str_mv AT xialiu lowranktensorfusionforenhanceddeeplearningbasedmultimodalbrainageestimation
AT guoweizheng lowranktensorfusionforenhanceddeeplearningbasedmultimodalbrainageestimation
AT imanbeheshti lowranktensorfusionforenhanceddeeplearningbasedmultimodalbrainageestimation
AT shanlingji lowranktensorfusionforenhanceddeeplearningbasedmultimodalbrainageestimation
AT zhinangou lowranktensorfusionforenhanceddeeplearningbasedmultimodalbrainageestimation
AT wenkuocui lowranktensorfusionforenhanceddeeplearningbasedmultimodalbrainageestimation