Cargando…

Multimodal Brain Network Jointly Construction and Fusion for Diagnosis of Epilepsy

Brain network analysis has been proved to be one of the most effective methods in brain disease diagnosis. In order to construct discriminative brain networks and improve the performance of disease diagnosis, many machine learning–based methods have been proposed. Recent studies show that combining...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhu, Qi, Yang, Jing, Xu, Bingliang, Hou, Zhenghua, Sun, Liang, Zhang, Daoqiang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8511490/
https://www.ncbi.nlm.nih.gov/pubmed/34658773
http://dx.doi.org/10.3389/fnins.2021.734711
_version_ 1784582774738386944
author Zhu, Qi
Yang, Jing
Xu, Bingliang
Hou, Zhenghua
Sun, Liang
Zhang, Daoqiang
author_facet Zhu, Qi
Yang, Jing
Xu, Bingliang
Hou, Zhenghua
Sun, Liang
Zhang, Daoqiang
author_sort Zhu, Qi
collection PubMed
description Brain network analysis has been proved to be one of the most effective methods in brain disease diagnosis. In order to construct discriminative brain networks and improve the performance of disease diagnosis, many machine learning–based methods have been proposed. Recent studies show that combining functional and structural brain networks is more effective than using only single modality data. However, in the most of existing multi-modal brain network analysis methods, it is a common strategy that constructs functional and structural network separately, which is difficult to embed complementary information of different modalities of brain network. To address this issue, we propose a unified brain network construction algorithm, which jointly learns both functional and structural data and effectively face the connectivity and node features for improving classification. First, we conduct space alignment and brain network construction under a unified framework, and then build the correlation model among all brain regions with functional data by low-rank representation so that the global brain region correlation can be captured. Simultaneously, the local manifold with structural data is embedded into this model to preserve the local structural information. Second, the PageRank algorithm is adaptively used to evaluate the significance of different brain regions, in which the interaction of multiple brain regions is considered. Finally, a multi-kernel strategy is utilized to solve the data heterogeneity problem and merge the connectivity as well as node information for classification. We apply the proposed method to the diagnosis of epilepsy, and the experimental results show that our method can achieve a promising performance.
format Online
Article
Text
id pubmed-8511490
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-85114902021-10-14 Multimodal Brain Network Jointly Construction and Fusion for Diagnosis of Epilepsy Zhu, Qi Yang, Jing Xu, Bingliang Hou, Zhenghua Sun, Liang Zhang, Daoqiang Front Neurosci Neuroscience Brain network analysis has been proved to be one of the most effective methods in brain disease diagnosis. In order to construct discriminative brain networks and improve the performance of disease diagnosis, many machine learning–based methods have been proposed. Recent studies show that combining functional and structural brain networks is more effective than using only single modality data. However, in the most of existing multi-modal brain network analysis methods, it is a common strategy that constructs functional and structural network separately, which is difficult to embed complementary information of different modalities of brain network. To address this issue, we propose a unified brain network construction algorithm, which jointly learns both functional and structural data and effectively face the connectivity and node features for improving classification. First, we conduct space alignment and brain network construction under a unified framework, and then build the correlation model among all brain regions with functional data by low-rank representation so that the global brain region correlation can be captured. Simultaneously, the local manifold with structural data is embedded into this model to preserve the local structural information. Second, the PageRank algorithm is adaptively used to evaluate the significance of different brain regions, in which the interaction of multiple brain regions is considered. Finally, a multi-kernel strategy is utilized to solve the data heterogeneity problem and merge the connectivity as well as node information for classification. We apply the proposed method to the diagnosis of epilepsy, and the experimental results show that our method can achieve a promising performance. Frontiers Media S.A. 2021-09-29 /pmc/articles/PMC8511490/ /pubmed/34658773 http://dx.doi.org/10.3389/fnins.2021.734711 Text en Copyright © 2021 Zhu, Yang, Xu, Hou, Sun and Zhang. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Zhu, Qi
Yang, Jing
Xu, Bingliang
Hou, Zhenghua
Sun, Liang
Zhang, Daoqiang
Multimodal Brain Network Jointly Construction and Fusion for Diagnosis of Epilepsy
title Multimodal Brain Network Jointly Construction and Fusion for Diagnosis of Epilepsy
title_full Multimodal Brain Network Jointly Construction and Fusion for Diagnosis of Epilepsy
title_fullStr Multimodal Brain Network Jointly Construction and Fusion for Diagnosis of Epilepsy
title_full_unstemmed Multimodal Brain Network Jointly Construction and Fusion for Diagnosis of Epilepsy
title_short Multimodal Brain Network Jointly Construction and Fusion for Diagnosis of Epilepsy
title_sort multimodal brain network jointly construction and fusion for diagnosis of epilepsy
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8511490/
https://www.ncbi.nlm.nih.gov/pubmed/34658773
http://dx.doi.org/10.3389/fnins.2021.734711
work_keys_str_mv AT zhuqi multimodalbrainnetworkjointlyconstructionandfusionfordiagnosisofepilepsy
AT yangjing multimodalbrainnetworkjointlyconstructionandfusionfordiagnosisofepilepsy
AT xubingliang multimodalbrainnetworkjointlyconstructionandfusionfordiagnosisofepilepsy
AT houzhenghua multimodalbrainnetworkjointlyconstructionandfusionfordiagnosisofepilepsy
AT sunliang multimodalbrainnetworkjointlyconstructionandfusionfordiagnosisofepilepsy
AT zhangdaoqiang multimodalbrainnetworkjointlyconstructionandfusionfordiagnosisofepilepsy