[1]南姣芬,孟攀婷,童志航,等.基于大脑磁共振成像的多模态多层次信息融合方法[J].郑州大学学报(工学版),2021,42(04):26-32.[doi:10.13705/j.issn.1671-6833.2021.04.006]
　Nan Yanfen,Meng Panting,Tong Zhihang,et al.A Multi-level Information Fusion Method Based on Multimodal Magnetic Resonance Imaging of Human Brain[J].Journal of Zhengzhou University (Engineering Science),2021,42(04):26-32.[doi:10.13705/j.issn.1671-6833.2021.04.006]
点击复制

基于大脑磁共振成像的多模态多层次信息融合方法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
42卷
期数:
2021年04期
页码:
26-32
栏目:
出版日期:
2021-07-30

文章信息/Info

Title:
A Multi-level Information Fusion Method Based on Multimodal Magnetic Resonance Imaging of Human Brain
作者:
南姣芬; 孟攀婷; 童志航; 张金灿
郑州轻工业大学计算机与通信工程学院;郑州大学管理工程学院;
Author(s):
Nan Yanfen; Meng Panting; Tong Zhihang; Zhang Jincan;
School of Computer and Communication Engineering, Zhengzhou Light Industry University; School of Management Engineering, Zhengzhou University;
关键词:
Keywords:
multi-level feature; information fusion; multimodal; magnetic resonance imaging
DOI:
10.13705/j.issn.1671-6833.2021.04.006
文献标志码:
A
摘要:
人类大脑的研究对揭示很多疾病的病理学机制存在重要价值，而单模态成像的研究在揭示大脑信息方面具有很大的片面性，因此越来越多的研究人员利用多影像数据间的交叉信息探索大脑奥秘。本文通过多层次特征计算对MCCA + jICA融合技术进行改进，提出一种基于无监督的多层次多模态人脑磁共振图像融合方法。模拟数据结果显示，与现在较为流行MCCA + jICA以及MCCAR + jICA相比，本文方法不仅在检测大脑多模态磁共振图像之间的共变成分上表现良好，还具有更高的稳定性。该方法的提出对更全面地探索大脑奥秘及相关疾病复杂机制具有重要的意义。
Abstract:
An unsupervised multi-level and multimodal fusion method was proposed for human brain magnetic resonance imaging data by multi-level feature calculation based on the improvement of MCCA+ jICA (multimodal canonical correlation analysis+joint independent component analysis).The method preprocessed the raw multimodal data,extracted the low-level features,calculated the high-level features,integrated the multi modal images with multi-level features,and performed fusion analysis with the spatial independent component technique.It was compared with MCCA+ jICA and MCCA+ jICA with reference.Results showed that for different signal-to-noise ratios,the proposed method (95%～99%)had the highest accuracy for detecting the target information,followed by MCCA+ jICA with reference (77%～82%)and MCCA+ jICA (74%～82%),the biggest correlation between the estimation target and the real target (0.890 6),followed by MCCA+ jICA (0.855 7)and MCCA+ jICA with reference (0.699 9),and the lowest standard deviation of the correlation between the mixed matrix from different modalities (0.105 5),followed by MCCA+ jICA with reference (0.138 4)and MCCA+ jICA (0.289 6).Therefore,the method proposed in this paper had a higher accuracy,stronger robustness and better stability in exploring the brain functional-structural co-variation and coupled relationship.This was of great significance to study the brain mechanism and pathophysiology of the brain-related diseases.

参考文献/References:

[1] MENG X,JIANG R T,LIN D D,et al.Predicting individualized clinical measures by a generalized prediction framework and multimodal fusion of MRI data [J].Neuroimage,2017,145:218-229.

[2] SUI J,HUSTER R,YU Q B,et al.Function-structure associations of the brain:evidence from multimodal connectivity and covariance studies [J].Neuroimage,2014,102(1):11-23.
[3] CALHOUN V D,LEMIEUX L.Neuroimage:special issue on multimodal data fusion [J].Neuroimage,2014,102(1):1-2.
[4] LIU M X,ZHANG J,YAP P T,et al.View-aligned hypergraph learning for Alzheimer′s disease diagnosis with incomplete multi-modality data [J].Medical image analysis,2017,36:123-134.
[5] QI S L,CALHOUN V D,Van ERP T G M,et al.Multimodal fusion with reference:searching for joint neuromarkers of working memory deficits in schizophrenia [J].IEEE transactions on medical imaging,2018,37(1):93-105.
[6] SUI J,QI S,Van ERP T G M,et al.Multimodal neuromarkers in schizophrenia via cognition-guided MRI fusion[EB/OL].(2018-08-02)[2020-12-08].https://doi.org/10.1038/s41467-018-05432-w.
[7] DING C,PENG H.Minimum redundancy feature selection from microarray gene expression data [J].Bioinformatics computational biology,2005,3(2):185-206.
[8] KRAMER M A.Nonlinear principal component analysis using autoassociative neural networks [J].Aiche journal,1991,37(2):233-243.
[9] ABDI H,WILLIAMS L J.Principal component analysis [J].Wiley interdisciplinary reviews computational statistics,2010,2(4):433-459.
[10] HE Y,CHEN Z,EVANS A.Structural insights into aberrant topological patterns of large-scale cortical networks in Alzheimer′s disease [J].The journal of neuroscience,2008,28(18):4756-4766.
[11] STAM C J,De HAAN W,DAFFERTSHOFER A,et al.Graph theoretical analysis of magnetoencephalographic functional connectivity in Alzheimer′s disease [J].Brain,2009,132(1):213-224.
[12] 尚志刚,沈晓阳,李蒙蒙,等.基于格兰杰因果的效应性连接分析方法综述 [J].郑州大学学报(工学版),2020,41(3):1-7,13.
[13] KETTENRING J R.Canonical analysis of several sets of variables [J].Biometrika,1971,58(3):433-451.
[14] CALHOUN V D,ADALI T,GIULIANI N R,et al.Method for multimodal analysis of independent source differences in schizophrenia:combining gray matter structural and auditory oddball functional data [J].Human brain mapping,2006,27(1):47-62.
[15] TZOURIO-MAZOYER N,LANDEAU B,PAPATHANASSIOU D,et al.Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain [J].Neuroimage,2002,15(1):273-289.
[16] MORI S,OISHI K,JIANG H Y,et al.Stereotaxic white matter atlas based on diffusion tensor imaging in an ICBM template [J].Neuroimage,2008,40(2):570-582.

相似文献/References:

[1]韩捷,吴彦召,陈磊,等.全矢-ARMA模型在机械振动强度预测研究的应用[J].郑州大学学报(工学版),2016,37(06):43.[doi:10.13705/j.issn.1671-6833.2016.06.024]
　Han Jie,Wu Yanzhao,Chen Lei,et al.Research on mechanical vibration intensity prediction based on FVS-ARMA model[J].Journal of Zhengzhou University (Engineering Science),2016,37(04):43.[doi:10.13705/j.issn.1671-6833.2016.06.024]
[2]刘广瑞,周文博,田欣,等.多传感器信息融合在焊接质量控制中的应用[J].郑州大学学报(工学版),2017,38(05):28.[doi:10.13705/j.issn.1671-6833.2017.02.025]
　Liu Guangrui,Zhou Wenbo,Tian Xin,et al.Application of Information Fusion in Welding based on Arc and Ultrasonic sensor[J].Journal of Zhengzhou University (Engineering Science),2017,38(04):28.[doi:10.13705/j.issn.1671-6833.2017.02.025]
[3]张大龙,余 刚,李致远,等.考虑杆臂误差的组合导航分离协方差交叉算法[J].郑州大学学报(工学版),2022,43(03):8.[doi:10.13705/j.issn.1671-6833.2022.03.013]
　ZHANG Dalong,YU Gang,LI Zhiyuan,et al.Split Covariance Intersection Algorithm for Integrated Navigation System Considering Lever Arm Error[J].Journal of Zhengzhou University (Engineering Science),2022,43(04):8.[doi:10.13705/j.issn.1671-6833.2022.03.013]

更新日期/Last Update: 2021-08-26