Decomposition-Based Correlation Learning for Multi-Modal MRI-Based Classification of Neuropsychiatric Disorders

被引:4
|
作者
Liu, Liangliang [1 ]
Chang, Jing [1 ]
Wang, Ying [1 ]
Liang, Gongbo [2 ]
Wang, Yu-Ping [3 ]
Zhang, Hui [1 ]
机构
[1] Henan Agr Univ, Coll Informat & Management Sci, Zhengzhou, Peoples R China
[2] Eastern Kentucky Univ, Dept Comp Sci, Richmond, KY 40475 USA
[3] Tulane Univ, Biomed Engn Dept, New Orleans, LA 70118 USA
基金
中国国家自然科学基金;
关键词
multi-modal; decomposition-based; matrix decomposition; canonical correlation analysis; neuropsychiatric disorders; INDEPENDENT COMPONENT ANALYSIS; FUNCTIONAL CONNECTIVITY; ALZHEIMERS-DISEASE; BIPOLAR DISORDER; IMAGING DATA; SCHIZOPHRENIA; DIFFUSION; FMRI; FUSION; MATTER;
D O I
10.3389/fnins.2022.832276
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
Multi-modal magnetic resonance imaging (MRI) is widely used for diagnosing brain disease in clinical practice. However, the high-dimensionality of MRI images is challenging when training a convolution neural network. In addition, utilizing multiple MRI modalities jointly is even more challenging. We developed a method using decomposition-based correlation learning (DCL). To overcome the above challenges, we used a strategy to capture the complex relationship between structural MRI and functional MRI data. Under the guidance of matrix decomposition, DCL takes into account the spike magnitude of leading eigenvalues, the number of samples, and the dimensionality of the matrix. A canonical correlation analysis (CCA) was used to analyze the correlation and construct matrices. We evaluated DCL in the classification of multiple neuropsychiatric disorders listed in the Consortium for Neuropsychiatric Phenomics (CNP) dataset. In experiments, our method had a higher accuracy than several existing methods. Moreover, we found interesting feature connections from brain matrices based on DCL that can differentiate disease and normal cases and different subtypes of the disease. Furthermore, we extended experiments on a large sample size dataset and a small sample size dataset, compared with several other well-established methods that were designed for the multi neuropsychiatric disorder classification; our proposed method achieved state-of-the-art performance on all three datasets.
引用
收藏
页数:15
相关论文
共 50 条
  • [21] Empirical Mode Decomposition Based Multi-Modal Activity Recognition
    Hu, Lingyue
    Zhao, Kailong
    Zhou, Xueling
    Ling, Bingo Wing-Kuen
    Liao, Guozhao
    SENSORS, 2020, 20 (21) : 1 - 15
  • [22] An enhanced multi-modal brain graph network for classifying neuropsychiatric disorders
    Liu, Liangliang
    Wang, Yu-Ping
    Wang, Yi
    Zhang, Pei
    Xiong, Shufeng
    MEDICAL IMAGE ANALYSIS, 2022, 81
  • [23] Decomposition-based tensor learning regression for improved classification of multimedia
    Zhang, Jianguang
    Jiang, Jianmin
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2016, 41 : 260 - 271
  • [24] Decomposition-Based Transfer Distance Metric Learning for Image Classification
    Luo, Yong
    Liu, Tongliang
    Tao, Dacheng
    Xu, Chao
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2014, 23 (09) : 3789 - 3801
  • [25] Common Representation Learning Using Step-based Correlation Multi-Modal CNN
    Bhatt, Gaurav
    Jha, Piyush
    Raman, Balasubramanian
    PROCEEDINGS 2017 4TH IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION (ACPR), 2017, : 864 - 869
  • [26] Classification of Parkinson's disease based on multi-modal features and stacking ensemble learning
    Yang, Yifeng
    Wei, Long
    Hu, Ying
    Wu, Yan
    Hu, Liangyun
    Nie, Shengdong
    JOURNAL OF NEUROSCIENCE METHODS, 2021, 350
  • [27] Multi-modal classification of neurodegenerative disease by progressive graph-based transductive learning
    Wang, Zhengxia
    Zhu, Xiaofeng
    Adeli, Ehsan
    Zhu, Yingying
    Nie, Feiping
    Munsell, Brent
    Wu, Guorong
    MEDICAL IMAGE ANALYSIS, 2017, 39 : 218 - 230
  • [28] Multi-modal Broad Learning System for Medical Image and Text-based Classification
    Zhou, Yanhong
    Du, Jie
    Guan, Kai
    Wang, Tianfu
    2021 43RD ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY (EMBC), 2021, : 3439 - 3442
  • [29] Nodule-CLIP: Lung nodule classification based on multi-modal contrastive learning
    Sun L.
    Zhang M.
    Lu Y.
    Zhu W.
    Yi Y.
    Yan F.
    Computers in Biology and Medicine, 175
  • [30] Memory based fusion for multi-modal deep learning
    Priyasad, Darshana
    Fernando, Tharindu
    Denman, Simon
    Sridharan, Sridha
    Fookes, Clinton
    INFORMATION FUSION, 2021, 67 : 136 - 146