Local-structure-preservation and redundancy-removal-based feature selection method and its application to the identification of biomarkers for schizophrenia

被引:0
|
作者
Xing, Ying [1 ]
Pearlson, Godfrey D. [2 ,3 ]
Kochunov, Peter [4 ,5 ]
Calhoun, Vince D. [6 ]
Du, Yuhui [1 ]
机构
[1] Shanxi Univ, Sch Comp & Informat Technol, Taiyuan, Peoples R China
[2] Yale Univ, Dept Psychiat, New Haven, CT USA
[3] Yale Univ, Dept Neurobiol, New Haven, CT USA
[4] Univ Maryland, Sch Med, Maryland Psychiat Res Ctr, Baltimore, MD USA
[5] Univ Maryland, Sch Med, Dept Psychiat, Baltimore, MD USA
[6] Emory Univ, Georgia State Univ, Georgia Inst Technol, Triinst Ctr Translat Res Neuroimaging & Data Sci, Atlanta, GA USA
基金
美国国家卫生研究院; 中国国家自然科学基金;
关键词
Regularization; Classification; Similarity; Redundancy; Mental disorder; Neuroimaging; CLASSIFIERS; STATE;
D O I
10.1016/j.neuroimage.2024.120839
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
Accurate diagnosis of mental disorders is expected to be achieved through the identification of reliable neuroimaging biomarkers with the help of cutting-edge feature selection techniques. However, existing feature selection methods often fall short in capturing the local structural characteristics among samples and effectively eliminating redundant features, resulting in inadequate performance in disorder prediction. To address this gap, we propose a novel supervised method named local-structure-preservation and redundancy-removal-based feature selection (LRFS), and then apply it to the identification of meaningful biomarkers for schizophrenia (SZ). LRFS method leverages graph-based regularization to preserve original sample similarity relationships during data transformation, thus retaining crucial local structure information. Additionally, it introduces redundancy-removal regularization based on interrelationships among features to exclude similar and redundant features from high-dimensional data. Moreover, LRFS method incorporates l2,1 sparse regularization that enables selecting a sparse and noise-robust feature subset. Experimental evaluations on eight public datasets with diverse properties demonstrate the superior performance of our method over nine popular feature selection methods in identifying discriminative features, with average classification accuracy gains ranging from 1.30 % to 9.11 %. Furthermore, the LRFS method demonstrates superior discriminability in four functional magnetic resonance imaging (fMRI) datasets from 708 healthy controls (HCs) and 537 SZ patients, with an average increase in classification accuracy ranging from 1.89 % to 9.24 % compared to other nine methods. Notably, our method reveals reproducible and significant changes in SZ patients relative to HCs across the four datasets, predominantly in the thalamus-related functional network connectivity, which exhibit a significant correlation with clinical symptoms. Convergence analysis, parameter sensitivity analysis, and ablation studies further demonstrate the effectiveness and robustness of our method. In short, our proposed feature selection method effectively identifies discriminative and reliable features that hold the potential to be biomarkers, paving the way for the elucidation of brain abnormalities and the advancement of precise diagnosis of mental disorders.
引用
收藏
页数:14
相关论文
共 33 条
  • [21] Optimized back analysis method for stress determination based on identification of local stress measurements and its application
    Pei, Qitao
    Ding, Xiuli
    Liu, Yuankun
    Lu, Bo
    Huang, Shuling
    Fu, Jing
    BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT, 2019, 78 (01) : 375 - 396
  • [22] Optimized back analysis method for stress determination based on identification of local stress measurements and its application
    Qitao Pei
    Xiuli Ding
    Yuankun Liu
    Bo Lu
    Shuling Huang
    Jing Fu
    Bulletin of Engineering Geology and the Environment, 2019, 78 : 375 - 396
  • [23] New Method for Feature Selection Based on Complex Causality Model and Its Application in the Industrial Unit of Wax Oil Hydrogenation
    Tian, Wang
    Qin, Kang
    Wu, Hao
    Li, Mingfeng
    Xie, Yu
    Zhang, Fanbin
    Liang, Jialin
    Shiyou Xuebao, Shiyou Jiagong/Acta Petrolei Sinica (Petroleum Processing Section), 2024, 40 (03): : 580 - 590
  • [24] New method for texture classification based on local surface structure and its application to ultrasonic liver images
    Horng, Ming-Huwi
    Sun, Yung-Nien
    Lin, Xi-Zhang
    Wang, Jen-Ya
    Biomedical Engineering - Applications, Basis and Communications, 1995, 7 (05): : 491 - 498
  • [25] VPMCD based novelty detection method on and its application to fault identification for local characteristic-scale decomposition
    Luo, Songrong
    Cheng, Junsheng
    CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2017, 20 (04): : 2955 - 2965
  • [26] VPMCD based novelty detection method on and its application to fault identification for local characteristic-scale decomposition
    Songrong Luo
    Junsheng Cheng
    Cluster Computing, 2017, 20 : 2955 - 2965
  • [27] Data anomaly identification method based on local outlier factor and application in monitoring data of heritage building structure
    Yang N.
    Fu Y.
    Li T.
    Jianzhu Jiegou Xuebao/Journal of Building Structures, 2022, 43 (10): : 68 - 75
  • [28] LLE Score: A New Filter-Based Unsupervised Feature Selection Method Based on Nonlinear Manifold Embedding and Its Application to Image Recognition
    Yao, Chao
    Liu, Ya-Feng
    Jiang, Bo
    Han, Jungong
    Han, Junwei
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (11) : 5257 - 5269
  • [29] An improved local mean decomposition method based on improved composite interpolation envelope and its application in bearing fault feature extraction
    Li, Xiang
    Ma, Jun
    Wang, Xiaodong
    Wu, Jiande
    Li, Zhuorui
    ISA TRANSACTIONS, 2020, 97 : 365 - 383
  • [30] A Novel Method of Nonlinear Rapid Feature Selection for High Dimensional Data and Its Application in Peptide QSAR Modeling Based on Support Vector Machine
    Dai Zhi-Jun
    Zhou Wei
    Yuan Zhe-Ming
    ACTA PHYSICO-CHIMICA SINICA, 2011, 27 (07) : 1654 - 1660