Hierarchical Structured Sparse Learning for Schizophrenia Identification

Mingliang Wang, Xiaoke Hao, Jiashuang Huang, Kangcheng Wang, Li Shen, Xijia Xu, Daoqiang Zhang, Mingxia Liu

Research output: Contribution to journalArticle

Abstract

Fractional amplitude of low-frequency fluctuation (fALFF) has been widely used for resting-state functional magnetic resonance imaging (rs-fMRI) based schizophrenia (SZ) diagnosis. However, previous studies usually measure the fALFF within low-frequency fluctuation (from 0.01 to 0.08Hz), which cannot fully cover the complex neural activity pattern in the resting-state brain. In addition, existing studies usually ignore the fact that each specific frequency band can delineate the unique spontaneous fluctuations of neural activities in the brain. Accordingly, in this paper, we propose a novel hierarchical structured sparse learning method to sufficiently utilize the specificity and complementary structure information across four different frequency bands (from 0.01Hz to 0.25Hz) for SZ diagnosis. The proposed method can help preserve the partial group structures among multiple frequency bands and the specific characters in each frequency band. We further develop an efficient optimization algorithm to solve the proposed objective function. We validate the efficacy of our proposed method on a real SZ dataset. Also, to demonstrate the generality of the method, we apply our proposed method on a subset of Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Experimental results on both datasets demonstrate that our proposed method achieves promising performance in brain disease classification, compared with several state-of-the-art methods.

Original languageEnglish (US)
JournalNeuroinformatics
DOIs
StatePublished - Jan 1 2019
Externally publishedYes

Fingerprint

Frequency bands
Schizophrenia
Learning
Brain
Neuroimaging
Group Structure
Brain Diseases
Alzheimer Disease
Magnetic Resonance Imaging
Databases

Keywords

  • Fractional amplitude of low-frequency fluctuations (fALFF)
  • Hierarchical feature selection
  • Resting-state functional magnetic resonance imaging (rs-fMRI)
  • Schizophrenia

ASJC Scopus subject areas

  • Software
  • Neuroscience(all)
  • Information Systems

Cite this

Hierarchical Structured Sparse Learning for Schizophrenia Identification. / Wang, Mingliang; Hao, Xiaoke; Huang, Jiashuang; Wang, Kangcheng; Shen, Li; Xu, Xijia; Zhang, Daoqiang; Liu, Mingxia.

In: Neuroinformatics, 01.01.2019.

Research output: Contribution to journalArticle

Wang, Mingliang ; Hao, Xiaoke ; Huang, Jiashuang ; Wang, Kangcheng ; Shen, Li ; Xu, Xijia ; Zhang, Daoqiang ; Liu, Mingxia. / Hierarchical Structured Sparse Learning for Schizophrenia Identification. In: Neuroinformatics. 2019.
@article{a659f799f0f94eca8bf25c4e7f9e155d,
title = "Hierarchical Structured Sparse Learning for Schizophrenia Identification",
abstract = "Fractional amplitude of low-frequency fluctuation (fALFF) has been widely used for resting-state functional magnetic resonance imaging (rs-fMRI) based schizophrenia (SZ) diagnosis. However, previous studies usually measure the fALFF within low-frequency fluctuation (from 0.01 to 0.08Hz), which cannot fully cover the complex neural activity pattern in the resting-state brain. In addition, existing studies usually ignore the fact that each specific frequency band can delineate the unique spontaneous fluctuations of neural activities in the brain. Accordingly, in this paper, we propose a novel hierarchical structured sparse learning method to sufficiently utilize the specificity and complementary structure information across four different frequency bands (from 0.01Hz to 0.25Hz) for SZ diagnosis. The proposed method can help preserve the partial group structures among multiple frequency bands and the specific characters in each frequency band. We further develop an efficient optimization algorithm to solve the proposed objective function. We validate the efficacy of our proposed method on a real SZ dataset. Also, to demonstrate the generality of the method, we apply our proposed method on a subset of Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Experimental results on both datasets demonstrate that our proposed method achieves promising performance in brain disease classification, compared with several state-of-the-art methods.",
keywords = "Fractional amplitude of low-frequency fluctuations (fALFF), Hierarchical feature selection, Resting-state functional magnetic resonance imaging (rs-fMRI), Schizophrenia",
author = "Mingliang Wang and Xiaoke Hao and Jiashuang Huang and Kangcheng Wang and Li Shen and Xijia Xu and Daoqiang Zhang and Mingxia Liu",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/s12021-019-09423-0",
language = "English (US)",
journal = "Neuroinformatics",
issn = "1539-2791",
publisher = "Humana Press",

}

TY - JOUR

T1 - Hierarchical Structured Sparse Learning for Schizophrenia Identification

AU - Wang, Mingliang

AU - Hao, Xiaoke

AU - Huang, Jiashuang

AU - Wang, Kangcheng

AU - Shen, Li

AU - Xu, Xijia

AU - Zhang, Daoqiang

AU - Liu, Mingxia

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Fractional amplitude of low-frequency fluctuation (fALFF) has been widely used for resting-state functional magnetic resonance imaging (rs-fMRI) based schizophrenia (SZ) diagnosis. However, previous studies usually measure the fALFF within low-frequency fluctuation (from 0.01 to 0.08Hz), which cannot fully cover the complex neural activity pattern in the resting-state brain. In addition, existing studies usually ignore the fact that each specific frequency band can delineate the unique spontaneous fluctuations of neural activities in the brain. Accordingly, in this paper, we propose a novel hierarchical structured sparse learning method to sufficiently utilize the specificity and complementary structure information across four different frequency bands (from 0.01Hz to 0.25Hz) for SZ diagnosis. The proposed method can help preserve the partial group structures among multiple frequency bands and the specific characters in each frequency band. We further develop an efficient optimization algorithm to solve the proposed objective function. We validate the efficacy of our proposed method on a real SZ dataset. Also, to demonstrate the generality of the method, we apply our proposed method on a subset of Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Experimental results on both datasets demonstrate that our proposed method achieves promising performance in brain disease classification, compared with several state-of-the-art methods.

AB - Fractional amplitude of low-frequency fluctuation (fALFF) has been widely used for resting-state functional magnetic resonance imaging (rs-fMRI) based schizophrenia (SZ) diagnosis. However, previous studies usually measure the fALFF within low-frequency fluctuation (from 0.01 to 0.08Hz), which cannot fully cover the complex neural activity pattern in the resting-state brain. In addition, existing studies usually ignore the fact that each specific frequency band can delineate the unique spontaneous fluctuations of neural activities in the brain. Accordingly, in this paper, we propose a novel hierarchical structured sparse learning method to sufficiently utilize the specificity and complementary structure information across four different frequency bands (from 0.01Hz to 0.25Hz) for SZ diagnosis. The proposed method can help preserve the partial group structures among multiple frequency bands and the specific characters in each frequency band. We further develop an efficient optimization algorithm to solve the proposed objective function. We validate the efficacy of our proposed method on a real SZ dataset. Also, to demonstrate the generality of the method, we apply our proposed method on a subset of Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Experimental results on both datasets demonstrate that our proposed method achieves promising performance in brain disease classification, compared with several state-of-the-art methods.

KW - Fractional amplitude of low-frequency fluctuations (fALFF)

KW - Hierarchical feature selection

KW - Resting-state functional magnetic resonance imaging (rs-fMRI)

KW - Schizophrenia

UR - http://www.scopus.com/inward/record.url?scp=85064806754&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064806754&partnerID=8YFLogxK

U2 - 10.1007/s12021-019-09423-0

DO - 10.1007/s12021-019-09423-0

M3 - Article

AN - SCOPUS:85064806754

JO - Neuroinformatics

JF - Neuroinformatics

SN - 1539-2791

ER -