Fine-granularity functional interaction signatures for characterization of brain conditions

Xintao Hu, Dajiang Zhu, Peili Lv, Kaiming Li, Junwei Han, Lihong Wang, Dinggang Shen, Lei Guo, Tianming Liu

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

In the human brain, functional activity occurs at multiple spatial scales. Current studies on functional brain networks and their alterations in brain diseases via resting-state functional magnetic resonance imaging (rs-fMRI) are generally either at local scale (regionally confined analysis and inter-regional functional connectivity analysis) or at global scale (graph theoretic analysis). In contrast, inferring functional interaction at fine-granularity sub-network scale has not been adequately explored yet. Here our hypothesis is that functional interaction measured at fine-granularity sub-network scale can provide new insight into the neural mechanisms of neurological and psychological conditions, thus offering complementary information for healthy and diseased population classification. In this paper, we derived fine-granularity functional interaction (FGFI) signatures in subjects with Mild Cognitive Impairment (MCI) and Schizophrenia by diffusion tensor imaging (DTI) and rs-fMRI, and used patient-control classification experiments to evaluate the distinctiveness of the derived FGFI features. Our experimental results have shown that the FGFI features alone can achieve comparable classification performance compared with the commonly used inter-regional connectivity features. However, the classification performance can be substantially improved when FGFI features and inter-regional connectivity features are integrated, suggesting the complementary information achieved from the FGFI signatures.

Original languageEnglish
Pages (from-to)301-317
Number of pages17
JournalNeuroinformatics
Volume11
Issue number3
DOIs
Publication statusPublished - 2013 Jul 1
Externally publishedYes

Fingerprint

Brain
Magnetic Resonance Imaging
Diffusion tensor imaging
Functional analysis
Diffusion Tensor Imaging
Brain Diseases
Schizophrenia
Psychology
Population
Experiments

Keywords

  • DTI
  • Fine granularity
  • Functional interaction
  • MCI
  • rs-fMRI
  • SZ

ASJC Scopus subject areas

  • Neuroscience(all)
  • Information Systems
  • Software

Cite this

Fine-granularity functional interaction signatures for characterization of brain conditions. / Hu, Xintao; Zhu, Dajiang; Lv, Peili; Li, Kaiming; Han, Junwei; Wang, Lihong; Shen, Dinggang; Guo, Lei; Liu, Tianming.

In: Neuroinformatics, Vol. 11, No. 3, 01.07.2013, p. 301-317.

Research output: Contribution to journalArticle

Hu, Xintao ; Zhu, Dajiang ; Lv, Peili ; Li, Kaiming ; Han, Junwei ; Wang, Lihong ; Shen, Dinggang ; Guo, Lei ; Liu, Tianming. / Fine-granularity functional interaction signatures for characterization of brain conditions. In: Neuroinformatics. 2013 ; Vol. 11, No. 3. pp. 301-317.
@article{8a2397a0e11b4dd6b891e87a4868fa06,
title = "Fine-granularity functional interaction signatures for characterization of brain conditions",
abstract = "In the human brain, functional activity occurs at multiple spatial scales. Current studies on functional brain networks and their alterations in brain diseases via resting-state functional magnetic resonance imaging (rs-fMRI) are generally either at local scale (regionally confined analysis and inter-regional functional connectivity analysis) or at global scale (graph theoretic analysis). In contrast, inferring functional interaction at fine-granularity sub-network scale has not been adequately explored yet. Here our hypothesis is that functional interaction measured at fine-granularity sub-network scale can provide new insight into the neural mechanisms of neurological and psychological conditions, thus offering complementary information for healthy and diseased population classification. In this paper, we derived fine-granularity functional interaction (FGFI) signatures in subjects with Mild Cognitive Impairment (MCI) and Schizophrenia by diffusion tensor imaging (DTI) and rs-fMRI, and used patient-control classification experiments to evaluate the distinctiveness of the derived FGFI features. Our experimental results have shown that the FGFI features alone can achieve comparable classification performance compared with the commonly used inter-regional connectivity features. However, the classification performance can be substantially improved when FGFI features and inter-regional connectivity features are integrated, suggesting the complementary information achieved from the FGFI signatures.",
keywords = "DTI, Fine granularity, Functional interaction, MCI, rs-fMRI, SZ",
author = "Xintao Hu and Dajiang Zhu and Peili Lv and Kaiming Li and Junwei Han and Lihong Wang and Dinggang Shen and Lei Guo and Tianming Liu",
year = "2013",
month = "7",
day = "1",
doi = "10.1007/s12021-013-9177-2",
language = "English",
volume = "11",
pages = "301--317",
journal = "Neuroinformatics",
issn = "1539-2791",
publisher = "Humana Press",
number = "3",

}

TY - JOUR

T1 - Fine-granularity functional interaction signatures for characterization of brain conditions

AU - Hu, Xintao

AU - Zhu, Dajiang

AU - Lv, Peili

AU - Li, Kaiming

AU - Han, Junwei

AU - Wang, Lihong

AU - Shen, Dinggang

AU - Guo, Lei

AU - Liu, Tianming

PY - 2013/7/1

Y1 - 2013/7/1

N2 - In the human brain, functional activity occurs at multiple spatial scales. Current studies on functional brain networks and their alterations in brain diseases via resting-state functional magnetic resonance imaging (rs-fMRI) are generally either at local scale (regionally confined analysis and inter-regional functional connectivity analysis) or at global scale (graph theoretic analysis). In contrast, inferring functional interaction at fine-granularity sub-network scale has not been adequately explored yet. Here our hypothesis is that functional interaction measured at fine-granularity sub-network scale can provide new insight into the neural mechanisms of neurological and psychological conditions, thus offering complementary information for healthy and diseased population classification. In this paper, we derived fine-granularity functional interaction (FGFI) signatures in subjects with Mild Cognitive Impairment (MCI) and Schizophrenia by diffusion tensor imaging (DTI) and rs-fMRI, and used patient-control classification experiments to evaluate the distinctiveness of the derived FGFI features. Our experimental results have shown that the FGFI features alone can achieve comparable classification performance compared with the commonly used inter-regional connectivity features. However, the classification performance can be substantially improved when FGFI features and inter-regional connectivity features are integrated, suggesting the complementary information achieved from the FGFI signatures.

AB - In the human brain, functional activity occurs at multiple spatial scales. Current studies on functional brain networks and their alterations in brain diseases via resting-state functional magnetic resonance imaging (rs-fMRI) are generally either at local scale (regionally confined analysis and inter-regional functional connectivity analysis) or at global scale (graph theoretic analysis). In contrast, inferring functional interaction at fine-granularity sub-network scale has not been adequately explored yet. Here our hypothesis is that functional interaction measured at fine-granularity sub-network scale can provide new insight into the neural mechanisms of neurological and psychological conditions, thus offering complementary information for healthy and diseased population classification. In this paper, we derived fine-granularity functional interaction (FGFI) signatures in subjects with Mild Cognitive Impairment (MCI) and Schizophrenia by diffusion tensor imaging (DTI) and rs-fMRI, and used patient-control classification experiments to evaluate the distinctiveness of the derived FGFI features. Our experimental results have shown that the FGFI features alone can achieve comparable classification performance compared with the commonly used inter-regional connectivity features. However, the classification performance can be substantially improved when FGFI features and inter-regional connectivity features are integrated, suggesting the complementary information achieved from the FGFI signatures.

KW - DTI

KW - Fine granularity

KW - Functional interaction

KW - MCI

KW - rs-fMRI

KW - SZ

UR - http://www.scopus.com/inward/record.url?scp=84881094915&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881094915&partnerID=8YFLogxK

U2 - 10.1007/s12021-013-9177-2

DO - 10.1007/s12021-013-9177-2

M3 - Article

VL - 11

SP - 301

EP - 317

JO - Neuroinformatics

JF - Neuroinformatics

SN - 1539-2791

IS - 3

ER -