Refined measure of functional connectomes for improved identifiability and prediction

Biao Cai, Gemeng Zhang, Wenxing Hu, Aiying Zhang, Pascal Zille, Yipu Zhang, Julia M. Stephen, Tony W. Wilson, Vince D. Calhoun, Yu Ping Wang

Research output: Contribution to journalArticle

Abstract

Brain functional connectome analysis is commonly based on population-wise inference. However, in this way precious information provided at the individual subject level may be overlooked. Recently, several studies have shown that individual differences contribute strongly to the functional connectivity patterns. In particular, functional connectomes have been proven to offer a fingerprint measure, which can reliably identify a given individual from a pool of participants. In this work, we propose to refine the standard measure of individual functional connectomes using dictionary learning. More specifically, we rely on the assumption that each functional connectivity is dominated by stable group and individual factors. By subtracting population-wise contributions from connectivity patterns facilitated by dictionary representation, intersubject variability should be increased within the group. We validate our approach using several types of analyses. For example, we observe that refined connectivity profiles significantly increase subject-specific identifiability across functional magnetic resonance imaging (fMRI) session combinations. Besides, refined connectomes can also improve the prediction power for cognitive behaviors. In accordance with results from the literature, we find that individual distinctiveness is closely linked with differences in neurocognitive activity within the brain. In summary, our results indicate that individual connectivity analysis benefits from the group-wise inferences and refined connectomes are indeed desirable for brain mapping.

Original languageEnglish (US)
Pages (from-to)4843-4858
Number of pages16
JournalHuman Brain Mapping
Volume40
Issue number16
DOIs
StatePublished - Nov 1 2019

Fingerprint

Connectome
Brain Mapping
Brain
Dermatoglyphics
Individuality
Population
Magnetic Resonance Imaging
Learning

Keywords

  • cognitive behavior prediction
  • functional connectivity
  • individual identification
  • refined connectomes
  • sparse dictionary learning model

ASJC Scopus subject areas

  • Anatomy
  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Neurology
  • Clinical Neurology

Cite this

Cai, B., Zhang, G., Hu, W., Zhang, A., Zille, P., Zhang, Y., ... Wang, Y. P. (2019). Refined measure of functional connectomes for improved identifiability and prediction. Human Brain Mapping, 40(16), 4843-4858. https://doi.org/10.1002/hbm.24741

Refined measure of functional connectomes for improved identifiability and prediction. / Cai, Biao; Zhang, Gemeng; Hu, Wenxing; Zhang, Aiying; Zille, Pascal; Zhang, Yipu; Stephen, Julia M.; Wilson, Tony W.; Calhoun, Vince D.; Wang, Yu Ping.

In: Human Brain Mapping, Vol. 40, No. 16, 01.11.2019, p. 4843-4858.

Research output: Contribution to journalArticle

Cai, B, Zhang, G, Hu, W, Zhang, A, Zille, P, Zhang, Y, Stephen, JM, Wilson, TW, Calhoun, VD & Wang, YP 2019, 'Refined measure of functional connectomes for improved identifiability and prediction', Human Brain Mapping, vol. 40, no. 16, pp. 4843-4858. https://doi.org/10.1002/hbm.24741
Cai, Biao ; Zhang, Gemeng ; Hu, Wenxing ; Zhang, Aiying ; Zille, Pascal ; Zhang, Yipu ; Stephen, Julia M. ; Wilson, Tony W. ; Calhoun, Vince D. ; Wang, Yu Ping. / Refined measure of functional connectomes for improved identifiability and prediction. In: Human Brain Mapping. 2019 ; Vol. 40, No. 16. pp. 4843-4858.
@article{7aaa0ea40813443a8f7ebce173d1eb2b,
title = "Refined measure of functional connectomes for improved identifiability and prediction",
abstract = "Brain functional connectome analysis is commonly based on population-wise inference. However, in this way precious information provided at the individual subject level may be overlooked. Recently, several studies have shown that individual differences contribute strongly to the functional connectivity patterns. In particular, functional connectomes have been proven to offer a fingerprint measure, which can reliably identify a given individual from a pool of participants. In this work, we propose to refine the standard measure of individual functional connectomes using dictionary learning. More specifically, we rely on the assumption that each functional connectivity is dominated by stable group and individual factors. By subtracting population-wise contributions from connectivity patterns facilitated by dictionary representation, intersubject variability should be increased within the group. We validate our approach using several types of analyses. For example, we observe that refined connectivity profiles significantly increase subject-specific identifiability across functional magnetic resonance imaging (fMRI) session combinations. Besides, refined connectomes can also improve the prediction power for cognitive behaviors. In accordance with results from the literature, we find that individual distinctiveness is closely linked with differences in neurocognitive activity within the brain. In summary, our results indicate that individual connectivity analysis benefits from the group-wise inferences and refined connectomes are indeed desirable for brain mapping.",
keywords = "cognitive behavior prediction, functional connectivity, individual identification, refined connectomes, sparse dictionary learning model",
author = "Biao Cai and Gemeng Zhang and Wenxing Hu and Aiying Zhang and Pascal Zille and Yipu Zhang and Stephen, {Julia M.} and Wilson, {Tony W.} and Calhoun, {Vince D.} and Wang, {Yu Ping}",
year = "2019",
month = "11",
day = "1",
doi = "10.1002/hbm.24741",
language = "English (US)",
volume = "40",
pages = "4843--4858",
journal = "Human Brain Mapping",
issn = "1065-9471",
publisher = "Wiley-Liss Inc.",
number = "16",

}

TY - JOUR

T1 - Refined measure of functional connectomes for improved identifiability and prediction

AU - Cai, Biao

AU - Zhang, Gemeng

AU - Hu, Wenxing

AU - Zhang, Aiying

AU - Zille, Pascal

AU - Zhang, Yipu

AU - Stephen, Julia M.

AU - Wilson, Tony W.

AU - Calhoun, Vince D.

AU - Wang, Yu Ping

PY - 2019/11/1

Y1 - 2019/11/1

N2 - Brain functional connectome analysis is commonly based on population-wise inference. However, in this way precious information provided at the individual subject level may be overlooked. Recently, several studies have shown that individual differences contribute strongly to the functional connectivity patterns. In particular, functional connectomes have been proven to offer a fingerprint measure, which can reliably identify a given individual from a pool of participants. In this work, we propose to refine the standard measure of individual functional connectomes using dictionary learning. More specifically, we rely on the assumption that each functional connectivity is dominated by stable group and individual factors. By subtracting population-wise contributions from connectivity patterns facilitated by dictionary representation, intersubject variability should be increased within the group. We validate our approach using several types of analyses. For example, we observe that refined connectivity profiles significantly increase subject-specific identifiability across functional magnetic resonance imaging (fMRI) session combinations. Besides, refined connectomes can also improve the prediction power for cognitive behaviors. In accordance with results from the literature, we find that individual distinctiveness is closely linked with differences in neurocognitive activity within the brain. In summary, our results indicate that individual connectivity analysis benefits from the group-wise inferences and refined connectomes are indeed desirable for brain mapping.

AB - Brain functional connectome analysis is commonly based on population-wise inference. However, in this way precious information provided at the individual subject level may be overlooked. Recently, several studies have shown that individual differences contribute strongly to the functional connectivity patterns. In particular, functional connectomes have been proven to offer a fingerprint measure, which can reliably identify a given individual from a pool of participants. In this work, we propose to refine the standard measure of individual functional connectomes using dictionary learning. More specifically, we rely on the assumption that each functional connectivity is dominated by stable group and individual factors. By subtracting population-wise contributions from connectivity patterns facilitated by dictionary representation, intersubject variability should be increased within the group. We validate our approach using several types of analyses. For example, we observe that refined connectivity profiles significantly increase subject-specific identifiability across functional magnetic resonance imaging (fMRI) session combinations. Besides, refined connectomes can also improve the prediction power for cognitive behaviors. In accordance with results from the literature, we find that individual distinctiveness is closely linked with differences in neurocognitive activity within the brain. In summary, our results indicate that individual connectivity analysis benefits from the group-wise inferences and refined connectomes are indeed desirable for brain mapping.

KW - cognitive behavior prediction

KW - functional connectivity

KW - individual identification

KW - refined connectomes

KW - sparse dictionary learning model

UR - http://www.scopus.com/inward/record.url?scp=85070298298&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070298298&partnerID=8YFLogxK

U2 - 10.1002/hbm.24741

DO - 10.1002/hbm.24741

M3 - Article

C2 - 31355994

AN - SCOPUS:85070298298

VL - 40

SP - 4843

EP - 4858

JO - Human Brain Mapping

JF - Human Brain Mapping

SN - 1065-9471

IS - 16

ER -