Relationship between neuronal network architecture and naming performance in temporal lobe epilepsy: A connectome based approach using machine learning

B. C. Munsell, G. Wu, J. Fridriksson, K. Thayer, N. Mofrad, N. Desisto, Dinggang Shen, L. Bonilha

Research output: Contribution to journalArticle

Abstract

Impaired confrontation naming is a common symptom of temporal lobe epilepsy (TLE). The neurobiological mechanisms underlying this impairment are poorly understood but may indicate a structural disorganization of broadly distributed neuronal networks that support naming ability. Importantly, naming is frequently impaired in other neurological disorders and by contrasting the neuronal structures supporting naming in TLE with other diseases, it will become possible to elucidate the common systems supporting naming. We aimed to evaluate the neuronal networks that support naming in TLE by using a machine learning algorithm intended to predict naming performance in subjects with medication refractory TLE using only the structural brain connectome reconstructed from diffusion tensor imaging. A connectome-based prediction framework was developed using network properties from anatomically defined brain regions across the entire brain, which were used in a multi-task machine learning algorithm followed by support vector regression. Nodal eigenvector centrality, a measure of regional network integration, predicted approximately 60% of the variance in naming. The nodes with the highest regression weight were bilaterally distributed among perilimbic sub-networks involving mainly the medial and lateral temporal lobe regions. In the context of emerging evidence regarding the role of large structural networks that support language processing, our results suggest intact naming relies on the integration of sub-networks, as opposed to being dependent on isolated brain areas. In the case of TLE, these sub-networks may be disproportionately indicative naming processes that are dependent semantic integration from memory and lexical retrieval, as opposed to multi-modal perception or motor speech production.

Original languageEnglish
JournalBrain and Language
DOIs
Publication statusAccepted/In press - 2017 Jan 1
Externally publishedYes

Fingerprint

Connectome
epilepsy
Temporal Lobe Epilepsy
learning
performance
Brain
Temporal Lobe
brain
Diffusion Tensor Imaging
Aptitude
Nervous System Diseases
Semantics
regression
Language
Machine Learning
Naming
Weights and Measures
medication
semantics
Disease

ASJC Scopus subject areas

  • Experimental and Cognitive Psychology
  • Language and Linguistics
  • Linguistics and Language
  • Cognitive Neuroscience
  • Speech and Hearing

Cite this

Relationship between neuronal network architecture and naming performance in temporal lobe epilepsy : A connectome based approach using machine learning. / Munsell, B. C.; Wu, G.; Fridriksson, J.; Thayer, K.; Mofrad, N.; Desisto, N.; Shen, Dinggang; Bonilha, L.

In: Brain and Language, 01.01.2017.

Research output: Contribution to journalArticle

@article{5f38b48d5a0c4eb8a75c07761565520c,
title = "Relationship between neuronal network architecture and naming performance in temporal lobe epilepsy: A connectome based approach using machine learning",
abstract = "Impaired confrontation naming is a common symptom of temporal lobe epilepsy (TLE). The neurobiological mechanisms underlying this impairment are poorly understood but may indicate a structural disorganization of broadly distributed neuronal networks that support naming ability. Importantly, naming is frequently impaired in other neurological disorders and by contrasting the neuronal structures supporting naming in TLE with other diseases, it will become possible to elucidate the common systems supporting naming. We aimed to evaluate the neuronal networks that support naming in TLE by using a machine learning algorithm intended to predict naming performance in subjects with medication refractory TLE using only the structural brain connectome reconstructed from diffusion tensor imaging. A connectome-based prediction framework was developed using network properties from anatomically defined brain regions across the entire brain, which were used in a multi-task machine learning algorithm followed by support vector regression. Nodal eigenvector centrality, a measure of regional network integration, predicted approximately 60{\%} of the variance in naming. The nodes with the highest regression weight were bilaterally distributed among perilimbic sub-networks involving mainly the medial and lateral temporal lobe regions. In the context of emerging evidence regarding the role of large structural networks that support language processing, our results suggest intact naming relies on the integration of sub-networks, as opposed to being dependent on isolated brain areas. In the case of TLE, these sub-networks may be disproportionately indicative naming processes that are dependent semantic integration from memory and lexical retrieval, as opposed to multi-modal perception or motor speech production.",
author = "Munsell, {B. C.} and G. Wu and J. Fridriksson and K. Thayer and N. Mofrad and N. Desisto and Dinggang Shen and L. Bonilha",
year = "2017",
month = "1",
day = "1",
doi = "10.1016/j.bandl.2017.08.006",
language = "English",
journal = "Brain and Language",
issn = "0093-934X",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Relationship between neuronal network architecture and naming performance in temporal lobe epilepsy

T2 - A connectome based approach using machine learning

AU - Munsell, B. C.

AU - Wu, G.

AU - Fridriksson, J.

AU - Thayer, K.

AU - Mofrad, N.

AU - Desisto, N.

AU - Shen, Dinggang

AU - Bonilha, L.

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Impaired confrontation naming is a common symptom of temporal lobe epilepsy (TLE). The neurobiological mechanisms underlying this impairment are poorly understood but may indicate a structural disorganization of broadly distributed neuronal networks that support naming ability. Importantly, naming is frequently impaired in other neurological disorders and by contrasting the neuronal structures supporting naming in TLE with other diseases, it will become possible to elucidate the common systems supporting naming. We aimed to evaluate the neuronal networks that support naming in TLE by using a machine learning algorithm intended to predict naming performance in subjects with medication refractory TLE using only the structural brain connectome reconstructed from diffusion tensor imaging. A connectome-based prediction framework was developed using network properties from anatomically defined brain regions across the entire brain, which were used in a multi-task machine learning algorithm followed by support vector regression. Nodal eigenvector centrality, a measure of regional network integration, predicted approximately 60% of the variance in naming. The nodes with the highest regression weight were bilaterally distributed among perilimbic sub-networks involving mainly the medial and lateral temporal lobe regions. In the context of emerging evidence regarding the role of large structural networks that support language processing, our results suggest intact naming relies on the integration of sub-networks, as opposed to being dependent on isolated brain areas. In the case of TLE, these sub-networks may be disproportionately indicative naming processes that are dependent semantic integration from memory and lexical retrieval, as opposed to multi-modal perception or motor speech production.

AB - Impaired confrontation naming is a common symptom of temporal lobe epilepsy (TLE). The neurobiological mechanisms underlying this impairment are poorly understood but may indicate a structural disorganization of broadly distributed neuronal networks that support naming ability. Importantly, naming is frequently impaired in other neurological disorders and by contrasting the neuronal structures supporting naming in TLE with other diseases, it will become possible to elucidate the common systems supporting naming. We aimed to evaluate the neuronal networks that support naming in TLE by using a machine learning algorithm intended to predict naming performance in subjects with medication refractory TLE using only the structural brain connectome reconstructed from diffusion tensor imaging. A connectome-based prediction framework was developed using network properties from anatomically defined brain regions across the entire brain, which were used in a multi-task machine learning algorithm followed by support vector regression. Nodal eigenvector centrality, a measure of regional network integration, predicted approximately 60% of the variance in naming. The nodes with the highest regression weight were bilaterally distributed among perilimbic sub-networks involving mainly the medial and lateral temporal lobe regions. In the context of emerging evidence regarding the role of large structural networks that support language processing, our results suggest intact naming relies on the integration of sub-networks, as opposed to being dependent on isolated brain areas. In the case of TLE, these sub-networks may be disproportionately indicative naming processes that are dependent semantic integration from memory and lexical retrieval, as opposed to multi-modal perception or motor speech production.

UR - http://www.scopus.com/inward/record.url?scp=85028930852&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028930852&partnerID=8YFLogxK

U2 - 10.1016/j.bandl.2017.08.006

DO - 10.1016/j.bandl.2017.08.006

M3 - Article

C2 - 28899551

AN - SCOPUS:85028930852

JO - Brain and Language

JF - Brain and Language

SN - 0093-934X

ER -