Deep learning based decomposition of brain networks

Pilsub Lee, Myungwon Choi, Daegyeom Kim, Suji Lee, Hyun-Ghang Jeong, Cheol E. Han

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A brain network is the essence of the intelligence where it consists of nodes that are anatomically defined brain regions, and edges that connect a pair of brain regions. The diffusion-weighted magnetic resonance (MR) images and the advances in computer-Aided tractography algorithms let us know strong association between human brain networks and cognitive functions. Brain regions dedicated to a certain specific cognitive function were spatially clustered and efficiently connected each other; it is called local functional segregation. However, it is not well known that such a local segregation is associated with a certain sub-network which may act as a building block of the brain network. In this work, using a graph auto-encoder, we extracted building blocks of brain networks and investigate whether they are affected by a neurological disease, Alzheimer's disease. We found that the brain network of each person is linear summation of the learned building blocks. Also, the activation levels of these building blocks vary in the normal controls and patients with Alzheimer's disease, showing that network deterioration in the disease group.

Original languageEnglish
Title of host publication1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages349-354
Number of pages6
ISBN (Electronic)9781538678220
DOIs
Publication statusPublished - 2019 Mar 18
Event1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019 - Okinawa, Japan
Duration: 2019 Feb 112019 Feb 13

Publication series

Name1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019

Conference

Conference1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019
CountryJapan
CityOkinawa
Period19/2/1119/2/13

Fingerprint

Brain
Decomposition
Deep learning
Magnetic resonance
Deterioration
Chemical activation
Association reactions

Keywords

  • Alzheimer's disease
  • brain networks
  • graph auto-encoder
  • graph convolutional neural network

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Artificial Intelligence

Cite this

Lee, P., Choi, M., Kim, D., Lee, S., Jeong, H-G., & Han, C. E. (2019). Deep learning based decomposition of brain networks. In 1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019 (pp. 349-354). [8669055] (1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICAIIC.2019.8669055

Deep learning based decomposition of brain networks. / Lee, Pilsub; Choi, Myungwon; Kim, Daegyeom; Lee, Suji; Jeong, Hyun-Ghang; Han, Cheol E.

1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 349-354 8669055 (1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, P, Choi, M, Kim, D, Lee, S, Jeong, H-G & Han, CE 2019, Deep learning based decomposition of brain networks. in 1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019., 8669055, 1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019, Institute of Electrical and Electronics Engineers Inc., pp. 349-354, 1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019, Okinawa, Japan, 19/2/11. https://doi.org/10.1109/ICAIIC.2019.8669055
Lee P, Choi M, Kim D, Lee S, Jeong H-G, Han CE. Deep learning based decomposition of brain networks. In 1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 349-354. 8669055. (1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019). https://doi.org/10.1109/ICAIIC.2019.8669055
Lee, Pilsub ; Choi, Myungwon ; Kim, Daegyeom ; Lee, Suji ; Jeong, Hyun-Ghang ; Han, Cheol E. / Deep learning based decomposition of brain networks. 1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 349-354 (1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019).
@inproceedings{1cd6139786ad4de9b657341b45683cea,
title = "Deep learning based decomposition of brain networks",
abstract = "A brain network is the essence of the intelligence where it consists of nodes that are anatomically defined brain regions, and edges that connect a pair of brain regions. The diffusion-weighted magnetic resonance (MR) images and the advances in computer-Aided tractography algorithms let us know strong association between human brain networks and cognitive functions. Brain regions dedicated to a certain specific cognitive function were spatially clustered and efficiently connected each other; it is called local functional segregation. However, it is not well known that such a local segregation is associated with a certain sub-network which may act as a building block of the brain network. In this work, using a graph auto-encoder, we extracted building blocks of brain networks and investigate whether they are affected by a neurological disease, Alzheimer's disease. We found that the brain network of each person is linear summation of the learned building blocks. Also, the activation levels of these building blocks vary in the normal controls and patients with Alzheimer's disease, showing that network deterioration in the disease group.",
keywords = "Alzheimer's disease, brain networks, graph auto-encoder, graph convolutional neural network",
author = "Pilsub Lee and Myungwon Choi and Daegyeom Kim and Suji Lee and Hyun-Ghang Jeong and Han, {Cheol E.}",
year = "2019",
month = "3",
day = "18",
doi = "10.1109/ICAIIC.2019.8669055",
language = "English",
series = "1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "349--354",
booktitle = "1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019",

}

TY - GEN

T1 - Deep learning based decomposition of brain networks

AU - Lee, Pilsub

AU - Choi, Myungwon

AU - Kim, Daegyeom

AU - Lee, Suji

AU - Jeong, Hyun-Ghang

AU - Han, Cheol E.

PY - 2019/3/18

Y1 - 2019/3/18

N2 - A brain network is the essence of the intelligence where it consists of nodes that are anatomically defined brain regions, and edges that connect a pair of brain regions. The diffusion-weighted magnetic resonance (MR) images and the advances in computer-Aided tractography algorithms let us know strong association between human brain networks and cognitive functions. Brain regions dedicated to a certain specific cognitive function were spatially clustered and efficiently connected each other; it is called local functional segregation. However, it is not well known that such a local segregation is associated with a certain sub-network which may act as a building block of the brain network. In this work, using a graph auto-encoder, we extracted building blocks of brain networks and investigate whether they are affected by a neurological disease, Alzheimer's disease. We found that the brain network of each person is linear summation of the learned building blocks. Also, the activation levels of these building blocks vary in the normal controls and patients with Alzheimer's disease, showing that network deterioration in the disease group.

AB - A brain network is the essence of the intelligence where it consists of nodes that are anatomically defined brain regions, and edges that connect a pair of brain regions. The diffusion-weighted magnetic resonance (MR) images and the advances in computer-Aided tractography algorithms let us know strong association between human brain networks and cognitive functions. Brain regions dedicated to a certain specific cognitive function were spatially clustered and efficiently connected each other; it is called local functional segregation. However, it is not well known that such a local segregation is associated with a certain sub-network which may act as a building block of the brain network. In this work, using a graph auto-encoder, we extracted building blocks of brain networks and investigate whether they are affected by a neurological disease, Alzheimer's disease. We found that the brain network of each person is linear summation of the learned building blocks. Also, the activation levels of these building blocks vary in the normal controls and patients with Alzheimer's disease, showing that network deterioration in the disease group.

KW - Alzheimer's disease

KW - brain networks

KW - graph auto-encoder

KW - graph convolutional neural network

UR - http://www.scopus.com/inward/record.url?scp=85063884338&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063884338&partnerID=8YFLogxK

U2 - 10.1109/ICAIIC.2019.8669055

DO - 10.1109/ICAIIC.2019.8669055

M3 - Conference contribution

T3 - 1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019

SP - 349

EP - 354

BT - 1st International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -