High-order Connectomic Manifold Learning for Autistic Brain State Identification

Mayssa Soussia, Islem Rekik (Lead / Corresponding author)

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

12 Citations (Scopus)
100 Downloads (Pure)

Abstract

Previous studies have identified disordered functional (from fMRI) and structural (from diffusion MRI) brain connectivities in Autism Spectrum Disorder (ASD). However, ‘shape connections’ between brain regions were rarely investigated in ASD – e.g., how morphological attributes of a specific brain region (e.g., sulcal depth) change in relation to morphological attributes in other regions. In this paper, we use conventional T1-w MRI to define morphological connectivity networks, each quantifying shape similarity between different cortical regions for a specific cortical attribute at both low-order and high-order levels. For ASD identification, we present a connectomic manifold learning framework, which learns multiple kernels to estimate a similarity measure between ASD and normal controls (NC) connectomic features, to perform dimensionality reduction for clustering ASD and NC subjects. We benchmark our ASD identification method against supervised and unsupervised state-of-the-art methods, while depicting the most discriminative high- and low-order relationships between morphological regions in the left and right hemispheres.
Original languageEnglish
Title of host publicationConnectomics in NeuroImaging
Place of PublicationSwitzerland
PublisherSpringer
Pages51-59
Number of pages9
Volume10511
ISBN (Electronic)9783319671598
ISBN (Print)9783319671581
DOIs
Publication statusPublished - 2017
EventInternational Workshop on Connectomics in Neuroimaging: Held in Conjunction with MICCAI 2017 - Québec City Convention Centre, Centre des congrès de Québec, Québec , Canada
Duration: 14 Sep 2017 → …
Conference number: First International Workshop
http://munsellb.people.cofc.edu/cni.html

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume10511
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceInternational Workshop on Connectomics in Neuroimaging
Abbreviated titleCNI 2017
CountryCanada
CityQuébec
Period14/09/17 → …
Internet address

Fingerprint

Brain
Magnetic resonance imaging
Magnetic Resonance Imaging

Cite this

Soussia, M., & Rekik, I. (2017). High-order Connectomic Manifold Learning for Autistic Brain State Identification. In Connectomics in NeuroImaging (Vol. 10511, pp. 51-59). (Lecture Notes in Computer Science; Vol. 10511). Switzerland: Springer . https://doi.org/10.1007/978-3-319-67159-8_7
Soussia, Mayssa ; Rekik, Islem. / High-order Connectomic Manifold Learning for Autistic Brain State Identification. Connectomics in NeuroImaging. Vol. 10511 Switzerland : Springer , 2017. pp. 51-59 (Lecture Notes in Computer Science).
@inproceedings{a6b38e7dc8834e67aa10a65a647627db,
title = "High-order Connectomic Manifold Learning for Autistic Brain State Identification",
abstract = "Previous studies have identified disordered functional (from fMRI) and structural (from diffusion MRI) brain connectivities in Autism Spectrum Disorder (ASD). However, ‘shape connections’ between brain regions were rarely investigated in ASD – e.g., how morphological attributes of a specific brain region (e.g., sulcal depth) change in relation to morphological attributes in other regions. In this paper, we use conventional T1-w MRI to define morphological connectivity networks, each quantifying shape similarity between different cortical regions for a specific cortical attribute at both low-order and high-order levels. For ASD identification, we present a connectomic manifold learning framework, which learns multiple kernels to estimate a similarity measure between ASD and normal controls (NC) connectomic features, to perform dimensionality reduction for clustering ASD and NC subjects. We benchmark our ASD identification method against supervised and unsupervised state-of-the-art methods, while depicting the most discriminative high- and low-order relationships between morphological regions in the left and right hemispheres.",
author = "Mayssa Soussia and Islem Rekik",
note = "{\circledC} Springer International Publishing AG 2017",
year = "2017",
doi = "10.1007/978-3-319-67159-8_7",
language = "English",
isbn = "9783319671581",
volume = "10511",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "51--59",
booktitle = "Connectomics in NeuroImaging",

}

Soussia, M & Rekik, I 2017, High-order Connectomic Manifold Learning for Autistic Brain State Identification. in Connectomics in NeuroImaging. vol. 10511, Lecture Notes in Computer Science, vol. 10511, Springer , Switzerland, pp. 51-59, International Workshop on Connectomics in Neuroimaging, Québec , Canada, 14/09/17. https://doi.org/10.1007/978-3-319-67159-8_7

High-order Connectomic Manifold Learning for Autistic Brain State Identification. / Soussia, Mayssa ; Rekik, Islem (Lead / Corresponding author).

Connectomics in NeuroImaging. Vol. 10511 Switzerland : Springer , 2017. p. 51-59 (Lecture Notes in Computer Science; Vol. 10511).

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

TY - GEN

T1 - High-order Connectomic Manifold Learning for Autistic Brain State Identification

AU - Soussia, Mayssa

AU - Rekik, Islem

N1 - © Springer International Publishing AG 2017

PY - 2017

Y1 - 2017

N2 - Previous studies have identified disordered functional (from fMRI) and structural (from diffusion MRI) brain connectivities in Autism Spectrum Disorder (ASD). However, ‘shape connections’ between brain regions were rarely investigated in ASD – e.g., how morphological attributes of a specific brain region (e.g., sulcal depth) change in relation to morphological attributes in other regions. In this paper, we use conventional T1-w MRI to define morphological connectivity networks, each quantifying shape similarity between different cortical regions for a specific cortical attribute at both low-order and high-order levels. For ASD identification, we present a connectomic manifold learning framework, which learns multiple kernels to estimate a similarity measure between ASD and normal controls (NC) connectomic features, to perform dimensionality reduction for clustering ASD and NC subjects. We benchmark our ASD identification method against supervised and unsupervised state-of-the-art methods, while depicting the most discriminative high- and low-order relationships between morphological regions in the left and right hemispheres.

AB - Previous studies have identified disordered functional (from fMRI) and structural (from diffusion MRI) brain connectivities in Autism Spectrum Disorder (ASD). However, ‘shape connections’ between brain regions were rarely investigated in ASD – e.g., how morphological attributes of a specific brain region (e.g., sulcal depth) change in relation to morphological attributes in other regions. In this paper, we use conventional T1-w MRI to define morphological connectivity networks, each quantifying shape similarity between different cortical regions for a specific cortical attribute at both low-order and high-order levels. For ASD identification, we present a connectomic manifold learning framework, which learns multiple kernels to estimate a similarity measure between ASD and normal controls (NC) connectomic features, to perform dimensionality reduction for clustering ASD and NC subjects. We benchmark our ASD identification method against supervised and unsupervised state-of-the-art methods, while depicting the most discriminative high- and low-order relationships between morphological regions in the left and right hemispheres.

U2 - 10.1007/978-3-319-67159-8_7

DO - 10.1007/978-3-319-67159-8_7

M3 - Conference contribution

SN - 9783319671581

VL - 10511

T3 - Lecture Notes in Computer Science

SP - 51

EP - 59

BT - Connectomics in NeuroImaging

PB - Springer

CY - Switzerland

ER -

Soussia M, Rekik I. High-order Connectomic Manifold Learning for Autistic Brain State Identification. In Connectomics in NeuroImaging. Vol. 10511. Switzerland: Springer . 2017. p. 51-59. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-319-67159-8_7