Identification of infants at high-risk for autism spectrum disorder using multiparameter multiscale white matter connectivity networks

Yan Jin, Chong Yaw Wee, Feng Shi, Kim Han Thung, Dong Ni, Pew Thian Yap, Dinggang Shen

Research output: Contribution to journalArticle

35 Citations (Scopus)

Abstract

Autism spectrum disorder (ASD) is a wide range of disabilities that cause life-long cognitive impairment and social, communication, and behavioral challenges. Early diagnosis and medical intervention are important for improving the life quality of autistic patients. However, in the current practice, diagnosis often has to be delayed until the behavioral symptoms become evident during childhood. In this study, we demonstrate the feasibility of using machine learning techniques for identifying high-risk ASD infants at as early as six months after birth. This is based on the observation that ASD-induced abnormalities in white matter (WM) tracts and whole-brain connectivity have already started to appear within 24 months after birth. In particular, we propose a novel multikernel support vector machine classification framework by using the connectivity features gathered from WM connectivity networks, which are generated via multiscale regions of interest (ROIs) and multiple diffusion statistics such as fractional anisotropy, mean diffusivity, and average fiber length. Our proposed framework achieves an accuracy of 76% and an area of 0.80 under the receiver operating characteristic curve (AUC), in comparison to the accuracy of 70% and the AUC of 70% provided by the best single-parameter single-scale network. The improvement in accuracy is mainly due to the complementary information provided by multiparameter multiscale networks. In addition, our framework also provides the potential imaging connectomic markers and an objective means for early ASD diagnosis. Hum Brain Mapp 36:4880-4896, 2015.

Original languageEnglish
Pages (from-to)4880-4896
Number of pages17
JournalHuman Brain Mapping
Volume36
Issue number12
DOIs
Publication statusPublished - 2015 Dec 1

Fingerprint

Area Under Curve
Early Medical Intervention
Connectome
Parturition
Behavioral Symptoms
Anisotropy
Brain
ROC Curve
Early Diagnosis
Communication
Quality of Life
Autism Spectrum Disorder
White Matter
Support Vector Machine
Machine Learning
Cognitive Dysfunction

Keywords

  • Autism spectrum disorder
  • Classification
  • Connectivity networks
  • Diffusion weighted imaging
  • Infant

ASJC Scopus subject areas

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

Cite this

Identification of infants at high-risk for autism spectrum disorder using multiparameter multiscale white matter connectivity networks. / Jin, Yan; Wee, Chong Yaw; Shi, Feng; Thung, Kim Han; Ni, Dong; Yap, Pew Thian; Shen, Dinggang.

In: Human Brain Mapping, Vol. 36, No. 12, 01.12.2015, p. 4880-4896.

Research output: Contribution to journalArticle

Jin, Yan ; Wee, Chong Yaw ; Shi, Feng ; Thung, Kim Han ; Ni, Dong ; Yap, Pew Thian ; Shen, Dinggang. / Identification of infants at high-risk for autism spectrum disorder using multiparameter multiscale white matter connectivity networks. In: Human Brain Mapping. 2015 ; Vol. 36, No. 12. pp. 4880-4896.
@article{cf3e3403eab84c42a044591b700055a3,
title = "Identification of infants at high-risk for autism spectrum disorder using multiparameter multiscale white matter connectivity networks",
abstract = "Autism spectrum disorder (ASD) is a wide range of disabilities that cause life-long cognitive impairment and social, communication, and behavioral challenges. Early diagnosis and medical intervention are important for improving the life quality of autistic patients. However, in the current practice, diagnosis often has to be delayed until the behavioral symptoms become evident during childhood. In this study, we demonstrate the feasibility of using machine learning techniques for identifying high-risk ASD infants at as early as six months after birth. This is based on the observation that ASD-induced abnormalities in white matter (WM) tracts and whole-brain connectivity have already started to appear within 24 months after birth. In particular, we propose a novel multikernel support vector machine classification framework by using the connectivity features gathered from WM connectivity networks, which are generated via multiscale regions of interest (ROIs) and multiple diffusion statistics such as fractional anisotropy, mean diffusivity, and average fiber length. Our proposed framework achieves an accuracy of 76{\%} and an area of 0.80 under the receiver operating characteristic curve (AUC), in comparison to the accuracy of 70{\%} and the AUC of 70{\%} provided by the best single-parameter single-scale network. The improvement in accuracy is mainly due to the complementary information provided by multiparameter multiscale networks. In addition, our framework also provides the potential imaging connectomic markers and an objective means for early ASD diagnosis. Hum Brain Mapp 36:4880-4896, 2015.",
keywords = "Autism spectrum disorder, Classification, Connectivity networks, Diffusion weighted imaging, Infant",
author = "Yan Jin and Wee, {Chong Yaw} and Feng Shi and Thung, {Kim Han} and Dong Ni and Yap, {Pew Thian} and Dinggang Shen",
year = "2015",
month = "12",
day = "1",
doi = "10.1002/hbm.22957",
language = "English",
volume = "36",
pages = "4880--4896",
journal = "Human Brain Mapping",
issn = "1065-9471",
publisher = "Wiley-Liss Inc.",
number = "12",

}

TY - JOUR

T1 - Identification of infants at high-risk for autism spectrum disorder using multiparameter multiscale white matter connectivity networks

AU - Jin, Yan

AU - Wee, Chong Yaw

AU - Shi, Feng

AU - Thung, Kim Han

AU - Ni, Dong

AU - Yap, Pew Thian

AU - Shen, Dinggang

PY - 2015/12/1

Y1 - 2015/12/1

N2 - Autism spectrum disorder (ASD) is a wide range of disabilities that cause life-long cognitive impairment and social, communication, and behavioral challenges. Early diagnosis and medical intervention are important for improving the life quality of autistic patients. However, in the current practice, diagnosis often has to be delayed until the behavioral symptoms become evident during childhood. In this study, we demonstrate the feasibility of using machine learning techniques for identifying high-risk ASD infants at as early as six months after birth. This is based on the observation that ASD-induced abnormalities in white matter (WM) tracts and whole-brain connectivity have already started to appear within 24 months after birth. In particular, we propose a novel multikernel support vector machine classification framework by using the connectivity features gathered from WM connectivity networks, which are generated via multiscale regions of interest (ROIs) and multiple diffusion statistics such as fractional anisotropy, mean diffusivity, and average fiber length. Our proposed framework achieves an accuracy of 76% and an area of 0.80 under the receiver operating characteristic curve (AUC), in comparison to the accuracy of 70% and the AUC of 70% provided by the best single-parameter single-scale network. The improvement in accuracy is mainly due to the complementary information provided by multiparameter multiscale networks. In addition, our framework also provides the potential imaging connectomic markers and an objective means for early ASD diagnosis. Hum Brain Mapp 36:4880-4896, 2015.

AB - Autism spectrum disorder (ASD) is a wide range of disabilities that cause life-long cognitive impairment and social, communication, and behavioral challenges. Early diagnosis and medical intervention are important for improving the life quality of autistic patients. However, in the current practice, diagnosis often has to be delayed until the behavioral symptoms become evident during childhood. In this study, we demonstrate the feasibility of using machine learning techniques for identifying high-risk ASD infants at as early as six months after birth. This is based on the observation that ASD-induced abnormalities in white matter (WM) tracts and whole-brain connectivity have already started to appear within 24 months after birth. In particular, we propose a novel multikernel support vector machine classification framework by using the connectivity features gathered from WM connectivity networks, which are generated via multiscale regions of interest (ROIs) and multiple diffusion statistics such as fractional anisotropy, mean diffusivity, and average fiber length. Our proposed framework achieves an accuracy of 76% and an area of 0.80 under the receiver operating characteristic curve (AUC), in comparison to the accuracy of 70% and the AUC of 70% provided by the best single-parameter single-scale network. The improvement in accuracy is mainly due to the complementary information provided by multiparameter multiscale networks. In addition, our framework also provides the potential imaging connectomic markers and an objective means for early ASD diagnosis. Hum Brain Mapp 36:4880-4896, 2015.

KW - Autism spectrum disorder

KW - Classification

KW - Connectivity networks

KW - Diffusion weighted imaging

KW - Infant

UR - http://www.scopus.com/inward/record.url?scp=84956577012&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956577012&partnerID=8YFLogxK

U2 - 10.1002/hbm.22957

DO - 10.1002/hbm.22957

M3 - Article

VL - 36

SP - 4880

EP - 4896

JO - Human Brain Mapping

JF - Human Brain Mapping

SN - 1065-9471

IS - 12

ER -