Diagnosis of autism spectrum disorders using regional and interregional morphological features

Chong Yaw Wee, Li Wang, Feng Shi, Pew Thian Yap, Dinggang Shen

Research output: Contribution to journalArticle

38 Citations (Scopus)

Abstract

This article describes a novel approach to identify autism spectrum disorder (ASD) utilizing regional and interregional morphological patterns extracted from structural magnetic resonance images. Two types of features are extracted to characterize the morphological patterns: (1) Regional features, which includes the cortical thickness, volumes of cortical gray matter, and cortical-associated white matter regions, and several subcortical structures extracted from different regions-of-interest (ROIs); (2) Interregional features, which convey the morphological change pattern between pairs of ROIs. We demonstrate that the integration of regional and interregional features via multi-kernel learning technique can significantly improve the classification performance of ASD, compared with using either regional or interregional features alone. Specifically, the proposed framework achieves an accuracy of 96.27% and an area of 0.9952 under the receiver operating characteristic curve, indicating excellent diagnostic power and generalizability. The best performance is achieved when both feature types are weighted approximately equal, indicating complementary between these two feature types. Regions that contributed the most to classification are in line with those reported in the previous studies, particularly the subcortical structures that are highly associated with human emotional modulation and memory formation. The autistic brains demonstrate a significant rightward asymmetry pattern particularly in the auditory language areas. These findings are in agreement with the fact that ASD is a behavioral- and language-related neurodevelopmental disorder. By concurrent consideration of both regional and interregional features, the current work presents an effective means for better characterization of neurobiological underpinnings of ASD that facilitates its identification from typically developing children.

Original languageEnglish
Pages (from-to)3414-3430
Number of pages17
JournalHuman Brain Mapping
Volume35
Issue number7
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Language
Auditory Cortex
ROC Curve
Magnetic Resonance Spectroscopy
Learning
Autism Spectrum Disorder
Brain
White Matter
Gray Matter
Power (Psychology)
Neurodevelopmental Disorders
Identification (Psychology)

ASJC Scopus subject areas

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

Cite this

Diagnosis of autism spectrum disorders using regional and interregional morphological features. / Wee, Chong Yaw; Wang, Li; Shi, Feng; Yap, Pew Thian; Shen, Dinggang.

In: Human Brain Mapping, Vol. 35, No. 7, 01.01.2014, p. 3414-3430.

Research output: Contribution to journalArticle

Wee, Chong Yaw ; Wang, Li ; Shi, Feng ; Yap, Pew Thian ; Shen, Dinggang. / Diagnosis of autism spectrum disorders using regional and interregional morphological features. In: Human Brain Mapping. 2014 ; Vol. 35, No. 7. pp. 3414-3430.
@article{bc55213d6e794315aea73cea422c44dd,
title = "Diagnosis of autism spectrum disorders using regional and interregional morphological features",
abstract = "This article describes a novel approach to identify autism spectrum disorder (ASD) utilizing regional and interregional morphological patterns extracted from structural magnetic resonance images. Two types of features are extracted to characterize the morphological patterns: (1) Regional features, which includes the cortical thickness, volumes of cortical gray matter, and cortical-associated white matter regions, and several subcortical structures extracted from different regions-of-interest (ROIs); (2) Interregional features, which convey the morphological change pattern between pairs of ROIs. We demonstrate that the integration of regional and interregional features via multi-kernel learning technique can significantly improve the classification performance of ASD, compared with using either regional or interregional features alone. Specifically, the proposed framework achieves an accuracy of 96.27{\%} and an area of 0.9952 under the receiver operating characteristic curve, indicating excellent diagnostic power and generalizability. The best performance is achieved when both feature types are weighted approximately equal, indicating complementary between these two feature types. Regions that contributed the most to classification are in line with those reported in the previous studies, particularly the subcortical structures that are highly associated with human emotional modulation and memory formation. The autistic brains demonstrate a significant rightward asymmetry pattern particularly in the auditory language areas. These findings are in agreement with the fact that ASD is a behavioral- and language-related neurodevelopmental disorder. By concurrent consideration of both regional and interregional features, the current work presents an effective means for better characterization of neurobiological underpinnings of ASD that facilitates its identification from typically developing children.",
keywords = "Autism spectrum disorders (ASD), Interregional features, Limbic system, Magnetic resonance imaging (MRI), Multiple-kernel learning (MKL), Regional features, Rightward asymmetry",
author = "Wee, {Chong Yaw} and Li Wang and Feng Shi and Yap, {Pew Thian} and Dinggang Shen",
year = "2014",
month = "1",
day = "1",
doi = "10.1002/hbm.22411",
language = "English",
volume = "35",
pages = "3414--3430",
journal = "Human Brain Mapping",
issn = "1065-9471",
publisher = "Wiley-Liss Inc.",
number = "7",

}

TY - JOUR

T1 - Diagnosis of autism spectrum disorders using regional and interregional morphological features

AU - Wee, Chong Yaw

AU - Wang, Li

AU - Shi, Feng

AU - Yap, Pew Thian

AU - Shen, Dinggang

PY - 2014/1/1

Y1 - 2014/1/1

N2 - This article describes a novel approach to identify autism spectrum disorder (ASD) utilizing regional and interregional morphological patterns extracted from structural magnetic resonance images. Two types of features are extracted to characterize the morphological patterns: (1) Regional features, which includes the cortical thickness, volumes of cortical gray matter, and cortical-associated white matter regions, and several subcortical structures extracted from different regions-of-interest (ROIs); (2) Interregional features, which convey the morphological change pattern between pairs of ROIs. We demonstrate that the integration of regional and interregional features via multi-kernel learning technique can significantly improve the classification performance of ASD, compared with using either regional or interregional features alone. Specifically, the proposed framework achieves an accuracy of 96.27% and an area of 0.9952 under the receiver operating characteristic curve, indicating excellent diagnostic power and generalizability. The best performance is achieved when both feature types are weighted approximately equal, indicating complementary between these two feature types. Regions that contributed the most to classification are in line with those reported in the previous studies, particularly the subcortical structures that are highly associated with human emotional modulation and memory formation. The autistic brains demonstrate a significant rightward asymmetry pattern particularly in the auditory language areas. These findings are in agreement with the fact that ASD is a behavioral- and language-related neurodevelopmental disorder. By concurrent consideration of both regional and interregional features, the current work presents an effective means for better characterization of neurobiological underpinnings of ASD that facilitates its identification from typically developing children.

AB - This article describes a novel approach to identify autism spectrum disorder (ASD) utilizing regional and interregional morphological patterns extracted from structural magnetic resonance images. Two types of features are extracted to characterize the morphological patterns: (1) Regional features, which includes the cortical thickness, volumes of cortical gray matter, and cortical-associated white matter regions, and several subcortical structures extracted from different regions-of-interest (ROIs); (2) Interregional features, which convey the morphological change pattern between pairs of ROIs. We demonstrate that the integration of regional and interregional features via multi-kernel learning technique can significantly improve the classification performance of ASD, compared with using either regional or interregional features alone. Specifically, the proposed framework achieves an accuracy of 96.27% and an area of 0.9952 under the receiver operating characteristic curve, indicating excellent diagnostic power and generalizability. The best performance is achieved when both feature types are weighted approximately equal, indicating complementary between these two feature types. Regions that contributed the most to classification are in line with those reported in the previous studies, particularly the subcortical structures that are highly associated with human emotional modulation and memory formation. The autistic brains demonstrate a significant rightward asymmetry pattern particularly in the auditory language areas. These findings are in agreement with the fact that ASD is a behavioral- and language-related neurodevelopmental disorder. By concurrent consideration of both regional and interregional features, the current work presents an effective means for better characterization of neurobiological underpinnings of ASD that facilitates its identification from typically developing children.

KW - Autism spectrum disorders (ASD)

KW - Interregional features

KW - Limbic system

KW - Magnetic resonance imaging (MRI)

KW - Multiple-kernel learning (MKL)

KW - Regional features

KW - Rightward asymmetry

UR - http://www.scopus.com/inward/record.url?scp=84902142587&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902142587&partnerID=8YFLogxK

U2 - 10.1002/hbm.22411

DO - 10.1002/hbm.22411

M3 - Article

C2 - 25050428

AN - SCOPUS:84902142587

VL - 35

SP - 3414

EP - 3430

JO - Human Brain Mapping

JF - Human Brain Mapping

SN - 1065-9471

IS - 7

ER -