Multiple deep learning architectures achieve superior performance diagnosing autism spectrum disorder using features previously extracted from structural and functional mri

Cooper Mellema, Alex Treacher, Kevin Nguyen, Albert Montillo

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

Abstract

The diagnosis of Autism Spectrum Disorder (ASD) is a subjective process requiring clinical expertise in neurodevelopmental disorders. Since such expertise is not available at many clinics, automated diagnosis using machine learning (ML) algorithms would be of great value to both clinicians and the imaging community to increase the diagnoses' availability and reproducibility while reducing subjectivity. This research systematically compares the performance of classifiers using over 900 subjects from the IMPAC database [1], using the database's derived anatomical and functional features to diagnose a subject as autistic or healthy. In total 12 classifiers are compared from 3 categories including: 6 nonlinear shallow ML models, 3 linear shallow models, and 3 deep learning models. When evaluated with an AUC ROC performance metric, results include: (1) amongst the shallow learning methods, linear models outperformed nonlinear models, agreeing with [2]. (2) Deep learning models outperformed shallow ML models. (3) The best model was a dense feedforward network, achieving 0.80 AUC which compares to the recently reported 0.79 \pm 0.01 AUC average of the top 10 methods from the IMPAC challenge [3]. These results demonstrate that even when using features derived from imaging data, deep learning methods can provide additional predictive accuracy over classical methods.

Original languageEnglish (US)
Title of host publicationISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging
PublisherIEEE Computer Society
Pages1891-1895
Number of pages5
ISBN (Electronic)9781538636411
DOIs
StatePublished - Apr 2019
Event16th IEEE International Symposium on Biomedical Imaging, ISBI 2019 - Venice, Italy
Duration: Apr 8 2019Apr 11 2019

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2019-April
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference16th IEEE International Symposium on Biomedical Imaging, ISBI 2019
CountryItaly
CityVenice
Period4/8/194/11/19

Fingerprint

Learning
Area Under Curve
Linear Models
Databases
Learning systems
Nonlinear Dynamics
Classifiers
Imaging techniques
Autism Spectrum Disorder
Deep learning
Research
Learning algorithms
Machine Learning
Availability
Neurodevelopmental Disorders

Keywords

  • Autism spectrum disorder
  • Deep learning
  • Machine learning
  • MRI
  • Neuroimaging

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Mellema, C., Treacher, A., Nguyen, K., & Montillo, A. (2019). Multiple deep learning architectures achieve superior performance diagnosing autism spectrum disorder using features previously extracted from structural and functional mri. In ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging (pp. 1891-1895). [8759193] (Proceedings - International Symposium on Biomedical Imaging; Vol. 2019-April). IEEE Computer Society. https://doi.org/10.1109/ISBI.2019.8759193

Multiple deep learning architectures achieve superior performance diagnosing autism spectrum disorder using features previously extracted from structural and functional mri. / Mellema, Cooper; Treacher, Alex; Nguyen, Kevin; Montillo, Albert.

ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society, 2019. p. 1891-1895 8759193 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2019-April).

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

Mellema, C, Treacher, A, Nguyen, K & Montillo, A 2019, Multiple deep learning architectures achieve superior performance diagnosing autism spectrum disorder using features previously extracted from structural and functional mri. in ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging., 8759193, Proceedings - International Symposium on Biomedical Imaging, vol. 2019-April, IEEE Computer Society, pp. 1891-1895, 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019, Venice, Italy, 4/8/19. https://doi.org/10.1109/ISBI.2019.8759193
Mellema C, Treacher A, Nguyen K, Montillo A. Multiple deep learning architectures achieve superior performance diagnosing autism spectrum disorder using features previously extracted from structural and functional mri. In ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society. 2019. p. 1891-1895. 8759193. (Proceedings - International Symposium on Biomedical Imaging). https://doi.org/10.1109/ISBI.2019.8759193
Mellema, Cooper ; Treacher, Alex ; Nguyen, Kevin ; Montillo, Albert. / Multiple deep learning architectures achieve superior performance diagnosing autism spectrum disorder using features previously extracted from structural and functional mri. ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society, 2019. pp. 1891-1895 (Proceedings - International Symposium on Biomedical Imaging).
@inproceedings{65fe76d5eeb3499995476535a52eae19,
title = "Multiple deep learning architectures achieve superior performance diagnosing autism spectrum disorder using features previously extracted from structural and functional mri",
abstract = "The diagnosis of Autism Spectrum Disorder (ASD) is a subjective process requiring clinical expertise in neurodevelopmental disorders. Since such expertise is not available at many clinics, automated diagnosis using machine learning (ML) algorithms would be of great value to both clinicians and the imaging community to increase the diagnoses' availability and reproducibility while reducing subjectivity. This research systematically compares the performance of classifiers using over 900 subjects from the IMPAC database [1], using the database's derived anatomical and functional features to diagnose a subject as autistic or healthy. In total 12 classifiers are compared from 3 categories including: 6 nonlinear shallow ML models, 3 linear shallow models, and 3 deep learning models. When evaluated with an AUC ROC performance metric, results include: (1) amongst the shallow learning methods, linear models outperformed nonlinear models, agreeing with [2]. (2) Deep learning models outperformed shallow ML models. (3) The best model was a dense feedforward network, achieving 0.80 AUC which compares to the recently reported 0.79 \pm 0.01 AUC average of the top 10 methods from the IMPAC challenge [3]. These results demonstrate that even when using features derived from imaging data, deep learning methods can provide additional predictive accuracy over classical methods.",
keywords = "Autism spectrum disorder, Deep learning, Machine learning, MRI, Neuroimaging",
author = "Cooper Mellema and Alex Treacher and Kevin Nguyen and Albert Montillo",
year = "2019",
month = "4",
doi = "10.1109/ISBI.2019.8759193",
language = "English (US)",
series = "Proceedings - International Symposium on Biomedical Imaging",
publisher = "IEEE Computer Society",
pages = "1891--1895",
booktitle = "ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - Multiple deep learning architectures achieve superior performance diagnosing autism spectrum disorder using features previously extracted from structural and functional mri

AU - Mellema, Cooper

AU - Treacher, Alex

AU - Nguyen, Kevin

AU - Montillo, Albert

PY - 2019/4

Y1 - 2019/4

N2 - The diagnosis of Autism Spectrum Disorder (ASD) is a subjective process requiring clinical expertise in neurodevelopmental disorders. Since such expertise is not available at many clinics, automated diagnosis using machine learning (ML) algorithms would be of great value to both clinicians and the imaging community to increase the diagnoses' availability and reproducibility while reducing subjectivity. This research systematically compares the performance of classifiers using over 900 subjects from the IMPAC database [1], using the database's derived anatomical and functional features to diagnose a subject as autistic or healthy. In total 12 classifiers are compared from 3 categories including: 6 nonlinear shallow ML models, 3 linear shallow models, and 3 deep learning models. When evaluated with an AUC ROC performance metric, results include: (1) amongst the shallow learning methods, linear models outperformed nonlinear models, agreeing with [2]. (2) Deep learning models outperformed shallow ML models. (3) The best model was a dense feedforward network, achieving 0.80 AUC which compares to the recently reported 0.79 \pm 0.01 AUC average of the top 10 methods from the IMPAC challenge [3]. These results demonstrate that even when using features derived from imaging data, deep learning methods can provide additional predictive accuracy over classical methods.

AB - The diagnosis of Autism Spectrum Disorder (ASD) is a subjective process requiring clinical expertise in neurodevelopmental disorders. Since such expertise is not available at many clinics, automated diagnosis using machine learning (ML) algorithms would be of great value to both clinicians and the imaging community to increase the diagnoses' availability and reproducibility while reducing subjectivity. This research systematically compares the performance of classifiers using over 900 subjects from the IMPAC database [1], using the database's derived anatomical and functional features to diagnose a subject as autistic or healthy. In total 12 classifiers are compared from 3 categories including: 6 nonlinear shallow ML models, 3 linear shallow models, and 3 deep learning models. When evaluated with an AUC ROC performance metric, results include: (1) amongst the shallow learning methods, linear models outperformed nonlinear models, agreeing with [2]. (2) Deep learning models outperformed shallow ML models. (3) The best model was a dense feedforward network, achieving 0.80 AUC which compares to the recently reported 0.79 \pm 0.01 AUC average of the top 10 methods from the IMPAC challenge [3]. These results demonstrate that even when using features derived from imaging data, deep learning methods can provide additional predictive accuracy over classical methods.

KW - Autism spectrum disorder

KW - Deep learning

KW - Machine learning

KW - MRI

KW - Neuroimaging

UR - http://www.scopus.com/inward/record.url?scp=85073913378&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073913378&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2019.8759193

DO - 10.1109/ISBI.2019.8759193

M3 - Conference contribution

C2 - 31741704

AN - SCOPUS:85073913378

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 1891

EP - 1895

BT - ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging

PB - IEEE Computer Society

ER -