A Framework to Diagnose Autism Spectrum Disorder Using Morphological Connectivity of sMRI and XGBoost

Vaibhavi  Gupta; Gokul  Manoj; Aditi  Bhattacharya; Sandeep Sengar; Rakesh  Mishra; Bhoomika R.  Kar; Chhitij  Srivastava; Jac Fredo Agastinose  Ronickom

doi:10.3233/SHTI230734

A Framework to Diagnose Autism Spectrum Disorder Using Morphological Connectivity of sMRI and XGBoost

Vaibhavi Gupta, Gokul Manoj, Aditi Bhattacharya, Sandeep Sengar, Rakesh Mishra, Bhoomika R. Kar, Chhitij Srivastava, Jac Fredo Agastinose Ronickom

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

In this study, we automated the diagnostic procedure of autism spectrum disorder (ASD) with the help of anatomical alterations found in structural magnetic resonance imaging (sMRI) data of the ASD brain and machine learning tools. Initially, the sMRI data was preprocessed using the FreeSurfer toolbox. Further, the brain regions were segmented into 148 regions of interest using the Destrieux atlas. Features such as volume, thickness, surface area, and mean curvature were extracted for each brain region, and the morphological connectivity was computed using Pearson correlation. These morphological connections were fed to XGBoost for feature reduction and to build the diagnostic model. The results showed an average accuracy of 94.16% for the top 18 features. The frontal and limbic regions contributed more features to the classification model. Our proposed method is thus effective for the classification of ASD and can also be useful for the screening of other similar neurological disorders.

Original language	English
Title of host publication	Telehealth Ecosystems in Practice
Subtitle of host publication	Proceedings of the EFMI Special Topic Conference 2023
Editors	Mauro Giacomini
Publisher	IOS Press
Pages	33 - 37
Volume	309
ISBN (Electronic)	9781643684512
ISBN (Print)	9781643684505
DOIs	https://doi.org/10.3233/SHTI230734
Publication status	Published - 27 Oct 2023
Event	The 2023 European Federation for Medical Informatics (EFMI) Special Topic Conference - University of Genoa, Turin, Italy Duration: 25 Oct 2023 → 27 Oct 2023

Publication series

Name	Studies in Health Technology and Informatics
Publisher	IOS Press
Volume	309
ISSN (Print)	0926-9630
ISSN (Electronic)	1879-8365

Conference

Conference	The 2023 European Federation for Medical Informatics (EFMI) Special Topic Conference
Country/Territory	Italy
City	Turin
Period	25/10/23 → 27/10/23

Access to Document

10.3233/SHTI230734

Cite this

Gupta, V., Manoj, G., Bhattacharya, A., Sengar, S., Mishra, R., Kar, B. R., Srivastava, C., & Ronickom, J. F. A. (2023). A Framework to Diagnose Autism Spectrum Disorder Using Morphological Connectivity of sMRI and XGBoost. In M. Giacomini (Ed.), Telehealth Ecosystems in Practice: Proceedings of the EFMI Special Topic Conference 2023 (Vol. 309, pp. 33 - 37). (Studies in Health Technology and Informatics; Vol. 309). IOS Press. https://doi.org/10.3233/SHTI230734

@inproceedings{d9906c02b441441dbeddccbb0c0a0f2b,

title = "A Framework to Diagnose Autism Spectrum Disorder Using Morphological Connectivity of sMRI and XGBoost",

abstract = "In this study, we automated the diagnostic procedure of autism spectrum disorder (ASD) with the help of anatomical alterations found in structural magnetic resonance imaging (sMRI) data of the ASD brain and machine learning tools. Initially, the sMRI data was preprocessed using the FreeSurfer toolbox. Further, the brain regions were segmented into 148 regions of interest using the Destrieux atlas. Features such as volume, thickness, surface area, and mean curvature were extracted for each brain region, and the morphological connectivity was computed using Pearson correlation. These morphological connections were fed to XGBoost for feature reduction and to build the diagnostic model. The results showed an average accuracy of 94.16% for the top 18 features. The frontal and limbic regions contributed more features to the classification model. Our proposed method is thus effective for the classification of ASD and can also be useful for the screening of other similar neurological disorders.",

author = "Vaibhavi Gupta and Gokul Manoj and Aditi Bhattacharya and Sandeep Sengar and Rakesh Mishra and Kar, {Bhoomika R.} and Chhitij Srivastava and Ronickom, {Jac Fredo Agastinose}",

year = "2023",

month = oct,

day = "27",

doi = "10.3233/SHTI230734",

language = "English",

isbn = "9781643684505",

volume = "309",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press",

pages = "33 -- 37",

editor = "Mauro Giacomini",

booktitle = "Telehealth Ecosystems in Practice",

note = "The 2023 European Federation for Medical Informatics (EFMI) Special Topic Conference ; Conference date: 25-10-2023 Through 27-10-2023",

}

Gupta, V, Manoj, G, Bhattacharya, A, Sengar, S, Mishra, R, Kar, BR, Srivastava, C & Ronickom, JFA 2023, A Framework to Diagnose Autism Spectrum Disorder Using Morphological Connectivity of sMRI and XGBoost. in M Giacomini (ed.), Telehealth Ecosystems in Practice: Proceedings of the EFMI Special Topic Conference 2023. vol. 309, Studies in Health Technology and Informatics, vol. 309, IOS Press, pp. 33 - 37, The 2023 European Federation for Medical Informatics (EFMI) Special Topic Conference, Turin, Italy, 25/10/23. https://doi.org/10.3233/SHTI230734

A Framework to Diagnose Autism Spectrum Disorder Using Morphological Connectivity of sMRI and XGBoost. / Gupta, Vaibhavi ; Manoj, Gokul ; Bhattacharya, Aditi et al.
Telehealth Ecosystems in Practice: Proceedings of the EFMI Special Topic Conference 2023. ed. / Mauro Giacomini. Vol. 309 IOS Press, 2023. p. 33 - 37 (Studies in Health Technology and Informatics; Vol. 309).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Framework to Diagnose Autism Spectrum Disorder Using Morphological Connectivity of sMRI and XGBoost

AU - Gupta, Vaibhavi

AU - Manoj, Gokul

AU - Bhattacharya, Aditi

AU - Sengar, Sandeep

AU - Mishra, Rakesh

AU - Kar, Bhoomika R.

AU - Srivastava, Chhitij

AU - Ronickom, Jac Fredo Agastinose

PY - 2023/10/27

Y1 - 2023/10/27

N2 - In this study, we automated the diagnostic procedure of autism spectrum disorder (ASD) with the help of anatomical alterations found in structural magnetic resonance imaging (sMRI) data of the ASD brain and machine learning tools. Initially, the sMRI data was preprocessed using the FreeSurfer toolbox. Further, the brain regions were segmented into 148 regions of interest using the Destrieux atlas. Features such as volume, thickness, surface area, and mean curvature were extracted for each brain region, and the morphological connectivity was computed using Pearson correlation. These morphological connections were fed to XGBoost for feature reduction and to build the diagnostic model. The results showed an average accuracy of 94.16% for the top 18 features. The frontal and limbic regions contributed more features to the classification model. Our proposed method is thus effective for the classification of ASD and can also be useful for the screening of other similar neurological disorders.

AB - In this study, we automated the diagnostic procedure of autism spectrum disorder (ASD) with the help of anatomical alterations found in structural magnetic resonance imaging (sMRI) data of the ASD brain and machine learning tools. Initially, the sMRI data was preprocessed using the FreeSurfer toolbox. Further, the brain regions were segmented into 148 regions of interest using the Destrieux atlas. Features such as volume, thickness, surface area, and mean curvature were extracted for each brain region, and the morphological connectivity was computed using Pearson correlation. These morphological connections were fed to XGBoost for feature reduction and to build the diagnostic model. The results showed an average accuracy of 94.16% for the top 18 features. The frontal and limbic regions contributed more features to the classification model. Our proposed method is thus effective for the classification of ASD and can also be useful for the screening of other similar neurological disorders.

U2 - 10.3233/SHTI230734

DO - 10.3233/SHTI230734

M3 - Conference contribution

SN - 9781643684505

VL - 309

T3 - Studies in Health Technology and Informatics

SP - 33

EP - 37

BT - Telehealth Ecosystems in Practice

A2 - Giacomini, Mauro

PB - IOS Press

T2 - The 2023 European Federation for Medical Informatics (EFMI) Special Topic Conference

Y2 - 25 October 2023 through 27 October 2023

ER -

Gupta V, Manoj G, Bhattacharya A, Sengar S, Mishra R, Kar BR et al. A Framework to Diagnose Autism Spectrum Disorder Using Morphological Connectivity of sMRI and XGBoost. In Giacomini M, editor, Telehealth Ecosystems in Practice: Proceedings of the EFMI Special Topic Conference 2023. Vol. 309. IOS Press. 2023. p. 33 - 37. (Studies in Health Technology and Informatics). doi: 10.3233/SHTI230734