Examining the Impact of fMRI Preprocessing Steps on Machine Learning-Based Classification of Autism Spectrum Disorder

Roberto C Sotero, Jose M Sanchez-Bornot, Iman Shaharabi-Farahani, Yasser Iturria-Medina

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

The use of functional magnetic resonance imaging (fMRI) data in machine learning (ML)-based classification of autism spectrum disorder (ASD) has been a topic of increasing research interest in past years due to the noninvasiveness of the fMRI technique and its potential for providing valuable biomarkers. However, there are still controversies surrounding some fMRI data preprocessing steps, such as bandpass filtering and global signal regression (GSR). It still needs to be determined whether or how these preprocessing steps impact the classification accuracy of ML algorithms. This paper uses fMRI signals from the ABIDE-I dataset to train a long short-term memory (LSTM) network to classify subjects into ASD or healthy controls (HC). We considered 18 preprocessing pipelines comprising all combinations of with and without filtering, with and without global signal regression, and three different segment lengths of 1 min, 2 min, and 3 min. The best model was obtained when using a segment length of 2 min. Our results suggest that not filtering produces significantly higher classification accuracies than filtering, whereas there were no significant differences in classification accuracies when removing or not the global signal.
Original languageEnglish
Title of host publicationICMHI 2023 - 2023 the 7th International Conference on Medical and Health Informatics
PublisherAssociation for Computing Machinery
Pages19-24
Number of pages6
ISBN (Electronic)9798400700712
ISBN (Print)979-8-4007-0071-2
DOIs
Publication statusPublished (in print/issue) - 18 Oct 2023
Event7th International Conference on Medical and Health Informatics - Kyoto, Japan
Duration: 12 May 202314 May 2023
Conference number: 2023
https://dl.acm.org/conference/icmhi

Publication series

NameACM International Conference Proceeding Series

Conference

Conference7th International Conference on Medical and Health Informatics
Abbreviated titleICMHI
Country/TerritoryJapan
CityKyoto
Period12/05/2314/05/23
Internet address

Bibliographical note

Funding Information:
This work was supported by the Alberta Innovates LevMax program, Grant 222300868.

Publisher Copyright:
© 2023 ACM.

Keywords

  • Machine learning
  • fMRI preprocessing
  • Autism Spectrum Disorder
  • Classification

Fingerprint

Dive into the research topics of 'Examining the Impact of fMRI Preprocessing Steps on Machine Learning-Based Classification of Autism Spectrum Disorder'. Together they form a unique fingerprint.

Cite this