Evaluation of Augmentation Methods in Classifying Autism Spectrum Disorders from fMRI Data with 3D Convolutional Neural Networks

Johan Jönemo; David Abramian; Anders Eklund

doi:10.3390/diagnostics13172773

Evaluation of Augmentation Methods in Classifying Autism Spectrum Disorders from fMRI Data with 3D Convolutional Neural Networks

Diagnostics (Basel). 2023 Aug 27;13(17):2773. doi: 10.3390/diagnostics13172773.

Authors

Johan Jönemo^{1

2}, David Abramian^{1

2}, Anders Eklund^{1

2

3}

Affiliations

¹ Division of Medical Informatics, Department of Biomedical Engineering, Linköping University, 581 83 Linköping, Sweden.
² Center for Medical Image Science and Visualization (CMIV), Linköping University, 581 83 Linköping, Sweden.
³ Division of Statistics and Machine Learning, Department of Computer and Information Science, Linköping University, 581 83 Linköping, Sweden.

Abstract

Classifying subjects as healthy or diseased using neuroimaging data has gained a lot of attention during the last 10 years, and recently, different deep learning approaches have been used. Despite this fact, there has not been any investigation regarding how 3D augmentation can help to create larger datasets, required to train deep networks with millions of parameters. In this study, deep learning was applied to derivatives from resting state functional MRI data, to investigate how different 3D augmentation techniques affect the test accuracy. Specifically, resting state derivatives from 1112 subjects in ABIDE (Autism Brain Imaging Data Exchange) preprocessed were used to train a 3D convolutional neural network (CNN) to classify each subject according to presence or absence of autism spectrum disorder. The results show that augmentation only provide minor improvements to the test accuracy.

Keywords: augmentation; autism; deep learning; functional MRI; resting state.

Abstract

Grants and funding