Machine learning for autism spectrum disorder diagnosis using structural magnetic resonance imaging: Promising but challenging

Abstract

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder that affects approximately 1% of the population and causes significant burdens. ASD's pathogenesis remains elusive; hence, diagnosis is based on a constellation of behaviors. Structural magnetic resonance imaging (sMRI) studies have shown several abnormalities in volumetric and geometric features of the autistic brain. However, inconsistent findings prevented most contributions from being translated into clinical practice. Establishing reliable biomarkers for ASD using sMRI is crucial for the correct diagnosis and treatment. In recent years, machine learning (ML) and specifically deep learning (DL) have quickly extended to almost every sector, notably in disease diagnosis. Thus, this has led to a shift and improvement in ASD diagnostic methods, fulfilling most clinical diagnostic requirements. However, ASD discovery remains difficult. This review examines the ML-based ASD diagnosis literature over the past 5 years. A literature-based taxonomy of the research landscape has been mapped, and the major aspects of this topic have been covered. First, we provide an overview of ML's general classification pipeline and the features of sMRI. Next, representative studies are highlighted and discussed in detail with respect to methods, and biomarkers. Finally, we highlight many common challenges and make recommendations for future directions. In short, the limited sample size was the main obstacle; Thus, comprehensive data sets and rigorous methods are necessary to check the generalizability of the results. ML technologies are expected to advance significantly in the coming years, contributing to the diagnosis of ASD and helping clinicians soon.

Keywords: autism spectrum disorder (ASD); biomarkers; deep learning; machine learning; structural magnetic resonance imaging (sMRI).

FIGURE 1

A literature-based taxonomy for ML-based ASD classification.

FIGURE 2

Different MRI modalities.

FIGURE 3

(A) Branches of Artificial Intelligence Science. (B) An artificial neuron’s architecture. Each input × is associated with a weight w. The sum of all weighted inputs is passed onto an activation function f that leads to an output.

FIGURE 4

Differences between (A) ML-based studies workflow and (B) DL-based studies workflow.

FIGURE 5

The components of typical DL-based methods for diagnosing ASD (Khodatars et al., 2021).

FIGURE 6

Schemes of conventional ML algorithms commonly used in MRI-based studies to diagnose ASD (A) SVM: support vector machine; (B) RF: random forest; (C) DT: decision tree; (D) KNN: k nearest neighbor.

FIGURE 7

Schemes of DL algorithms are commonly used in MRI-based studies to diagnose ASD. (A) AE: autoencoder; (B) Stacked Autoencoder; (C) CNN: convolutional neural network.

FIGURE 8

Publication by year. (A) Shows a rise in the number of papers published in the ASD diagnosis area from 2017 onward, according to the “PubMed by year”; (B) represents the number of papers published, reviewed here, by year.

FIGURE 9

Reviewed studies analysis. (A) Shows a variety of ML and DL approaches used to diagnose ASD. (B) Shows a different set of CV techniques. (C) Shows the data sets used in the studies and their number. (D) Shows the imaging modality used to build the models.

FIGURE 10

Shows relationships between the sample size and the accuracy of the studies.