Neuroimaging genetics approaches to identify new biomarkers for the early diagnosis of autism spectrum disorder

Abstract

Autism-spectrum disorders (ASDs) are developmental disabilities that manifest in early childhood and are characterized by qualitative abnormalities in social behaviors, communication skills, and restrictive or repetitive behaviors. To explore the neurobiological mechanisms in ASD, extensive research has been done to identify potential diagnostic biomarkers through a neuroimaging genetics approach. Neuroimaging genetics helps to identify ASD-risk genes that contribute to structural and functional variations in brain circuitry and validate biological changes by elucidating the mechanisms and pathways that confer genetic risk. Integrating artificial intelligence models with neuroimaging data lays the groundwork for accurate diagnosis and facilitates the identification of early diagnostic biomarkers for ASD. This review discusses the significance of neuroimaging genetics approaches to gaining a better understanding of the perturbed neurochemical system and molecular pathways in ASD and how these approaches can detect structural, functional, and metabolic changes and lead to the discovery of novel biomarkers for the early diagnosis of ASD.

Fig. 1. Genes associated with brain metabolism in autism-spectrum disorder (ASD) and other neurological disorders.

Risk genes for various neurological disorders and ASD-related genes that affect brain metabolism can be detected by using neuroimaging techniques, such as positron emission tomography (PET), magnetic resonance imaging (MRI), and magnetic resonance spectroscopy (MRS).

Fig. 2. Neuroimaging techniques to detect serotonergic, dopaminergic, GABAergic, and glutamatergic abnormalities in autism-spectrum disorder (ASD).

ASD-associated mutations in serotonin and dopamine transporters and in GABA and glutamate receptors can be detected by using various positron emission tomography (PET) probes and magnetic resonance (MR) techniques.

Fig. 3. Machine-learning (ML) approaches for early diagnosis and better evaluation of autism-spectrum disorder (ASD).

ML methods or techniques can be applied to ASD raw data obtained from genomics and neuroimaging approaches. ML uses supervised and unsupervised learning methods to classify and distinguish clusters in ASD. Deep-learning techniques, such as deep neural network (DNN) and convolutional neural network (CNN), can be applied to diagnose ASD.