Related Experiment Video
Updated: Aug 22, 2026
Probing the Brain in Autism Using fMRI and Diffusion Tensor Imaging
Published on: September 12, 2011
AI and neuroimaging in autism spectrum disorder: advances in diagnosis, methodological challenges and future
Kuljeet Singh1, Khushi Mogha2, Sidi Mohamed Sid'El Moctar3,4
1Department of Computer Science, School of Sciences, Christ University, Bengaluru, 560029, India. kuljeetshan94@gmail.com.
Background:
Autism Spectrum Disorder (ASD) is characterized by challenges in social interaction, communication, and restricted or repetitive behaviors, with motor abnormalities increasingly recognized as potential indicators for early identification.
Objective:
This paper presents a comprehensive review of recent advancements in ASD research, with particular emphasis on neuroimaging, artificial intelligence (AI), and machine learning (ML)-based diagnostic approaches. The review examines global and country-specific prevalence trends, current diagnostic methodologies, and existing therapeutic interventions.
Methods:
Through a critical analysis of the literature, including experimental and review studies, key challenges are identified, such as small sample sizes, limited population diversity, heterogeneous imaging protocols, restricted generalizability, and reliance on single-modal datasets. The review further summarizes publicly available ASD datasets and evaluates the strengths and limitations of contemporary AI-driven neuroimaging approaches for ASD diagnosis.
Results:
The contributions of this study include a comprehensive synthesis of neuroimaging and AI-based diagnostic methods, an analysis of available datasets, and a critical evaluation of current methodological challenges and future research directions.
Conclusion:
The findings highlight the growing potential of AI-driven tools for supporting early ASD diagnosis while emphasizing the need for standardized protocols, external validation, explainable AI, and clinically translatable frameworks. Future research should focus on improving dataset diversity, conducting multicenter clinical validation studies, and integrating adaptive learning methodologies to enhance the reliability and applicability of ASD diagnostic systems. This study contributes to the growing body of multidisciplinary research aimed at advancing early diagnosis, personalized intervention, and evidence-based clinical decision support for individuals with ASD.
