AUTISM SPECTRUM DISORDER PREDICTION IN KIDS USING DEEP LEARNING

Abstract: Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by challenges in social interaction, communication, and behavior. Early and accurate diagnosis is crucial for effective intervention, yet traditional diagnostic methods can be time-consuming and require specialized expertise. Recent advancements in deep learning, particularly convolutional neural networks (CNNs), offer promising avenues for automated and efficient ASD detection.

This study explores the application of CNNs for early ASD detection in children by analyzing data modalities like facial images. For instance, leveraging facial image datasets, models like DenseNet-121 have achieved high accuracy rates, indicating distinctive facial features associated with ASD. Moreover, CNNs applied to neuroimaging data, such as resting-state functional MRI, have demonstrated the ability to identify functional connectivity patterns indicative of ASD. The integration of CNN-based approaches across these diverse data sources underscores the potential of deep learning in facilitating early and accurate ASD diagnosis. By automating the detection process, these methods can augment clinical assessments, leading to timely interventions and improved outcomes for children with ASD.

Keywords: Autism Spectrum Disorder (ASD), Deep Learning, Convolutional Neural Networks (CNNs), Early ASD Detection, Facial Image Analysis, Neuroimaging, DenseNet-121, Medical Image Classification.