Computer Vision Tools for Low-Cost and Noninvasive Measurement of Autism-Related Behaviors in Infants

Abstract

The early detection of developmental disorders is key to child outcome, allowing interventions to be initiated which promote development and improve prognosis. Research on autism spectrum disorder (ASD) suggests that behavioral signs can be observed late in the first year of life. Many of these studies involve extensive frame-by-frame video observation and analysis of a child's natural behavior. Although nonintrusive, these methods are extremely time-intensive and require a high level of observer training; thus, they are burdensome for clinical and large population research purposes. This work is a first milestone in a long-term project on non-invasive early observation of children in order to aid in risk detection and research of neurodevelopmental disorders. We focus on providing low-cost computer vision tools to measure and identify ASD behavioral signs based on components of the Autism Observation Scale for Infants (AOSI). In particular, we develop algorithms to measure responses to general ASD risk assessment tasks and activities outlined by the AOSI which assess visual attention by tracking facial features. We show results, including comparisons with expert and nonexpert clinicians, which demonstrate that the proposed computer vision tools can capture critical behavioral observations and potentially augment the clinician's behavioral observations obtained from real in-clinic assessments.

A scalable app for measuring autism risk behaviors in young children: A technical validity and feasibility study

“…Currently, identification of children with neurodevelopmental disorders in early childhood requires low specificity screening with questionnaires followed by time-consuming observational assessments by highly-trained clinicians. Even in the field of autism, where progress has been made in developing new technologies for measuring risk for the disorder, there is not yet a low-cost and scalable way to directly observe children and characterize their development automatically and on a ubiquitous mobile device [9,19]. There is a need for novel, scalable tools to measure social communication and affective behaviors and to use such measures to identify children who are at risk for neurodevelopmental disorders in a manner that can be disseminated to primary care clinics, schools, or homes.…”

A Six‐Minute Measure of Vocalizations in Toddlers with Autism Spectrum Disorder

“…The development of automated, scalable screening tools that directly assess behavior are needed. To that end, previous studies [Bovery et al, 2018;Campbell et al, 2019;Dawson & Sapiro, 2019;Hashemi et al, 2014Hashemi et al, , 2018 have evaluated a tablet-based application (app) that uses dynamic stimuli designed to elicit and measure symptoms associated with ASD. This scalable app can be administered during well-child visits in the primary care setting (and parallel efforts indicate that it is also possible to administer at home [Egger et al, 2018]).…”

Uma contribuição ao auxíılio do diagnóstico do autismo a partir do processamento de imagens para extração de medidas antropométricas

“…Usando a computação no auxílio ao diagnóstico do autismo, [5] desenvolveram um programa de visão computacional que analisa quadros de vídeos de crianças em testes comportamentais. Esses testes servem para detectar transtornos de comportamento, o que pode melhorar a exatidão do diagnóstico.…”

“…Algumas iniciativas têm utilizado a tecnologia para auxiliar o diagnóstico, como [5], que desenvolveram um software de processamento de imagens e visão computacional para aumentar a exatidão na triagem de crianças submetidas ao diagnóstico de autismo a partir da análise de vídeos de testes comportamentais. Recentemente, alguns pesquisadores têm concentrado esforços na verificação da relação do autismo com a Antropometria, queé a "ciência que estuda as medidas de tamanho, peso e proporções do corpo humano a partir de medições de uma população estudada" [6].…”