Autism auxiliary evaluation system and method based on deep learning

Abstract

The invention provides an autism auxiliary evaluation system and method based on deep learning. The system comprises a data acquisition and feature extraction unit, a first neural network, a second neural network, a third neural network and a result output unit; the data acquisition and feature extraction unit and the result output unit are respectively connected with the first neural network, the second neural network and the third neural network, wherein the data acquisition and feature extraction unit is used for acquiring eye movement data of a subject watching a video to obtain a hotspot map, a focus map and a scanning path map; the first neural network inputs the hotspot map to obtain a first classification result; the second neural network inputs the focus image to obtain a second classification result; the third neural network inputs the scanning path map to obtain a third classification result; and the result output unit gathers the first classification result, the second classification result and the third classification result to obtain an autism detection result of the subject. According to the invention, the autism prediction efficiency and the autism prediction accuracy are improved.

Description

technical field [0001] The present invention relates to the technical field of autism assessment, in particular to a deep learning-based auxiliary assessment system and method for autism. Background technique [0002] Autism spectrum disorder (ASD), or "autism spectrum disorder", "autism", "autism" is a heterogeneous neurodevelopmental disorder with social impairment and stereotyped behavior as the core obstacle. The incidence of ASD children is increasing year by year worldwide, and it has become a social public health problem. Autism affects 1 in 68 people in the United States, according to the Autism and Developmental Disabilities Surveillance Network under the Centers for Disease Control and Prevention, so attention to ASD has risen dramatically over the past few years. Rehabilitation training is the main treatment for children with ASD, and more and more examples show that the earlier the intervention, the better the prognosis. Through the early diagnosis and interven...

AI Technical Summary

Problems solved by technology

[0006] In short, the existing technical solutions mainly have the following problems: 1), the stimulus materials based on eye movement are too typical and out of touch with real life scenes

In the current scheme based on eye movement-assisted diagnosis, the stimulus materials provided are all static pictures, which are out of touch with real life scenes, and cannot truly evaluate the emotion recognition ability of ASD children in real social interaction

2), not suitable for auxiliary diagnosis of children aged 6-18 months

Most of the current autism spectrum disorder scales have age ranges. For autistic patients, there are often problems with difficult questions or ages that are not within the scope of the scale.

Moreover, for younger children, it is impossible to conduct questionnaire surveys and interviews. They can only rely on the daily observations of their parents and elders, as well as doctor's interviews and behavioral checks for diagnosis, which may easily lead to missed diagnosis and misdiagnosis.

The current method of using glasses-type eye trackers to obtain eye movement data, using multimodal data such as EEG for data collection, and using facial expression responses is too difficult for children aged 6-18 months

3), need tedious manual feature extraction work

Images