[Health simulation, access to somatic care for people with ASD]

The clinical characteristics of people with autism spectrum disorders can make it difficult for them to access care, including treatment and medical imaging examinations. Simulation-based learning can facilitate the performance of a CT scan, as in the case of Irène, who was able to adopt the expected body positions thanks to this intervention.

Computer-Aided Screening of Autism Spectrum Disorder: Eye-Tracking Study Using Data Visualization and Deep Learning

Background

The early diagnosis of autism spectrum disorder (ASD) is highly desirable but remains a challenging task, which requires a set of cognitive tests and hours of clinical examinations. In addition, variations of such symptoms exist, which can make the identification of ASD even more difficult. Although diagnosis tests are largely developed by experts, they are still subject to human bias. In this respect, computer-assisted technologies can play a key role in supporting the screening process.

Objective

This paper follows on the path of using eye tracking as an integrated part of screening assessment in ASD based on the characteristic elements of the eye gaze. This study adds to the mounting efforts in using eye tracking technology to support the process of ASD screening

Methods

The proposed approach basically aims to integrate eye tracking with visualization and machine learning. A group of 59 school-aged participants took part in the study. The participants were invited to watch a set of age-appropriate photographs and videos related to social cognition. Initially, eye-tracking scanpaths were transformed into a visual representation as a set of images. Subsequently, a convolutional neural network was trained to perform the image classification task.

Results

The experimental results demonstrated that the visual representation could simplify the diagnostic task and also attained high accuracy. Specifically, the convolutional neural network model could achieve a promising classification accuracy. This largely suggests that visualizations could successfully encode the information of gaze motion and its underlying dynamics. Further, we explored possible correlations between the autism severity and the dynamics of eye movement based on the maximal information coefficient. The findings primarily show that the combination of eye tracking, visualization, and machine learning have strong potential in developing an objective tool to assist in the screening of ASD.

Conclusions

Broadly speaking, the approach we propose could be transferable to screening for other disorders, particularly neurodevelopmental disorders.

Variational Autoencoder for Image-Based Augmentation of Eye-Tracking Data

Over the past decade, deep learning has achieved unprecedented successes in a diversity of application domains, given large-scale datasets. However, particular domains, such as healthcare, inherently suffer from data paucity and imbalance. Moreover, datasets could be largely inaccessible due to privacy concerns, or lack of data-sharing incentives. Such challenges have attached significance to the application of generative modeling and data augmentation in that domain. In this context, this study explores a machine learning-based approach for generating synthetic eye-tracking data. We explore a novel application of variational autoencoders (VAEs) in this regard. More specifically, a VAE model is trained to generate an image-based representation of the eye-tracking output, so-called scanpaths. Overall, our results validate that the VAE model could generate a plausible output from a limited dataset. Finally, it is empirically demonstrated that such approach could be employed as a mechanism for data augmentation to improve the performance in classification tasks.

Learning Clusters in Autism Spectrum Disorder: Image-Based Clustering of Eye-Tracking Scanpaths with Deep Autoencoder

Autism spectrum disorder (ASD) is a lifelong condition characterized by social and communication impairments. This study attempts to apply unsupervised Machine Learning to discover clusters in ASD. The key idea is to learn clusters based on the visual representation of eye-tracking scanpaths. The clustering model was trained using compressed representations learned by a deep autoencoder. Our experimental results demonstrate a promising tendency of clustering structure. Further, the clusters are explored to provide interesting insights into the characteristics of the gaze behavior involved in autism.

Initiation and response of joint attention bids in autism spectrum disorder children depend on the visibility of the target

BACKGROUND AND AIMS

Response to joint attention (RJA) and initiation of joint attention (IJA) are impaired in pre-schoolers with autism spectrum disorder (ASD). Children's response to joint attention may depend on the presence of the target in the child's field of vision or on the type of deictic index (head and eye orientation, pointing and verbalisations) used by the adult to initiate joint attention.

METHODS

This study deals with 50 ASD children aged from 2 years 8 months to 11 years 7 months, with a communicative level comparable to children under 31 months of age, according to the French version of the Early Social Communication Scales (ECSP, by its French acronym). We compared the aforementioned ASD children with 50 typically developing (TD) children, aged 9 to 30 months who had no communication disorders according to the ECSP. During the ECSP test, we analysed joint attention behaviours on three posters present or absent from the children's visual field.

RESULTS

We did not observe any difference in the number of IJAs between groups, but ASD children were less responsive than TD children were. Our results showed a developmental progression in the responses of children with ASD if several deictic cues were used by an adult simultaneously (looking and pointing, or looking and verbalising to indicate a target), whether the referent was present or absent from the child's visual field. In addition, we observed developmental progression when the referent was behind the child and the adult only used their gaze to refer to it.

CONCLUSION

Thus, we argue that the type of cues used affects ASD children's response behaviours during joint attention towards a referent that may be present or absent from their visual field.Implications: Regarding the social and the sensory difficulties of children with ASD, many therapeutic approaches focus their intervention methods on non-verbal communication skills and joint attention. This fundamental research makes it possible to identify the most appropriate type of deictic index for children with ASD with developmental delay, depending on the presence or absence of the referent in the child's visual field.

Visual Exploration of Dynamic or Static Joint Attention Bids in Children With Autism Syndrome Disorder

Eye-tracking studies have revealed a specific visual exploration style characterizing individuals with autism spectrum disorder (ASD). The aim of this study is to investigate the impact of stimulus type (static vs. dynamic) on visual exploration in children with ASD. Twenty-eight children with ASD, 28 children matched for developmental communication age, and 28 children matched for chronological age watched a video and a series of photos involving the same joint attention scene. For each stimulus, areas of interest (AOI) were determined based on Voronoi diagrams, which were defined around participants' fixation densities, defined by the mean shift algorithm. To analyze the eye-tracking data on visual exploration, we used a method for creating AOI a posteriori, based on participants' actual fixations. The results showed the value of both kinds of stimuli. The photos allowed for the identification of more precise AOI and showed similarities in exploration between ASD and typical children. On the other hand, video revealed that, among ASD children only, there are few differences in the way they look at the target depending on the deictic cue used. This raises questions regarding their understanding of a joint attention bid recorded on a video. Finally, whatever the stimulus, pointing seems to be the most important element for children looking at the target.