ABSTRACT
Autism spectrum disorder (ASD) is a lifelong developmental disorder characterized by repetitive, restricted behavior and deficits in communication and social interactions. Early diagnosis and intervention can significantly reduce the hazards of the disease. However, the lack of effective clinical resources for early diagnosis has been a long-standing problem. In response to this problem, we apply the recent advances in deep neural networks on eye-tracking data in this study to classify children with and without ASD. First, we record the eye movement data of 31 children with ASD and 43 typically developing children on four categories of stimuli to construct an eye-tracking data set for ASD identification. Based on the collected eye movement data, we extract the dynamic saccadic scanpath on each image for all subjects. Then, we utilize the hierarchical features learned from a convolutional neural network and multidimensional visual salient features to encode the scanpaths. Next, we adopt the support vector machine to learn the relationship between encoded pieces of scanpaths and the labels from the two classes via supervised learning. Finally, we derive the scores of each scanpath and make the final judgment for each subject according to the scores on all scanpaths. The experimental results have shown that the proposed model has a maximum classification accuracy of 94.28% in the diagnostic tests. Based on existing research and calculation models, dynamic saccadic scanpaths can provide promising findings and implications for ASD early detection. Furthermore, integrating more information of the scanpaths into the model and developing a more in-depth description of scanpaths can improve the recognition accuracy. We hope our work can contribute to the development of multimodal approaches in the early detection and diagnosis of ASD.
- S. Wang, M. Jiang, X. M. Duchesne, E. A. Laugeson, D. P. Kennedy, R. Adolphs, and Q. Zhao. 2015. Atypical visual saliency in autism spectrum disorder quantified through model-based eye tracking. Neuron, 88, 3 (Nov. 2015), 604-615. DOI=10.1016/j.neuron.2015.09.042.Google ScholarCross Ref
- M. J. Maenner, K. A. Shaw, J. Baio, D. Bilder, A. Washington, M. Patrick, M. DiRienzo, D. L. Christensen, L. D. Wiggins, S. Pettygrove 2020. Prevalence and characteristics of autism spectrum disorder among children aged 8 years autism and developmental disabilities monitoring network, 11 sites, united states, 2016. Surveillance Summaries. (Mar. 2020), 1-23. DOI=10.15585/mmwr.ss6904a1.Google Scholar
- N. I. Vargas-Cuentas, A. Roman-Gonzalez, R. H. Gilman, F. Barrientos, J. Ting, D. Hidalgo, K. Jensen, and M. Zimic. 2017. Developing an eye tracking algorithm as a potential tool for early diagnosis of autism spectrum disorder in children. PloS one, 12, 11 (Nov. 2017), 1-13. DOI=10.1371/journal.pone.0188826.Google Scholar
- C. Lord, T. S. Brugha, T. Charman, J. Cusack, G. Dumas, T. Frazier 2020. Autism spectrum disorder. Nature Reviews Disease Primers, 6, 1, (Jan. 2020), 1-23. DOI= 10.1038/s41572-019-0138-4.Google Scholar
- M. Jiang and Q. Zhao. 2017. Learning visual attention to identify people with autism spectrum disorder. In Proc. 16th IEEE Int. Conf. Comput. Vis., (Venice, Italy, Oct. 22-29, 2017). IEEE, 1-10. DOI=10.1109/ICCV.2017.354.Google Scholar
- W. Liu, M. Li, and L. Yi. 2016. Identifying children with autism spectrum disorder based on their face processing abnormality: A machine learning framework. Autism Research, 9 (Jan. 2016), 888-898. DOI=10.1002/aur.1615.Google Scholar
- K. Pierce, S. Marinero, R. Hazin, B. McKenna, C. C. Barnes, and A. Malige. 2016. Eye tracking reveals abnormal visual preference for geometric images as an early biomarker of an autism spectrum disorder subtype associated with increased symptom severity. Biological Psychiatry, 79, 8, (Jun. 2016), 657-666. DOI=10.1016/j.biopsych.2015.03.032.Google ScholarCross Ref
- W. Jones and A. Klin. 2013. Attention to eyes is present but in decline in 2-6-month-old infants later diagnosed with autism. Nature, 504, 7480, (Dec. 2013), 427-431. DOI=10.1038/nature12715.Google ScholarCross Ref
- Y. He, Q. Su, L. Wang, W. He, C. Tan, H. Zhang, M. L. Ng, Y. Chen, and N. Yan. 2019. The characteristics of intelligence profile and eye gaze in facial emotion recognition in mild and moderate preschoolers with autism spectrum disorder. Frontiers in psychiatry, 10, 402, (Jun. 2019), 101-109. DOI=10.3389/fpsyt.2019.00402.Google Scholar
- M. Elsabbagh, J. Fernandes, S. J. Webb, G. Dawson, T. Charman, and M. H. Johnson. 2013. Disengagement of visual attention in infancy is associated with emerging autism in toddlerhood. Biological Psychiatry, 74, 3, (Aug. 2013), 189-194. DOI=10.1016/j.biopsych.2012.11.030.Google ScholarCross Ref
- T. W. Frazier, E. W. Klingemier, M. Beukemann, L. Speer, L. Markowitz, S. Parikh, S. Wexberg, K. Giuliano, E. Schulte, C. Delahunty 2016. Development of an objective autism risk index using remote eye tracking. Journal of the American Academy of Child & Adolescent Psychiatry, 55, 4, (Apr. 2016), 301-309. DOI=10.1016/j.jaac.2016.01.011.Google Scholar
- M. Murias, S. Major, K. Davlantis, L. Franz, A. Harris, B. Rardin, M. Sabatos-DeVito, and G. Dawson. 2018. Validation of eye-tracking measures of social attention as a potential biomarker for autism clinical trials. Autism Research, 11, 1, (Jan. 2018), 166–174. DOI=10.1002/aur.1894.Google Scholar
- N. Liu, J. Han, T. Liu, and X. Li, 2018. Learning to predict eye fixations via multiresolution convolutional neural networks. IEEE Trans. Neural Netw. Learn. Syst., 29, 2, (Feb. 2018), 392-404. DOI=10.1109/TNNLS.2016.2628878.Google Scholar
- T. Judd, K. Ehinger, F. Durand, and A. Torralba. 2009. Learning to predict where humans look. In Proc. 16th IEEE Int. Conf. Comput. Vis., (Kyoto, Japan, Sep. 29-Oct. 2, 2009). IEEE, 2106-2113. DOI=10.1109/ICCV.2009.5459462.Google Scholar
- L. Itti, C. Koch, and E. Niebur, 1998. A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20, 11, (Nov. 1998), 1254-1259. DOI=10.1109/34.730558.Google ScholarDigital Library
- T. Falkmer, K. Anderson, M. Falkmer, and C. Horlin. 2013. Diagnostic procedures in autism spectrum disorders: a systematic literature review. European Child and Adolescent Psychiatry, 22, 6, (Jun. 2013), 329-340. DOI= 10.1007/s00787-013-0375-0.Google ScholarCross Ref
Recommendations
A Tactile Robot for Developmental Disorder Therapy
TechMindSociety '18: Proceedings of the Technology, Mind, and SocietyDevelopmental disorders, such as Attention-Deficit-- Hyperactivity Disorder (ADHD) and Autism Spectrum Disorder (ASD), have clinical symptoms of inattention, hyperactivity, and impulsivity. These symptoms are often accompanied by tactile and ...
Machine learning based on eye-tracking data to identify Autism Spectrum Disorder: A systematic review and meta-analysis
Graphical abstractDisplay Omitted
Highlights- Machine learning with eye-tracking has performed with high accuracy to identify ASD.
- A high degree of heterogeneity was found among included studies.
- Methodological drawbacks might deteriorate the reliability of reported results.
Abstract BackgroundMachine learning has been widely used to identify Autism Spectrum Disorder (ASD) based on eye-tracking, but its accuracy is uncertain. We aimed to summarize the available evidence on the performances of machine learning algorithms in ...
Interactive Robot-Aided Diagnosis System for Children with Autism Spectrum Disorder
HCI in Business, Government and OrganizationsAbstractAutism spectrum disorder (ASD) is a group of complex neurodevelopmental disorders characterized by difficulties with social communication and interaction as well as restrictive interest and stereotyped behavior. Despite the behavioral symptoms of ...
Comments