ASDeep: Machine-Learning based Video Screening for Detecting Autism Risk in the First Year of Life

Over the last two decades, the average age of first diagnosis of autism spectrum disorder (ASD) in the United States has remained steady, at over 4 years of age, despite an average age of first parental concerns of 14 months and recent progress in understanding manifestations of ASD in infancy. Early intensive intervention has been shown to be highly promising for young children with ASD, including infants and toddlers, but is typically reserved for children with a formal diagnosis, making accurate identification as early as possible imperative. A measure that could identify ASD risk during this period of onset offers the opportunity for intervention before the full set of symptoms is present.

PI Ozonoff and her team have developed a new video-based screening tool, the Video-referenced Infant Rating System for Autism (VIRSA), that utilizes a large library of video clips depicting a wide range of social-communication ability and relies solely on video in the ratings, with no written descriptions of behavior. We hypothesized that the semantic clarity afforded by video would provide improved early discrimination of infants at highest risk for ASD. The VIRSA was able to predict ASD diagnosis with high sensitivity across ages (6-18 months) and demonstrated 100% sensitivity (no false negatives) in concurrently identifying children showing signs of autism at 18 months of age.

Despite the demonstrated success of video-based screening, one major obstacle is the labor-intensive process of labeling and reviewing the videos manually by clinicians. In this proposed collaborative project, we propose to leverage videos from the VIRSA as a training set and apply computer vision and machine learning methods to develop a neural network model for ASD recognition

People

Faculty

  • Sally Ozonoff, Psychiatry & Behavioral Science (Lead Principal Investigator)
  • Samson Cheung, Electrical & Computer Eng., Univ. of Kentucky (Investigator)
  • Chen-Nee Chuah, Electrical & Computer Eng. (Investigator)
  • Gregory S. Young, Psychiatry & Behavioral Science (Investigator)

Students

  • Chongruo Wu, CS, UC Davis (PhD)
  • Dongjie Chen, ECE, UC Davis (PhD)
  • Sidrah Liaqat, ECE, Univ. of Kentucky (PhD)
  • Halil Helvaci, ECE, Univ. of Kentucky (PhD)

Alumni

  • Dev Kashikar, ECE, UC Davis (MS)

Publications & Presentations

  • D. Chen, S-C. Cheung, C-N. Chuah, and S. Ozonoff, "Differentially Private Generative Adversarial Networks with Model Inversion," IEEE Workshop on Information Forensics and Security (WIFS), Dec 7-10, 2021.
  • S. Liaqat, C. Wu, P. R. Duggiarala, S. Cheung, C-N. Chuah, S. Ozonoff, "Predicting ASD Diagnosis in Children with Synthetic and Imaged-based Eye Gaze Data," Elsevier Journal on Signal Processing: Image Communication (SPIC) Special Issue on Saliency for ASD Detection, vol. 94, May 2021, 116198. (DOI: https://doi.org/10.1016/j.image.2021.116198)
  • C. Wu, S. Liaqat, H. Helvaci, S-C. Cheung, C-N. Chuah, S. Ozonoff, and G. Young, "Machine Learning Based Autism Spectrum Disorder Detection from Videos," IEEE International Conference on E-Health Networking, Application & Services (Healthcom), December 2020.
  • C. Wu, S. Liaqat, S. Cheung, C-N. Chuah, and S. Ozonoff, “Predicting Autism Diagnosis Using Image with Fixations and Synthetic Saccade Patterns,” 2019 IEEE International Conference on Multimedia and Expo Workshop(ICMEW), Shanghai, China, pp. 647-650, July 2019, doi: 10.1109/ICMEW.2019.00125.
Abstracts/Posters
  • Sidrah Liaqat, "Predicting ASD Diagnosis in Children with Synthetic and Image-based Eye Gaze Data," 4th Commonwealth Computational Summit, University of Kentucky, October 2020 (First Place in Poster Competition). Also in 5th Annual Neuroscience Clinical Translational Research Symposium.
  • Halil Helvaci, "An Alignment-free and Reference-free Approach for Cell Type Classification with scRNA-seq," 4th Commonwealth Computational Summit, University of Kentucky, October 2929. Also in 5th Annual Neuroscience Clinical Translational Research Symposium.
Thesis
  • Devashish Kashikar, "Diagnosing Autism Spectrum Disorder with Machine Learning," MS Plan I-Thesis, Dec 2019.

Funding

This project is supported by the 2019 Dean’s Collaborative Research award (DECOR) and NIH R01MH121344 grant titled "Novel video-based approaches for detection of autism risk in the first year of life".