Automated Quantification of Eye Tics Using Computer Vision and Deep Learning Techniques
Movement Disorders · 2024-01 · 39 (1) · 183-191
DOI: 10.1002/mds.29593 ↗Kurz gefasst
Fachartikel in der Zeitschrift Movement Disorders, online erschienen am 25.12.2023. Verfasst von Christine Conelea und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychiatry & Behavioral Sciences, University of Minnesota, Minneapolis, Minnesota, USA. Hauptthemen laut MEDLINE: Tics, Deep Learning, Tic Disorders, Tourette Syndrome. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIDA NIH HHS, NIMH NIH HHS, National Science Foundation.
Abstract (Originalsprache)
Background
Tourette syndrome (TS) tics are typically quantified using “paper and pencil” rating scales that are susceptible to factors that adversely impact validity. Video‐based methods to more objectively quantify tics have been developed but are challenged by reliance on human raters and procedures that are resource intensive. Computer vision approaches that automate detection of atypical movements may be useful to apply to tic quantification.
Objective
The current proof‐of‐concept study applied a computer vision approach to train a supervised deep learning algorithm to detect eye tics in video, the most common tic type in patients with TS.
Methods
Videos (N = 54) of 11 adolescent patients with TS were rigorously coded by trained human raters to identify 1.5‐second clips depicting “eye tic events” (N = 1775) and “non‐tic events” (N = 3680). Clips were encoded into three‐dimensional facial landmarks. Supervised deep learning was applied to processed data using random split and disjoint split regimens to simulate model validity under different conditions.
Results
Area under receiver operating characteristic curve was 0.89 for the random split regimen, indicating high accuracy in the algorithm's ability to properly classify eye tic vs. non–eye tic movements. Area under receiver operating characteristic curve was 0.74 for the disjoint split regimen, suggesting that algorithm generalizability is more limited when trained on a small patient sample.
Conclusions
The algorithm was successful in detecting eye tics in unseen validation sets. Automated tic detection from video is a promising approach for tic quantification that may have future utility in TS screening, diagnostics, and treatment outcome measurement. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Psychiatry & Behavioral Sciences, University of Minnesota, Minneapolis, Minnesota, USA.
- Department of Electrical & Computer Engineering, University of Minnesota, Minneapolis, Minnesota, USA.
- Department of Neurology, University of Minnesota, Minneapolis, Minnesota, USA.
- Department of Computer Science & Engineering, University of Minnesota, Minneapolis, Minnesota, USA.
ORCID-Profile: Christine Conelea
Förderung
- NIDA NIH HHS
- NIMH NIH HHS
- National Science Foundation
- National Institute of Mental Health
- National Institute on Drug Abuse
Zitieren
APA
Conelea, C., Liang, H., DuBois, M., Raab, B., Kellman, M., Wellen, B., Jacob, S., Wang, S., Sun, J., & Lim, K. (2024). Automated Quantification of Eye Tics Using Computer Vision and Deep Learning Techniques. Movement Disorders, 39(1), 183-191. https://doi.org/10.1002/mds.29593
Vancouver
Conelea C, Liang H, DuBois M, Raab B, Kellman M, Wellen B, et al. Automated Quantification of Eye Tics Using Computer Vision and Deep Learning Techniques. Movement Disorders. 2024;39(1):183-191. doi:10.1002/mds.29593
BibTeX
@article{Conelea2024,
author = {Conelea, Christine and Liang, Hengyue and DuBois, Megan and Raab, Brittany and Kellman, Mia and Wellen, Brianna and Jacob, Suma and Wang, Sonya and Sun, Ju and Lim, Kelvin},
title = {Automated Quantification of Eye Tics Using Computer Vision and Deep Learning Techniques},
journal = {Movement Disorders},
year = {2024},
volume = {39},
number = {1},
pages = {183--191},
doi = {10.1002/mds.29593}
}
EUVIMED