Related Experiment Video
Updated: Jul 17, 2025
07:38
Generating Acute and Chronic Experimental Models of Motor Tic Expression in Rats
Published on: May 27, 2021
8.0K
Video-based evaluation system for tic action in Tourette syndrome: modeling, detection, and evaluation
Junya Wu1, Tianshu Zhou2, Yufan Guo3
1Key Laboratory for Biomedical Engineering of Ministry of Education, Engineering Research Center of EMR and Intelligent Expert System, Ministry of Education, College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, 310027 China.
Health Information Science and Systems
|August 31, 2023
Summary
This study introduces a novel method for detecting Tourette syndrome (TS) tics using facial video analysis. The approach accurately identifies tic actions, aiding in long-term patient evaluation and diagnosis.
Area of Science:
- Neurology
- Computer Science
- Biomedical Engineering
Background:
- Clinical observations are the standard for Tourette syndrome (TS) assessment.
- Accurate tic symptom detection is crucial for TS diagnosis and treatment evaluation.
- Automated methods can potentially improve the objectivity and efficiency of tic assessment.
Purpose of the Study:
- To develop and evaluate a tic action detection method using facial video feature recognition for Tourette syndrome patients.
- To create a framework for tic action analysis and discrimination using deep learning and anomaly detection.
- To assess the effectiveness of the proposed method for long-term tic symptom monitoring in TS.
Main Methods:
- Facial Region of Interest (ROI) extraction from videos.
- Utilizing a 3D convolutional neural network (CNN) for video feature representation learning.
- Integrating a multi-instance learning anomaly detection strategy for tic action discrimination.
Main Results:
- Achieved an average tic detection accuracy of 91.02%.
- Reported precision of 77.07% and recall of 78.78% for tic detection.
- Demonstrated effective tic action detection in Tourette syndrome patients without requiring fine-grained labeling.
Conclusions:
- The proposed facial video analysis method shows high accuracy in detecting tic actions in Tourette syndrome.
- This approach facilitates objective and potentially continuous monitoring of tic symptoms over time.
- The method holds significance for the long-term evaluation and management of individuals with Tourette syndrome.
