Graduate Seminar Series: Clinical Stream
Graduate Seminar Series for the Institute of Biomedical Engineering (BME). This day is for clinical stream presenters.
If you would like to invite your Principal Investigator, please add their email via the ‘Add Guest’ button and they will also be notified of your presentation.
Presentation Title: A Novel Automatic Tele-Rehabilitation System Using Vision Technology
Background: Tele-rehabilitation has the potential to considerably change the way patients are monitored from their homes during the care process by providing equitable access without the need to travel to rehab centers or the high cost of personal in-home services. Developing a tele-rehab platform with the capability to automate exercise guidance and support efficient communication with the therapists will have a significant impact on rehabilitation outcomes of aging population. Our goal is to design and validate a biofeedback system to identify the quality of performed exercises and inform the patients to refine their movements to get the most out of their plan of care.
Methods: Various datasets were reviewed and Miron et al. dataset including depth videos was selected. This data was collected from 30 participants performing 9 different rehabilitation exercises. Each exercise was labeled as “Correctly” or “Incorrectly” executed by a clinician. We have used a pre-trained 3D Convolution Neural Network (3D-CNN) to design our biofeedback system.
Results: The proposed biofeedback system achieved an average accuracy of 91.05% and an average F1-Score of 64.20% using Leave-One-Subject-Out cross-validation.
Conclusion: The proposed 3D-CNN was able to classify the rehabilitation videos and feedback on the quality of exercises to the users to help them modify their movement patterns. We are expanding our platform to also extract other features such as the inter-relationships of the various body parts; muscles and their coordination to enable the therapist better to understand the rehab exercises, remotely.
A. Miron, N. Sadawi, W. Ismail, H. Hussain, and C. Grosan, “Intellirehabds (Irds)—a dataset of physical rehabilitation movements,” Data, vol. 6, no. 5, pp. 1–13, 2021, doi: 10.3390/DATA6050046.
Supervisor Name: Dr. Atena Roshan Fekr, Professor Geoff Fernie
Year of Study: 2
Program of Study: MASc
Zoom link: https://us02web.zoom.us/j/89610372821?pwd=azd4SCtYVWtreVovaGNPV1c2NGY2Zz09
Meeting ID: 896 1037 2821
Powered by Calendly.com