- This event has passed.
Graduate Seminar Series: Clinical Stream – Nicholas Zhao
March 1, 2023 @ 12:30 pm - 1:00 pm EST
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: Automated Hand Function Assessment from Egocentric Video
Abstract:
Restoration of arm and hand function is reported to be the top priority for rehabilitation by individuals with spinal cord injury (SCI). Clinical hand function assessments such as the Graded Redefined Assessment of Strength Sensibility and Prehension (GRASSP) are methods to evaluate the level of hand function of an individual with SCI, but they must be done in person by a trained clinician. This restriction to an in-person clinical setting limits the accessibility of the assessment, as well as its relevance to daily life. To address these limitations, egocentric video is an emerging method that remotely provides detailed information about upper extremity movements, as well as functional context. Previous works using egocentric video in rehabilitation have focused on detecting quantity of hand use and usage of compensatory grasping postures, using deep computer vision models. However, there have been no studies that assess the quality of hand function from egocentric video. A successful implementation of such a model would allow for automated remote monitoring of rehabilitation progress at home without requiring constant supervision from a clinician.
The objective of this study is to develop a deep learning model capable of predicting clinical hand function assessment scores from egocentric video. To achieve this objective, the following research plan will be enacted: 1. Annotate a dataset with adapted GRASSP scoring. 2. Explore multiple deep learning architectures to determine the best performing model.
Supervisor Name: Jose Zariffa
Year of Study: 2
Program of Study: MASc
Zoom link: https://us02web.zoom.us/j/89610372821?pwd=azd4SCtYVWtreVovaGNPV1c2NGY2Zz09
Meeting ID: 896 1037 2821
Password: 483329
Powered by Calendly.com