Automated Retained Surgical Item (RSI) detection - BC-421
Preferred Disciplines: Computer Science (Masters)
Project length: 8-12 months (2 units)
Approx. start date: As soon as possible
Location: Vancouver, BC
No. of Positions: 1
Company: Dr. Chris Nguan Inc
Dr Christopher Nguan (Dr. Chris Nguan Inc.) is a Canadian board certified Urologic Surgery Specialist who has sub-specialty training in Advanced Minimally Invasive surgical techniques including daVinci robotic Surgery Systems, as well as Transplantation. He is an Associate Professor at the University of British Columbia – Department of Urological Sciences, Surgical Head of Kidney Transplantation at Vancouver General Hospital and the Director of the Surgical Technologies Experimental Laboratory & Advanced Robotics (STELLAR) facility at VGH.
Dr. Nguan’s research interests are diverse and are categorized into two main divisions: Transplant related research and Medical Technology. The team around Dr. Nguan consists of surgeons, nurses, and engineers who have collaborated for multiple years yielding many publications and awards. Led by a provincial leader in kidney surgery, the team fundamentally understands the problem in regards to the proposed project and has the skills to solve it.
Summary of Project:
BC has more than 200,000 major operations annually. Each one carries the risk of an RSI. Operations in the abdomen and pelvis are identified as higher risk, and if RSI occurs, patients may present with secondary pain, infection, obstruction, hemorrhage, or worse. RSI cause physical, emotional and financial consequences for patients and healthcare systems.
What is the cause of RSI? The workflow in the operating room (OR), no matter how advanced, requires manual counting. Every item in the OR for a procedure is counted by the nurses. This has repeatedly been shown to lack reliability due to 2 factors - misplaced items (59%) and arithmetic error (41%). With technological advances, this is unacceptable for the modern OR.
- Development of a plug-and-play technology to perform automated RSI detection
- Study the current workflow of typical OR and current RSI detection methods (manual/automated)
- Development of an image processing algorithm to track the surgical items
- Development of a “smart” algorithm to calculate the number of items that should be present at the end of the surgery (based on the initial items, type of surgery and items used, etc.)
Expertise and Skills Needed:
- Image processing
- Machine learning
- Software development
For more info or to apply to this applied research position, please