Surgical errors result in thousands of injuries and deaths each year, which can however be prevented with appropriate training and skill assessment methods. Surgical skill evaluation today is predominantly based on manual evaluations by expert surgeons---which is time-consuming, non-uniform, and cumbersome to work into the natural flow of training or testing events.
This project develops algorithms to automatically determine surgical procedural steps and errors from image data during surgeon training . The procedural step and error assessment can be used for post-hoc evaluations or even as live feedback during training.
In collaboration with Katherine Barsness, MD, Northwestern University and Lurie Children's Hospital of Chicago.
© argallab 2016