Benjamín Béjar Haro receives 2012 MICCAI Best Paper Award
January 8, 2013
Benjamín Béjar, graduate student in the Center for Imaging Science (CIS) and the Department of Biomedical Engineering (BME) at JHU, received the 2012 Best Paper Award in Medical Robotics and Computer Assisted Intervention Systems from the Medical Image Computing and Computer Assisted Intervention Society (“MICCAI”) for his paper entitled “Surgical Gesture Classification from Video Data.” The paper is co-authored with Dr. Luca Zappella, Postdoctoral Fellow in CIS, and Dr. René Vidal, Associate Professor in CIS and BME. This work is part of the Language of Surgery project at JHU, led by Dr. Gregory Hager, Professor and Chairman in the Department of Computer Science, whose goal is to develop methods for modeling surgical tasks and using these models to evaluate the skill level of a surgeon and improve the way in which they are trained. Much of the existing work on automatic classification of gestures and skill in robotic surgery is based on kinematic and dynamic cues, such as time to completion, speed, forces, torque, or robot trajectories.
In this paper, the authors show that in a typical surgical training setup, video data can be equally discriminative. In particular, the authors develop computer vision and machine learning methods for decomposing a video of a surgical task (e.g., suturing, knot tying) into surgical gestures (e.g., grabbing the needle, inserting the needle), and show how this decomposition can be used to determine how well a gesture is executed.