The advent of computer-integrated surgery (CIS) technologies has renewed interest in improving the current learning and evaluation paradigms for surgeons. The ability of CIS systems to record quantitative motion and video data of the surgical workspace opens up the possibility of creating descriptive mathematical models to represent and analyze surgical training and performance. These models can then form the basis for evaluating and training surgeons, producing quantitative measures of surgical proficiency, automatically annotating surgical recordings, and providing data for a variety of other applications in medical informatics.
In developing mathematical models to recognize and evaluate surgical dexterity, we must first investigate the underlying structure in surgical motion. We hypothesize that motion during a surgery is not a random set of gestures but a deliberate sequence of gestures, each with its own surgical intent. In this talk, I present highlights in our investigation of the existence of structure in surgical motion. During our research, we made no assumptions about the construct of the structure. We borrowed techniques and ideas from computer vision, image processing, speech processing, language theory, machine learning and statistical analysis to help in our investigation. Our focus was on the analyses of fundamental surgical tasks, such as suturing, knot tying and needle hoop passing, across varying surgical skill levels.