Automated Objective Surgical Skill Assessment in the Operating Room Using Unstructured Tool Motion
This addresses the problem of inefficient learning for surgical trainees in obstructed, unstructured procedures by providing personalized feedback.
The paper tackled automated surgical skill assessment for unstructured nasal septoplasty in the operating room by developing features based on brushing and coverage activities, achieving about 72% accuracy in classifying surgeon training levels.
Previous work on surgical skill assessment using intraoperative tool motion in the operating room (OR) has focused on highly-structured surgical tasks such as cholecystectomy. Further, these methods only considered generic motion metrics such as time and number of movements, which are of limited instructive value. In this paper, we developed and evaluated an automated approach to the surgical skill assessment of nasal septoplasty in the OR. The obstructed field of view and highly unstructured nature of septoplasty precludes trainees from efficiently learning the procedure. We propose a descriptive structure of septoplasty consisting of two types of activity: (1) brushing activity directed away from the septum plane characterizing the consistency of the surgeon's wrist motion and (2) activity along the septal plane characterizing the surgeon's coverage pattern. We derived features related to these two activity types that classify a surgeon's level of training with an average accuracy of about 72%. The features we developed provide surgeons with personalized, actionable feedback regarding their tool motion.