Hidden Markov models of minimally invasive surgery

Abstract

A crucial process in surgical education is to evaluate the level of surgical skills. For laparoscopic surgery, skill evaluation is traditionally preformed subjectively by experts grading a video of a procedure performed by a student. By its nature, this process is preformed using fuzzy criteria. The objective of the current study was to develop and assess a skill scale using Discrete Hidden Markov Models (DHMM). Ten surgeons (5 Novice Surgeons--NS; 5 Expert Surgeons--ES) performed a cholecystectomy and Nissen fundoplication in a porcine model. An instrumented laparoscopic grasper equipped with a three-axis force/torque sensor was used to measure the forces/torques at the hand/tool interface synchronized with a video of the tool operative maneuvers. A synthesis of frame-by-frame video analysis and a vector quantization algorithm, defined force/torque signatures for 14 types of tool/tissue interactions. From each step of the surgical procedures, two DHMM were developed representing the performance of 3 surgeons randomly selected from the 5 in the ES and NS groups. The data obtained by the remaining 2 surgeons in each group were used for evaluating the performance scale. The final result was a surgical performance index which represented a ratio of statistical similarity between the examined surgeon's DHMM and the DHMM of NS and ES. The difference between the performance index value, for a surgeon under study, and the NS/ES boundary, was considered to indicate the level of expertise in the surgeon's own group. Using this index, 87.5% of the surgical procedures were correctly classified into the NS and ES groups. The 12.5% of the procedures that were misclassified were preformed by the ES and classified as NS. However, in these cases the performance index values were very close to the NS/ES boundary. Preliminary data suggest that a performance index based on DHMM and force/torque signatures provides an objective means of distinguishing NS from ES. In addition this methodology can be further applied to evaluate haptic virtual reality surgical simulators for improving realism in surgical education.