

The analogy between Minimally Invasive Surgery (MIS) and the human language inspires the decomposition of a surgical task into its primary elements. The frequency of different elements or words” and their sequential associations or “grammar” both hold critical information about the process and outcome of the procedure. Modeling these sequential element expressions using a multi finite states model (Markov model) reveals the grammatical structure of the surgical task and is utilized as one of the key steps in objectively assessing surgical performance. The experimental protocol included 30 surgeons at different levels of training (5×Rl,R2,R3,R4,R5, and experts) performing Laparoscopic suturing on an animal model (pig). The kinematics and dynamics of left and right endoscopic tools along with the visual view of the surgical scene were acquired by the Blue DRAGON system. The methodology of decomposing the surgical task is based on a fully connected, finite-states (30 states) Markov model (MM) where the left and right hands are represented by 15 states each. In addition to the MM objective analysis, a scoring protocol was used by an expert surgeon to subjectively assess the subjects’ technical performance. An objective learning curve was defined based on measuring quantitative statistical distance (similarity) between MM of experts and MM of residents at different levels of training. The objective learning curve (e.g. statistical distance between MM) was similar to that of the subjective performance analysis. The MM proved to be a powerful and compact mathematical model for decomposing a complex task such as laparoscopic suturing. Systems like surgical robots or virtual reality simulators that inherently measure the kinematics and dynamics of the surgical tool may benefit from inclusion of the proposed methodology for analysis of efficacy and objective evaluation of surgical skills during training.