Minimally invasive surgery skills assessment using multiple synchronized sensors

Skills assessment in minimally invasive surgery (MIS) has been a challenge for training centers for long time. The emerging maturity of camera-based systems has the potential to transform solutions to problems in many areas, including MIS. The current assessment methods are mostly subjective or have limitations. In this work, we integrated and coordinated multiple camera sensors to work together to assess the performance of MIS trainees and surgeons. The goal is to develop an objective data-driven assessment that takes advantage of the coordinated sensors. We built and synchronized a network of sensors that can capture large sets of measures from the training environment. The measures are then processed to produce a reliable set of individual and composed coordinated in time metrics that suggest patterns of skills development. The sensors are non-invasive, real-time and coordinated over many cues (eyes, external shots of body and instruments, internal shots of operative field). The platform is validated by a case study of 58 subjects. The results show that the output of the platform has high accuracy and reliability in detecting patterns of skills development and predicting the skill level of the trainees.