A Summative Assessment of the Pattern-Cutting Task in Laparoscopic Box Trainer using Color Tracking and Fuzzy Logic

In Minimally Invasive Surgery (MIS), surgeons should acquire many skills before carrying out a real operation. The Fundamentals of Laparoscopic Surgery (FLS) tasks are currently used as an assessment tool for laparoscopic skills. However, the current training methods still require the presence of an expert surgeon to assess the surgical dexterity of the trainee. This process is time-consuming and may lead to subjective assessment. This research aims to extend the application of image processing and analysis methods to detect and track the tips of the laparoscopic instruments and to localize the circle center to calculate the distance between the scissors' tips and the circle's center in each processed frame. The data obtained will feed the fuzzy system to assess the trainer's performance with a processing speed of 4 frames per second. The proposed system can provide a final text report that lists an error counter value and the fuzzy assessment at each time slot of 0.29 s on average. Additionally, a BMP image that summarizes the tips of the scissors within the predefined circles during the test is created. Finally, a Canny edge detector is applied to detect whether any circle line was cut during the test. This work enables a summative assessment of the precision-cutting task without altering the original setup of the FLS box trainer. Additionally, this can expedite the development of surgery skills and assess the trainees' performance using a single-input-single-output fuzzy logic system. The output of the fuzzy logic assessment is the performance evaluation for the surgeon, and it is quantified in percentages.