Automated Assessment of Simulated Laparoscopic Surgical Skill Performance using Deep Learning

Abstract Artificial intelligence (AI) has the potential to improve healthcare and patient safety and is currently being adopted across various fields of medicine and healthcare. AI and in particular computer vision (CV) are well suited to the analysis of minimally invasive surgical simulation videos for training and performance improvement. CV techniques have rapidly improved in recent years from accurately recognizing objects, instruments, and gestures to phases of surgery and more recently to remembering past surgical steps. Lack of labeled data is a particular problem in surgery considering its complexity, as human annotation and manual assessment are both expensive in time and cost, and in most cases rely on direct intervention of clinical expertise. In this work, a newly collected simulated laparoscopic surgical dataset (LSPD) is presented that will initiate the research in automating this problem and avoiding manual expert assessments. LSPD statistical analyses are given to show similarities and differences between different expertise levels (on Stack, Bands, and Tower Skills). In addition, a 3-dimensional convolutional neural network (3DCNN) is used to classify the experience level of the surgeons, novices, and trainees and is found to achieve good results at distinguishing these, with F1 score of 0.91 and AUC of 0.92.