Automated Assessment of Simulated Laparoscopic Surgical Performance using 3DCNN

Artificial intelligence & Computer vision have the potential to improve surgical training, especially for minimally invasive surgery by analyzing intraoperative and simulation videos for training or performance improvement purposes. Among these, techniques based on deep learning have rapidly improved, from recognizing objects, instruments, and gestures, to remembering past surgical steps and phases of surgery. However, data scarcity is a problem, particularly in surgery, where complex datasets and human annotation are expensive and time-consuming, and in most cases rely on direct intervention of clinical expertise. Laproscopic surgical assessment of performance traditionally relies on direct observation or video analysis by human experts, a costly and time-consuming undertaking. 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 is given to show similarity and differences between different expertise level (on Stack, Bands, and Tower Skills). Finally, a convolutional neural network is used to predict the experience level of the surgeons, where the model achieved good distinguishing results. The proposed work offers the potential to automate performance assessment and self-learn important features that can discriminate between the performance of novice, trainee, and expert levels.