Pupillometry in telerobotic surgery: A comparative evaluation of algorithms for cognitive effort estimation

Abstract

Background: Eye gaze tracking and pupillometry are emerging topics in telerobotic surgery as it is believed that they will enable novel gaze-based interaction paradigms and provide insights into the user’s cognitive load (CL). Further, the successful integration of CL estimation into telerobotic systems is thought to catalyze the development of new human-computer interfaces for personalized assistance and training processes. However, this field is in its infancy, and identifying reliable gaze and pupil-tracking solutions in robotic surgery is still an area of ongoing research and high uncertainty. Methods: Considering the potential benefits of pupillometry-based CL assessments in telerobotic surgery, we seek to better understand the possibilities and limitations of contemporary pupillometry-based cognitive effort estimation algorithms in telerobotic surgery. To this end, we conducted a user study using the da Vinci Research Kit (dVRK) and performed two experiments where participants were asked to perform a series of N-Back tests, either while (i) idling or (ii) performing a peg transfer task. We then compare four contemporary CL estimation methods based on direct analysis of pupil diameter in the spatial and frequency domains. Results: We find that some methods can detect the presence of cognitive effort in simple scenarios (e.g., when the user is not performing any manual task), they fail to differentiate the different levels of CL. Similarly, when the manual peg transfer task is added, the reliability of all models is compromised, highlighting the necessity of more robust methods that consider different factors that complement the pupil diameter information. Conclusion: Our results offer a quantitative perspective of the limitations of the current solutions and highlight the necessity of developing tailored designs for the telerobotic surgery environment.