SurgGaze improves surgeon eye tracking accuracy using tool contact points
SurgGaze: Implicit Calibration for Accurate Gaze Analysis in Operating Rooms with Wearable Eyetrackers
Human-Computer Interaction
Summary
Tracking where surgeons look during laparoscopic surgery helps understand their attention, but current wearable eye trackers often have big errors. The authors found that surgeons tend to look near where their tools touch tissue during surgery. They used this behavior to automatically correct eye tracker errors without asking the surgeon to do explicit calibration. Their method, SurgGaze, cut gaze estimation errors by over 40% in tests, making it easier to study surgeons' focus during operations.
What this means in practice
- •For surgical training teams: Improve feedback on how trainees visually attend to key areas during laparoscopic procedures without interrupting workflow for explicit eye tracker calibration.
- •For augmented reality developers: Enhance calibration of wearable devices that track eye gaze in medical settings, enabling more precise AR overlays based on surgeon attention.
Authors
Jingying Wang, Rosiana Natalie, Keyuan Hu, Wenqian Xu, Brian George, Vitaliy Popov, Anhong Guo, Xu Wang
Abstract
Accurate gaze tracking is essential for understanding surgeons' visual attention and cognitive processes during laparoscopic surgery, yet wearable eye trackers produce large errors systematically correlated with ground-truth gaze locations, as demonstrated in Study 1. We introduce SurgGaze, an implicit calibration method that corrects these errors using high-confidence surgical moments. Building on evidence that surgeons' gaze converges near the tool-tissue contact point (TTCP) during dissection, SurgGaze uses TTCP as a surrogate for true gaze to construct training pairs. We evaluate SurgGaze in a simulated operating room trial and an authentic operating room case study. In simulation, SurgGaze reduced gaze estimation error by 40.6%, significantly outperforming conventional 9-point explicit calibration. The case study showed that these moments provide reliable training data and that calibrated gaze improves interpretation of surgeons' attention beyond numeric error reduction. These findings demonstrate that structured behavioral signals can enable implicit calibration for gaze tracking in complex real-world settings.