Intraoperative adaptive eye model based on instrument-integrated OCT for robot-assisted vitreoretinal surgery

Abstract

Purpose: Pars plana vitrectomy (PPV) is the most common surgical procedure performed by retinal specialists, highlighting the need for model-based assistance and automation in surgical treatment. An intraoperative retinal model provides precise anatomical information relative to the surgical instrument, enhancing surgical precision and safety. Methods: This work focuses on the intraoperative parametrization of retinal shape using 1D instrument-integrated optical coherence tomography distance measurements combined with a surgical robot. Our approach accommodates variability in eye geometries by transitioning from an initial spherical model to an ellipsoidal representation, improving accuracy as more data is collected through sensor motion. Results: We demonstrate that ellipsoid fitting outperforms sphere fitting for regular eye shapes, achieving a mean absolute error of less than 40 μm in simulation and below 200 μm on 3D printed models and ex vivo porcine eyes. The model reliably transitions from a spherical to an ellipsoidal representation across all six tested eye shapes when specific criteria are satisfied. Conclusion: The adaptive eye model developed in this work meets the accuracy requirements for clinical application in PPV within the central retina. Additionally, the global model effectively extrapolates beyond the scanned area to encompass the retinal periphery.This capability enhances PPV procedures, particularly through virtual boundary assistance and improved surgical navigation, ultimately contributing to safer surgical outcomes.