Harvey Y. Shi,1 Pablo Ortiz,1 Jianwei D. Li,1 Amit Narawane,1 Robert Trout,1 Yuan Tian,1 Mark Draelos,2 Ryan P. McNabb,1 Anthony N. Kuo,1 Joseph A. Izatt1
1Duke Univ. (United States) 2Univ. of Michigan (United States)
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Real-time volumetric microscope-integrated OCT (MIOCT) visualization of ophthalmic surgeries is limited by the narrow field of view of OCT relative to the movement of the surgical instruments, requiring extensive manual repositioning by a trained operator. We developed a computer vision system for instrument tracking that utilizes a microscope video camera and a deep-learning object detector trained on synthetic data, which consisted of 3D rendered models of surgical instruments alongside an eye model. This system was then tested in a clinical MIOCT platform, providing high fidelity, video-rate (>40 Hz) object tracking of a cataract surgery instrument over a model eye phantom.
Conference Presentation
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Harvey Y. Shi, Pablo Ortiz, Jianwei D. Li, Amit Narawane, Robert Trout, Yuan Tian, Mark Draelos, Ryan P. McNabb, Anthony N. Kuo, Joseph A. Izatt, "Synthetic data algorithm development for high-speed instrument tracking of OCT imaging during anterior chamber ophthalmic surgeries," Proc. SPIE PC12824, Ophthalmic Technologies XXXIV, PC1282415 (13 March 2024); https://doi.org/10.1117/12.2692376