Synthetic data algorithm development for high-speed instrument tracking of OCT imaging during anterior chamber ophthalmic surgeries

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

doi:10.1117/12.2692376

13 March 2024 Synthetic data algorithm development for high-speed instrument tracking of OCT imaging during anterior chamber ophthalmic surgeries

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

Author Affiliations +

Proceedings Volume PC12824, Ophthalmic Technologies XXXIV; PC1282415 (2024) https://doi.org/10.1117/12.2692376
Event: SPIE BiOS, 2024, San Francisco, California, United States

Abstract

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.

Citation Download Citation

Harvey Y. Shi, Pablo Ortiz, Jianwei D. Li, Amit Narawane, Robert Trout, Yuan Tian, Mark Draelos, Ryan P. McNabb, Anthony N. Kuo, and 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

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

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.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available