Generating virtual histology staining of human coronary OCT images using transformer-based neural network

Xueshen Li; Hongshan Liu; Xiaoyu Song; Brigitta C. Brott; Silvio H. Litovsky; Yu Gan

doi:10.1117/12.3003138

13 March 2024 Generating virtual histology staining of human coronary OCT images using transformer-based neural network

Xueshen Li, Hongshan Liu, Xiaoyu Song, Brigitta C. Brott, Silvio H. Litovsky, Yu Gan

Proceedings Volume 12819, Diagnostic and Therapeutic Applications of Light in Cardiology 2024; 1281903 (2024) https://doi.org/10.1117/12.3003138
Event: SPIE BiOS, 2024, San Francisco, California, United States

Abstract

Histopathological information is critical to identify diseased region in coronary tissues, with great potential to guide the treatment of coronary artery disease. We develop a pathology-aware generative adversarial network (GAN) to generate virtual histology images from coronary optical coherence tomography (OCT) images. The proposed network integrates transformer network structure with a cycleGAN framework. Our algorithm advances existing cycleGAN-based method with a lower value of Frechet Inception distance, as demonstrated by a cross-validation experiment from a human coronary dataset. Our work incorporates histopathological visualization into real-time OCT imaging, holding great potential to assist diagnostic and therapeutic applications of cardiovascular diseases.

Conference Presentation

Citation Download Citation

Xueshen Li, Hongshan Liu, Xiaoyu Song, Brigitta C. Brott, Silvio H. Litovsky, and Yu Gan "Generating virtual histology staining of human coronary OCT images using transformer-based neural network", Proc. SPIE 12819, Diagnostic and Therapeutic Applications of Light in Cardiology 2024, 1281903 (13 March 2024); https://doi.org/10.1117/12.3003138

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