Automated object detection within coronary optical coherence tomography images

Hongshan Liu; Xuesheng Li; Yu Gan

doi:10.1117/12.2610257

7 March 2022 Automated object detection within coronary optical coherence tomography images

Hongshan Liu, Xuesheng Li, Yu Gan

Proceedings Volume PC11936, Diagnostic and Therapeutic Applications of Light in Cardiology 2022; PC119360E (2022) https://doi.org/10.1117/12.2610257
Event: SPIE BiOS, 2022, San Francisco, California, United States

Abstract

In this project, we propose a deep learning-based method to detect calcified tissue within coronary optical coherence tomography (OCT) images. Conventionally, diseased tissue was manually checked on a frame (Bscan)-by-frame (Bscan) basis. Based on faster region-based convolutional neural network, our proposed method can automatically detect the calcified regions from diseased coronary artery. Our method achieves promising result of mean average precision (0.74) and recall (0.79) in detecting calcified regions. The proposed method could provide valuable information for locating calcified tissue within a large volume of OCT images. It has great potential to aid the treatment of coronary artery disease.

Conference Presentation

Citation Download Citation

Hongshan Liu, Xuesheng Li, and Yu Gan "Automated object detection within coronary optical coherence tomography images", Proc. SPIE PC11936, Diagnostic and Therapeutic Applications of Light in Cardiology 2022, PC119360E (7 March 2022); https://doi.org/10.1117/12.2610257

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