Presentation
5 March 2021 Machine-learning-based biochemical characterization of atherosclerotic plaques in intravascular optical coherence tomography–fluorescence lifetime imaging
Author Affiliations +
Abstract
Intravascular optical coherence tomography-fluorescence lifetime imaging (OCT-FLIm) provides co-registered structural and biochemical information of atherosclerotic plaques in a label-free manner. For intuitive image interpretation of OCT-FLIm, herein, we present a machine learning classifier where key biochemical components (lipids, lipids+macrophages, macrophages, fibrotic, and normal) related to plaque destabilization are characterized based on the combination of multispectral FLIm parameters and convolutional OCT features. Using dataset from in vivo atheromatous swine models, the classification accuracy was >92% for each plaque component according the five-fold cross validation. This highly translatable imaging strategy will open a new avenue for clinical intracoronary assessment of high-risk plaques.
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hyeong Soo Nam, Sunwon Kim M.D., Min Woo Lee, Hyun Jung Kim, Woo Jae Kang, Joon Woo Song, Jeongmoo Han, Dong Oh Kang M.D., Wang-Yuhl Oh, Jin Won Kim M.D., and Hongki Yoo "Machine-learning-based biochemical characterization of atherosclerotic plaques in intravascular optical coherence tomography–fluorescence lifetime imaging", Proc. SPIE 11621, Diagnostic and Therapeutic Applications of Light in Cardiology 2021, 116210M (5 March 2021); https://doi.org/10.1117/12.2578099
Advertisement
Advertisement
KEYWORDS
Coherence imaging

Optical coherence tomography

Coherence (optics)

In vivo imaging

Machine learning

Fluorescence lifetime imaging

Medicine

Back to Top