QOCT-Net: A Physics-Informed Neural Network for Intravascular Optical Coherence Tomography Attenuation Imaging

• Published in: IEEE journal of biomedical and health informatics Vol. 27; no. 8; pp. 1 - 13
• Main Authors: Zheng, Sun, Shuyan, Wang, Yingsa, Hou, Meichen, Sun
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.08.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Attenuation; attenuation coefficient; Attenuation coefficients; Computer Simulation; Coronary Vessels; Deep learning; Humans; Image resolution; Imaging; intravascular optical coherence tomography; Mathematical models; Medical imaging; Neural networks; Neural Networks, Computer; Optical Coherence Tomography; Optical imaging; Optical scattering; Photonics; Physics; Plaque, Atherosclerotic - diagnostic imaging; quantitative imaging; recurrent inference machine; Scattering; Signal to noise ratio; Tomography; Tomography, Optical Coherence - methods
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2023.3276422

Intravascular optical coherence tomography (IVOCT) provides high-resolution, depth-resolved images of coronary arterial microstructure by acquiring backscattered light. Quantitative attenuation imaging is important for accurate characterization of tissue components and identification of vulnerable plaques. In this work, we proposed a deep learning method for IVOCT attenuation imaging based on the multiple scattering model of light transport. A physics-informed deep network named Quantitative OCT Network (QOCT-Net) was designed to recover pixel-level optical attenuation coefficients directly from standard IVOCT B-scan images. The network was trained and tested on simulation and in vivo datasets. Results showed superior attenuation coefficient estimates both visually and based on quantitative image metrics. The structural similarity, energy error depth and peak signal-to-noise ratio are improved by at least 7%, 5% and 12.4%, respectively, compared with the state-of-the-art non-learning methods. This method potentially enables high-precision quantitative imaging for tissue characterization and vulnerable plaque identification.