Determination of lipid-rich plaques by artificial intelligence-enabled quantitative computed tomography using near-infrared spectroscopy as reference
Document Type
Journal Article
Publication Date
12-1-2023
Journal
Atherosclerosis
Volume
386
DOI
10.1016/j.atherosclerosis.2023.117363
Keywords
Artificial intelligence; Computed tomography; Coronary artery disease; Lipid-rich plaque; Near-infrared spectroscopy
Abstract
BACKGROUND AND AIMS: Artificial intelligence quantitative CT (AI-QCT) determines coronary plaque morphology with high efficiency and accuracy. Yet, its performance to quantify lipid-rich plaque remains unclear. This study investigated the performance of AI-QCT for the detection of low-density noncalcified plaque (LD-NCP) using near-infrared spectroscopy-intravascular ultrasound (NIRS-IVUS). METHODS: The INVICTUS Registry is a multi-center registry enrolling patients undergoing clinically indicated coronary CT angiography and IVUS, NIRS-IVUS, or optical coherence tomography. We assessed the performance of various Hounsfield unit (HU) and volume thresholds of LD-NCP using maxLCBI ≥ 400 as the reference standard and the correlation of the vessel area, lumen area, plaque burden, and lesion length between AI-QCT and IVUS. RESULTS: This study included 133 atherosclerotic plaques from 47 patients who underwent coronary CT angiography and NIRS-IVUS The area under the curve of LD-NCP was 0.97 (95% confidence interval [CI]: 0.93-1.00] with an optimal volume threshold of 2.30 mm. Accuracy, sensitivity, and specificity were 94% (95% CI: 88-96%], 93% (95% CI: 76-98%), and 94% (95% CI: 88-98%), respectively, using <30 HU and 2.3 mm, versus 42%, 100%, and 27% using <30 HU and >0 mm volume of LD-NCP (p < 0.001 for accuracy and specificity). AI-QCT strongly correlated with IVUS measurements; vessel area (r = 0.87), lumen area (r = 0.87), plaque burden (r = 0.78) and lesion length (r = 0.88), respectively. CONCLUSIONS: AI-QCT demonstrated excellent diagnostic performance in detecting significant LD-NCP using maxLCBI ≥ 400 as the reference standard. Additionally, vessel area, lumen area, plaque burden, and lesion length derived from AI-QCT strongly correlated with respective IVUS measurements.
APA Citation
Omori, Hiroyuki; Matsuo, Hitoshi; Fujimoto, Shinichiro; Sobue, Yoshihiro; Nozaki, Yui; Nakazawa, Gaku; Takahashi, Kuniaki; Osawa, Kazuhiro; Okubo, Ryo; Kaneko, Umihiko; Sato, Hideyuki; Kajiya, Takashi; Miyoshi, Toru; Ichikawa, Keishi; Abe, Mitsunori; Kitagawa, Toshiro; Ikenaga, Hiroki; Saji, Mike; Iguchi, Nobuo; Ijichi, Takeshi; Mikamo, Hiroshi; Kurata, Akira; Moroi, Masao; Iijima, Raisuke; Malkasian, Shant; Crabtree, Tami; Min, James K.; Earls, James P.; and Nakanishi, Rine, "Determination of lipid-rich plaques by artificial intelligence-enabled quantitative computed tomography using near-infrared spectroscopy as reference" (2023). GW Authored Works. Paper 4050.
https://hsrc.himmelfarb.gwu.edu/gwhpubs/4050
Department
Radiology