TY - JOUR
T1 - Determination of lipid-rich plaques by artificial intelligence-enabled quantitative computed tomography using near-infrared spectroscopy as reference
AU - Omori, Hiroyuki
AU - Matsuo, Hitoshi
AU - Fujimoto, Shinichiro
AU - Sobue, Yoshihiro
AU - Nozaki, Yui
AU - Nakazawa, Gaku
AU - Takahashi, Kuniaki
AU - Osawa, Kazuhiro
AU - Okubo, Ryo
AU - Kaneko, Umihiko
AU - Sato, Hideyuki
AU - Kajiya, Takashi
AU - Miyoshi, Toru
AU - Ichikawa, Keishi
AU - Abe, Mitsunori
AU - Kitagawa, Toshiro
AU - Ikenaga, Hiroki
AU - Saji, Mike
AU - Iguchi, Nobuo
AU - Ijichi, Takeshi
AU - Mikamo, Hiroshi
AU - Kurata, Akira
AU - Moroi, Masao
AU - Iijima, Raisuke
AU - Malkasian, Shant
AU - Crabtree, Tami
AU - Min, James K.
AU - Earls, James P.
AU - Nakanishi, Rine
N1 - Publisher Copyright:
© 2023 The Authors
PY - 2023/12
Y1 - 2023/12
N2 - 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 maxLCBI4mm ≥ 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<30HU was 0.97 (95% confidence interval [CI]: 0.93–1.00] with an optimal volume threshold of 2.30 mm3. 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 mm3, versus 42%, 100%, and 27% using <30 HU and >0 mm3 volume of LD-NCP (p < 0.001 for accuracy and specificity). AI-QCT strongly correlated with IVUS measurements; vessel area (r2 = 0.87), lumen area (r2 = 0.87), plaque burden (r2 = 0.78) and lesion length (r2 = 0.88), respectively. Conclusions: AI-QCT demonstrated excellent diagnostic performance in detecting significant LD-NCP using maxLCBI4mm ≥ 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.
AB - 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 maxLCBI4mm ≥ 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<30HU was 0.97 (95% confidence interval [CI]: 0.93–1.00] with an optimal volume threshold of 2.30 mm3. 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 mm3, versus 42%, 100%, and 27% using <30 HU and >0 mm3 volume of LD-NCP (p < 0.001 for accuracy and specificity). AI-QCT strongly correlated with IVUS measurements; vessel area (r2 = 0.87), lumen area (r2 = 0.87), plaque burden (r2 = 0.78) and lesion length (r2 = 0.88), respectively. Conclusions: AI-QCT demonstrated excellent diagnostic performance in detecting significant LD-NCP using maxLCBI4mm ≥ 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.
UR - http://www.scopus.com/inward/record.url?scp=85176147890&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85176147890&partnerID=8YFLogxK
U2 - 10.1016/j.atherosclerosis.2023.117363
DO - 10.1016/j.atherosclerosis.2023.117363
M3 - Article
C2 - 37944269
AN - SCOPUS:85176147890
SN - 0021-9150
VL - 386
JO - Atherosclerosis
JF - Atherosclerosis
M1 - 117363
ER -