Determination of lipid-rich plaques by artificial intelligence-enabled quantitative computed tomography using near-infrared spectroscopy as reference

Hiroyuki Omori, Department of Cardiovascular Medicine, Gifu Heart Center, Gifu, Japan.
Hitoshi Matsuo, Department of Cardiovascular Medicine, Gifu Heart Center, Gifu, Japan.
Shinichiro Fujimoto, Department of Cardiovascular Biology and Medicine, Juntendo University, Graduate School of Medicine, Tokyo, Japan.
Yoshihiro Sobue, Department of Cardiovascular Medicine, Gifu Heart Center, Gifu, Japan.
Yui Nozaki, Department of Cardiovascular Biology and Medicine, Juntendo University, Graduate School of Medicine, Tokyo, Japan.
Gaku Nakazawa, Department of Cardiology, Kindai University Faculty of Medicine, Osaka, Japan.
Kuniaki Takahashi, Department of Cardiology, Kindai University Faculty of Medicine, Osaka, Japan.
Kazuhiro Osawa, Department of General Internal Medicine 3, Kawasaki Medical School General Medical Center, Okayama Red-Cross Hospital, Okayama, Japan.
Ryo Okubo, Toho University Omori Medical Center, Tokyo, Japan.
Umihiko Kaneko, Sapporo Cardiovascular Clinic, Hokkaido, Japan.
Hideyuki Sato, Edogawa Hospital Tokyo, Japan; Department of Radiological Technology, Juntendo University Hospital, Tokyo, Japan.
Takashi Kajiya, Tenyoukai Central Hospital, Kagoshima, Japan.
Toru Miyoshi, Department of Cardiovascular Medicine, Dentistry and Pharmaceutical Sciences, Okayama University Graduate School of Medicine, Okayama, Japan.
Keishi Ichikawa, Department of Cardiovascular Medicine, Dentistry and Pharmaceutical Sciences, Okayama University Graduate School of Medicine, Okayama, Japan.
Mitsunori Abe, Yotsuba Circulation Clinic, Ehime, Japan.
Toshiro Kitagawa, Department of Cardiovascular Medicine, Hiroshima University Graduate School of Biomedical and Health Sciences, Hiroshima, Japan.
Hiroki Ikenaga, Department of Cardiovascular Medicine, Hiroshima University Graduate School of Biomedical and Health Sciences, Hiroshima, Japan.
Mike Saji, Toho University Omori Medical Center, Tokyo, Japan; Department of Cardiology, Sakakibara Heart Institute, Tokyo, Japan.
Nobuo Iguchi, Department of Cardiology, Sakakibara Heart Institute, Tokyo, Japan.
Takeshi Ijich, Department of Cardiology, Tokai University, School of Medicine, Kanagawa, Japan.
Hiroshi Mikamo, Department of Cardiology, Toho University Sakura Medical Center, Chiba, Japan.
Akira Kurata, Department of Cardiology, Shikoku Cancer Center, Department of Radiology, Ehime University Graduate School of Medicine, Ehime, Japan.
Masao Moroi, Department of Cardiovascular Medicine, Toho University Ohashi Medical Center, Tokyo, Japan.
Raisuke Iijima, Department of Cardiovascular Medicine, Toho University Ohashi Medical Center, Tokyo, Japan.
Shant Malkasian, Wayne State University School of Medicine, Detroit, MI, USA.
Tami Crabtree, Cleerly Inc., CO, USA.
James K. Min, Cleerly Inc., CO, USA.
James P. Earls, Cleerly Inc., CO, USA; George Washington University School of Medicine and Health Sciences, Washington, DC, USA.
Rine Nakanishi, Toho University Omori Medical Center, Tokyo, Japan. Electronic address: rine.n@med.toho-u.ac.jp.

Document Type

Journal Article

Publication Date

10-29-2023

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.

Department

Radiology

Link to Full Text

Share

COinS