TY - JOUR
T1 - AI Evaluation of Stenosis on Coronary CT Angiography, Comparison With Quantitative Coronary Angiography and Fractional Flow Reserve
T2 - A CREDENCE Trial Substudy
AU - Griffin, William F
AU - Choi, Andrew D
AU - Riess, Joanna S
AU - Marques, Hugo
AU - Chang, Hyuk-Jae
AU - Choi, Jung Hyun
AU - Doh, Joon-Hyung
AU - Her, Ae-Young
AU - Koo, Bon-Kwon
AU - Nam, Chang-Wook
AU - Park, Hyung-Bok
AU - Shin, Sang-Hoon
AU - Cole, Jason
AU - Gimelli, Alessia
AU - Khan, Muhammad Akram
AU - Lu, Bin
AU - Gao, Yang
AU - Nabi, Faisal
AU - Nakazato, Ryo
AU - Schoepf, U Joseph
AU - Driessen, Roel S
AU - Bom, Michiel J
AU - Thompson, Randall
AU - Jang, James J
AU - Ridner, Michael
AU - Rowan, Chris
AU - Avelar, Erick
AU - Généreux, Philippe
AU - Knaapen, Paul
AU - de Waard, Guus A
AU - Pontone, Gianluca
AU - Andreini, Daniele
AU - Earls, James P
N1 - Copyright © 2022 The Authors. Published by Elsevier Inc. All rights reserved.
PY - 2023/2
Y1 - 2023/2
N2 - OBJECTIVES: The study compared the performance for detection and grading of coronary stenoses using artificial intelligence-enabled quantitative coronary computed tomography angiography (AI-QCT) analyses to core lab-interpreted coronary computed tomography angiography (CTA), core lab quantitative coronary angiography (QCA), and invasive fractional flow reserve (FFR).BACKGROUND: Clinical reads of coronary CTA, especially by less experienced readers, may result in overestimation of coronary artery disease stenosis severity compared with expert interpretation. AI-based solutions applied to coronary CTA may overcome these limitations.METHODS: Coronary CTA, FFR, and QCA data from 303 stable patients (64 ± 10 years of age, 71% male) from the CREDENCE (Computed TomogRaphic Evaluation of Atherosclerotic DEtermiNants of Myocardial IsChEmia) trial were retrospectively analyzed using an Food and Drug Administration-cleared cloud-based software that performs AI-enabled coronary segmentation, lumen and vessel wall determination, plaque quantification and characterization, and stenosis determination.RESULTS: Disease prevalence was high, with 32.0%, 35.0%, 21.0%, and 13.0% demonstrating ≥50% stenosis in 0, 1, 2, and 3 coronary vessel territories, respectively. Average AI-QCT analysis time was 10.3 ± 2.7 minutes. AI-QCT evaluation demonstrated per-patient sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 94%, 68%, 81%, 90%, and 84%, respectively, for ≥50% stenosis, and of 94%, 82%, 69%, 97%, and 86%, respectively, for detection of ≥70% stenosis. There was high correlation between stenosis detected on AI-QCT evaluation vs QCA on a per-vessel and per-patient basis (intraclass correlation coefficient = 0.73 and 0.73, respectively; P < 0.001 for both). False positive AI-QCT findings were noted in in 62 of 848 (7.3%) vessels (stenosis of ≥70% by AI-QCT and QCA of <70%); however, 41 (66.1%) of these had an FFR of <0.8.CONCLUSIONS: A novel AI-based evaluation of coronary CTA enables rapid and accurate identification and exclusion of high-grade stenosis and with close agreement to blinded, core lab-interpreted quantitative coronary angiography. (Computed TomogRaphic Evaluation of Atherosclerotic DEtermiNants of Myocardial IsChEmia [CREDENCE]; NCT02173275).
AB - OBJECTIVES: The study compared the performance for detection and grading of coronary stenoses using artificial intelligence-enabled quantitative coronary computed tomography angiography (AI-QCT) analyses to core lab-interpreted coronary computed tomography angiography (CTA), core lab quantitative coronary angiography (QCA), and invasive fractional flow reserve (FFR).BACKGROUND: Clinical reads of coronary CTA, especially by less experienced readers, may result in overestimation of coronary artery disease stenosis severity compared with expert interpretation. AI-based solutions applied to coronary CTA may overcome these limitations.METHODS: Coronary CTA, FFR, and QCA data from 303 stable patients (64 ± 10 years of age, 71% male) from the CREDENCE (Computed TomogRaphic Evaluation of Atherosclerotic DEtermiNants of Myocardial IsChEmia) trial were retrospectively analyzed using an Food and Drug Administration-cleared cloud-based software that performs AI-enabled coronary segmentation, lumen and vessel wall determination, plaque quantification and characterization, and stenosis determination.RESULTS: Disease prevalence was high, with 32.0%, 35.0%, 21.0%, and 13.0% demonstrating ≥50% stenosis in 0, 1, 2, and 3 coronary vessel territories, respectively. Average AI-QCT analysis time was 10.3 ± 2.7 minutes. AI-QCT evaluation demonstrated per-patient sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 94%, 68%, 81%, 90%, and 84%, respectively, for ≥50% stenosis, and of 94%, 82%, 69%, 97%, and 86%, respectively, for detection of ≥70% stenosis. There was high correlation between stenosis detected on AI-QCT evaluation vs QCA on a per-vessel and per-patient basis (intraclass correlation coefficient = 0.73 and 0.73, respectively; P < 0.001 for both). False positive AI-QCT findings were noted in in 62 of 848 (7.3%) vessels (stenosis of ≥70% by AI-QCT and QCA of <70%); however, 41 (66.1%) of these had an FFR of <0.8.CONCLUSIONS: A novel AI-based evaluation of coronary CTA enables rapid and accurate identification and exclusion of high-grade stenosis and with close agreement to blinded, core lab-interpreted quantitative coronary angiography. (Computed TomogRaphic Evaluation of Atherosclerotic DEtermiNants of Myocardial IsChEmia [CREDENCE]; NCT02173275).
KW - artificial intelligence
KW - atherosclerosis
KW - coronary artery disease
KW - coronary computed tomography
KW - coronary CTA
KW - fractional flow reserve
KW - quantitative coronary angiography
U2 - 10.1016/j.jcmg.2021.10.020
DO - 10.1016/j.jcmg.2021.10.020
M3 - Article
C2 - 35183478
SN - 1936-878X
VL - 16
SP - 193
EP - 205
JO - Jacc: Cardiovascular Imaging
JF - Jacc: Cardiovascular Imaging
IS - 2
ER -