Lin A, Manral N, McElhinney P, Killekar A, Matsumoto H, Kwiecinski J, Pieszko K, Razipour A, Grodecki K, Park C, Otaki Y, Doris M, Kwan AC, Han D, Kuronuma K, Flores Tomasino G, Tzolos E, Shanbhag A, Goeller M, Marwan M, Gransar H, Tamarappoo BK, Cadet S, Achenbach S, Nicholls SJ, Wong DT, Berman DS, Dweck M, Newby DE, Williams MC, Slomka PJ, and Dey D
Background: Atherosclerotic plaque quantification from coronary CT angiography (CCTA) enables accurate assessment of coronary artery disease burden and prognosis. We sought to develop and validate a deep learning system for CCTA-derived measures of plaque volume and stenosis severity., Methods: This international, multicentre study included nine cohorts of patients undergoing CCTA at 11 sites, who were assigned into training and test sets. Data were retrospectively collected on patients with a wide range of clinical presentations of coronary artery disease who underwent CCTA between Nov 18, 2010, and Jan 25, 2019. A novel deep learning convolutional neural network was trained to segment coronary plaque in 921 patients (5045 lesions). The deep learning network was then applied to an independent test set, which included an external validation cohort of 175 patients (1081 lesions) and 50 patients (84 lesions) assessed by intravascular ultrasound within 1 month of CCTA. We evaluated the prognostic value of deep learning-based plaque measurements for fatal or non-fatal myocardial infarction (our primary outcome) in 1611 patients from the prospective SCOT-HEART trial, assessed as dichotomous variables using multivariable Cox regression analysis, with adjustment for the ASSIGN clinical risk score., Findings: In the overall test set, there was excellent or good agreement, respectively, between deep learning and expert reader measurements of total plaque volume (intraclass correlation coefficient [ICC] 0·964) and percent diameter stenosis (ICC 0·879; both p<0·0001). When compared with intravascular ultrasound, there was excellent agreement for deep learning total plaque volume (ICC 0·949) and minimal luminal area (ICC 0·904). The mean per-patient deep learning plaque analysis time was 5·65 s (SD 1·87) versus 25·66 min (6·79) taken by experts. Over a median follow-up of 4·7 years (IQR 4·0-5·7), myocardial infarction occurred in 41 (2·5%) of 1611 patients from the SCOT-HEART trial. A deep learning-based total plaque volume of 238·5 mm 3 or higher was associated with an increased risk of myocardial infarction (hazard ratio [HR] 5·36, 95% CI 1·70-16·86; p=0·0042) after adjustment for the presence of deep learning-based obstructive stenosis (HR 2·49, 1·07-5·50; p=0·0089) and the ASSIGN clinical risk score (HR 1·01, 0·99-1·04; p=0·35)., Interpretation: Our novel, externally validated deep learning system provides rapid measurements of plaque volume and stenosis severity from CCTA that agree closely with expert readers and intravascular ultrasound, and could have prognostic value for future myocardial infarction., Funding: National Heart, Lung, and Blood Institute and the Miriam & Sheldon G Adelson Medical Research Foundation., Competing Interests: Declaration of interests SC, PJS, DD, and DSB received software royalties from Cedars-Sinai Medical Center outside of the current work. DSB, PJS, and DD hold a single patent (US8885905B2/WO2011069120A1, Method and System for Plaque Characterisation). KP reports a non-financial advisory role with Kardiollytics. KG reports grants or contracts from the Foundation for Polish Science and Polish Society of Cardiology. ACK reports partial effort support from the Doris Duke Charitable Foundation Grant. KK reports grants or contracts from The Society of Nuclear Medicine and Molecular Imaging Wagner-Torizuka Fellowship and Nihon University School of Medicine Alumni Association. ET is supported by a grant from the British Heart Foundation. SC reports financial support from the Miriam & Sheldon G Adelson Medical Research Foundation Grant. SJN reports grants or contracts from AstraZeneca, New Amsterdam Pharma, Amgen, Anthera, Eli Lilly, Esperion, Novartis, Cerenis, The Medicines Company, Resverlogix, InfraReDx, Roche, Sanofi-Regeneron, and LipoScience; and consulting fees from AstraZeneca, Amarin, Akcea, Eli Lilly, Anthera, Omthera, Merck, Takeda, Resverlogix, Sanofi-Regeneron, CSL Behring, Esperion, and Boehringer Ingelheim. MDw reports consulting fees from Novartis, Jupiter Bioventures, and Silence Therapeutics; and payment or honoraria from Pfizer and Novartis. DEN reports a grant from the British Heart Foundation and Wellcome Trust. MCW reports a grant from the British Heart Foundation; declares payment or honoraria from Cannon Medical Systems; and a leadership or fiduciary roles with British Society of Cardiovascular Imaging, Society of Cardiovascular Computed Tomography, and European Society of Cardiovascular Radiology. All other authors declare no competing interests., (Copyright © 2022 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY-NC-ND 4.0 license. Published by Elsevier Ltd.. All rights reserved.)