Deep learning-enabled coronary CT angiography for plaque and stenosis quantification and cardiac risk prediction: an international multicentre study

Andrew Lin, MBBS; Nipun Manral, MSc; Priscilla McElhinney, BSc; Aditya Killekar, MSc; Hidenari Matsumoto, MD; Jacek Kwiecinski, MD; Konrad Pieszko, MD; Aryabod Razipour, MD; Kajetan Grodecki, MD; Caroline Park, BSc; Yuka Otaki, MD; Mhairi Doris, MD; Alan C Kwan, MD; Donghee Han, MD; Keiichiro Kuronuma, MD; Guadalupe Flores Tomasino, MD; Evangelos Tzolos, MD; Aakash Shanbhag, MSc; Markus Goeller, MD; Mohamed Marwan, MD; Heidi Gransar, MS; Balaji K Tamarappoo, MD; Sebastien Cadet, MSc; Stephan Achenbach, ProfMD; Stephen J Nicholls, ProfMBBS; Dennis T Wong, MBBS; Daniel S Berman, MD; Marc Dweck, ProfMBChB; David E Newby, ProfMD; Michelle C Williams, MBChB; Piotr J Slomka, ProfPhD; Damini Dey, ProfPhD

The Lancet: Digital Health (Apr 2022)

Deep learning-enabled coronary CT angiography for plaque and stenosis quantification and cardiac risk prediction: an international multicentre study

Andrew Lin, MBBS,
Nipun Manral, MSc,
Priscilla McElhinney, BSc,
Aditya Killekar, MSc,
Hidenari Matsumoto, MD,
Jacek Kwiecinski, MD,
Konrad Pieszko, MD,
Aryabod Razipour, MD,
Kajetan Grodecki, MD,
Caroline Park, BSc,
Yuka Otaki, MD,
Mhairi Doris, MD,
Alan C Kwan, MD,
Donghee Han, MD,
Keiichiro Kuronuma, MD,
Guadalupe Flores Tomasino, MD,
Evangelos Tzolos, MD,
Aakash Shanbhag, MSc,
Markus Goeller, MD,
Mohamed Marwan, MD,
Heidi Gransar, MS,
Balaji K Tamarappoo, MD,
Sebastien Cadet, MSc,
Stephan Achenbach, ProfMD,
Stephen J Nicholls, ProfMBBS,
Dennis T Wong, MBBS,
Daniel S Berman, MD,
Marc Dweck, ProfMBChB,
David E Newby, ProfMD,
Michelle C Williams, MBChB,
Piotr J Slomka, ProfPhD,
Damini Dey, ProfPhD

Affiliations

Andrew Lin, MBBS: Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Monash Cardiovascular Research Centre, Victorian Heart Institute, Monash University, Melbourne, VIC, Australia; MonashHeart, Monash Health, Melbourne, VIC, Australia
Nipun Manral, MSc: Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Priscilla McElhinney, BSc: Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Aditya Killekar, MSc: Division of Artificial Intelligence, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Hidenari Matsumoto, MD: Division of Cardiology, Showa University School of Medicine, Tokyo, Japan
Jacek Kwiecinski, MD: Division of Artificial Intelligence, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA; British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, UK; Department of Interventional Cardiology and Angiology, Institute of Cardiology, Warsaw, Poland
Konrad Pieszko, MD: Division of Artificial Intelligence, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Department of Interventional Cardiology, Collegium Medicum, University of Zielona Góra, Poland
Aryabod Razipour, MD: Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Kajetan Grodecki, MD: Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Department of Cardiology, Medical University of Warsaw, Warsaw, Poland
Caroline Park, BSc: Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Yuka Otaki, MD: Department of Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Mhairi Doris, MD: British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, UK
Alan C Kwan, MD: Department of Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Donghee Han, MD: Department of Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Keiichiro Kuronuma, MD: Department of Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Guadalupe Flores Tomasino, MD: Department of Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Evangelos Tzolos, MD: Department of Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA; British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, UK
Aakash Shanbhag, MSc: Division of Artificial Intelligence, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Markus Goeller, MD: Department of Cardiology, Friedrich-Alexander Universität Erlangen-Nürnberg, Erlangen, Germany
Mohamed Marwan, MD: Department of Cardiology, Friedrich-Alexander Universität Erlangen-Nürnberg, Erlangen, Germany
Heidi Gransar, MS: Department of Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Balaji K Tamarappoo, MD: Department of Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Sebastien Cadet, MSc: Department of Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Stephan Achenbach, ProfMD: Department of Cardiology, Friedrich-Alexander Universität Erlangen-Nürnberg, Erlangen, Germany
Stephen J Nicholls, ProfMBBS: Monash Cardiovascular Research Centre, Victorian Heart Institute, Monash University, Melbourne, VIC, Australia; MonashHeart, Monash Health, Melbourne, VIC, Australia
Dennis T Wong, MBBS: Monash Cardiovascular Research Centre, Victorian Heart Institute, Monash University, Melbourne, VIC, Australia; MonashHeart, Monash Health, Melbourne, VIC, Australia
Daniel S Berman, MD: Department of Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Marc Dweck, ProfMBChB: British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, UK
David E Newby, ProfMD: British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, UK
Michelle C Williams, MBChB: British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, UK
Piotr J Slomka, ProfPhD: Division of Artificial Intelligence, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Damini Dey, ProfPhD: Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Correspondence to: Prof Damini Dey, Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA 90048, USA

Journal volume & issue: Vol. 4, no. 4
pp. e256 – e265

Abstract

Read online

Summary: 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 mm3 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.

Published in The Lancet: Digital Health

ISSN: 2589-7500 (Online)
Publisher: Elsevier
Country of publisher: United Kingdom
LCC subjects: Medicine: Medicine (General): Computer applications to medicine. Medical informatics
Website: https://www.thelancet.com/journals/landig/home

About the journal