Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Multicenter Study
. 2024 Oct;17(10):e016958.
doi: 10.1161/CIRCIMAGING.124.016958. Epub 2024 Sep 30.

Patient-Specific Myocardial Infarction Risk Thresholds From AI-Enabled Coronary Plaque Analysis

Robert J H Miller  1   2 , Nipun Manral  1 , Andrew Lin  1   3   4 , Aakash Shanbhag  1 , Caroline Park  1 , Jacek Kwiecinski  5 , Aditya Killekar  1 , Priscilla McElhinney  1 , Hidenari Matsumoto  6 , Aryabod Razipour  1 , Kajetan Grodecki  1   7 , Alan C Kwan  1 , Donghee Han  1 , Keiichiro Kuronuma  1 , Guadalupe Flores Tomasino  1 , Jolien Geers  1   8 , Markus Goeller  9 , Mohamed Marwan  9 , Heidi Gransar  1 , Balaji K Tamarappoo  10 , Sebastien Cadet  1 , Victor Y Cheng  11 , Stephan Achenbach  9 , Stephen J Nicholls  3   4 , Dennis T Wong  3   4 , Lu Chen  12 , J Jane Cao  12 , Daniel S Berman  1 , Marc R Dweck  13 , David E Newby  13 , Michelle C Williams  13 , Piotr J Slomka  1 , Damini Dey  1
Affiliations
Multicenter Study

Patient-Specific Myocardial Infarction Risk Thresholds From AI-Enabled Coronary Plaque Analysis

Robert J H Miller et al. Circ Cardiovasc Imaging. 2024 Oct.

Abstract

Background: Plaque quantification from coronary computed tomography angiography has emerged as a valuable predictor of cardiovascular risk. Deep learning can provide automated quantification of coronary plaque from computed tomography angiography. We determined per-patient age- and sex-specific distributions of deep learning-based plaque measurements and further evaluated their risk prediction for myocardial infarction in external samples.

Methods: In this international, multicenter study of 2803 patients, a previously validated deep learning system was used to quantify coronary plaque from computed tomography angiography. Age- and sex-specific distributions of coronary plaque volume were determined from 956 patients undergoing computed tomography angiography for stable coronary artery disease from 5 cohorts. Multicenter external samples were used to evaluate associations between coronary plaque percentiles and myocardial infarction.

Results: Quantitative deep learning plaque volumes increased with age and were higher in male patients. In the combined external sample (n=1847), patients in the ≥75th percentile of total plaque volume (unadjusted hazard ratio, 2.65 [95% CI, 1.47-4.78]; P=0.001) were at increased risk of myocardial infarction compared with patients below the 50th percentile. Similar relationships were seen for most plaque volumes and persisted in multivariable analyses adjusting for clinical characteristics, coronary artery calcium, stenosis, and plaque volume, with adjusted hazard ratios ranging from 2.38 to 2.50 for patients in the ≥75th percentile of total plaque volume.

Conclusions: Per-patient age- and sex-specific distributions for deep learning-based coronary plaque volumes are strongly predictive of myocardial infarction, with the highest risk seen in patients with coronary plaque volumes in the ≥75th percentile.

Keywords: cardiac imaging techniques; coronary artery disease; deep learning; myocardial infarction; plaque, atherosclerotic.

PubMed Disclaimer

Conflict of interest statement

Dr Miller has received consulting fees and research support from Pfizer. S. Cadet, Dr Slomka, Dr Dey, and Dr Berman received software royalties from Cedars-Sinai Medical Center and report equity in APQ Health Inc. outside of the current work. Dr Berman, Dr Slomka, and Dr Dey hold a patent (US8885905B2/WO2011069120A1, Method and System for Plaque Characterization). Dr Grodecki reports grants or contracts from the Foundation for Polish Science and Polish Society of Cardiology. Dr Kwan reports partial effort support from the Doris Duke Charitable Foundation Grant. Dr Kuronuma is supported by grants from The Society of Nuclear Medicine and Molecular Imaging Wagner-Torizuka Fellowship and Nihon University School of Medicine Alumni Association. S. Cadet reports financial support from the Miriam and Sheldon G Adelson Medical Research Foundation Grant. Dr Nicholls 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. Dr Dweck reports consulting fees from Novartis, Jupiter Bioventures, and Silence Therapeutics; and payment or honoraria from Pfizer and Novartis. Dr Newby reports a grant from the British Heart Foundation (RE/24/130012, CH/09/002, and RG/F/22/110093) and Wellcome Trust. Dr Williams has given talks for Canon Medical Systems, Siemens Healthineers and Novartis. The other authors report no conflicts.

Figures

Figure 1:
Figure 1:
Example of deep learning plaque quantification results in a patient who experienced a major adverse cardiovascular event. Panel A shows three-dimensional (3D) rendering of coronary computed tomography angiography (CTA)-based quantitative plaque analysis with red non-calcified plaque and orange low-attenuation plaque. Panel B demonstrates a 3D representation of the coronary artery lumen (blue), non-calcified plaque (red) and low-attenuation plaque (orange). The lesion is located in the right coronary artery with long-axis cross-section in Panel C, and short-axis cross-section of the lesion in Panel D.
Figure 2:
Figure 2:
Distribution of total plaque volume as a function of sex and age. Expected plaque volume increase with age in female and male patients, with overall higher expected plaque volumes in male patients.
Figure 3:
Figure 3:
Age and sex adjusted hazard ratio for fatal or non-fatal myocardial infarction in the combined external testing sample. CI: confidence interval.
See this image and copyright information in PMC

References

    1. Gulati M, Levy PD, Mukherjee D, Amsterdam E, Bhatt DL, Birtcher KK, Blankstein R, Boyd J, Bullock-Palmer RP, Conejo T, et al. 2021 aha/acc/ase/chest/saem/scct/scmr Guideline for the evaluation and diagnosis of chest pain. Circulation. 2021;144:e368–e454 - PubMed
    1. Antonopoulos AS, Angelopoulos A, Tsioufis K, Antoniades C, Tousoulis D. Cardiovascular risk stratification by coronary computed tomography angiography imaging. Eur J Prev Cardiol. 2022;29:608–624 - PubMed
    1. Rosendael ARv, Shaw LJ, Xie JX, Dimitriu-Leen AC, Smit JM, Scholte AJ, Werkhoven JMv, Callister TQ, DeLago A, Berman DS, et al. Superior risk stratification with coronary computed tomography angiography using a comprehensive atherosclerotic risk score. JACC Cardiovasc Imaging. 2019;12:1987–1997 - PMC - PubMed
    1. Rozanski A, Gransar H, Shaw LJ, Kim J, Miranda-Peats L, Wong ND, Rana JS, Orakzai R, Hayes SW, Friedman JD, et al. Impact of coronary artery calcium scanning on coronary risk factors and downstream testing the eisner (early identification of subclinical atherosclerosis by noninvasive imaging research) prospective randomized trial. J Am Coll Cardiol. 2011;57:1622–1632 - PMC - PubMed
    1. Mitchell JD, Fergestrom N, Gage BF, Paisley R, Moon P, Novak E, Cheezum M, Shaw LJ, Villines TC. Impact of statins on cardiovascular outcomes following coronary artery calcium scoring. J Am Coll Cardiol. 2018;72:3233–3242 - PMC - PubMed

Publication types

MeSH terms