Prediction of Rapidly Progressing Coronary Plaques Using a 3D Convolutional Neural Network Model Based on Coronary CT Angiography

Cardiovascular Reviews

3083-48802981-8109

Bio-Byword Scientific Publishing Pty. Ltd.

10.26689/cr.v3i4.13000

Article

Prediction of Rapidly Progressing Coronary Plaques Using a 3D Convolutional Neural Network Model Based on Coronary CT Angiographyhttps://artdesignp.com/journal/CR/3/4/10.26689/cr.v3i4.13000ZhangWentao,HuangBingcang,LuWeiping,WangYing,SunGuangjie,XuJiahong,GeZhiru

2025

2025-12-31

Objective：To develop a three-dimensional convolutional neural network (3D-CNN) model based on coronary computed tomography angiography (CCTA) for predicting rapid plaque progression (RPP), and to compare its performance against traditional machine learning models and existing advanced methodologies. Methods:This retrospective study analyzed 150 patients who underwent serial CCTA examinations. Following strict alignment of CTA volume data with plaque masks, traditional machine learning models (LASSO, Elastic Net, Random Forest, XGBoost) and a lightweight 3D-CNN model were constructed. RPP was defined as an annualized plaque burden (PB) increase ≥ 1.0%. Model performance was primarily evaluated using the area under the receiver operating characteristic curve (AUC), with SHAP (SHapley Additive exPlanations) employed for model interpretation. Results:Traditional models demonstrated limited discriminatory ability, with AUCs ranging from 0.32 to 0.51. The developed 3D-CNN model achieved an AUC of 0.75 on the independent test set, with a sensitivity of 0.64 and a specificity of 0.88. SHAP analysis revealed that the 3D-CNN focused on internal plaque texture and Hounsfield Unit (HU) distribution patterns, whereas traditional models relied on limited features such as plaque volume.Conclusion:The 3D-CNN model can directly learn deep features associated with RPP from CCTA images. Its performance is significantly superior to traditional models and demonstrates potential comparable to current advanced radiomics and machine learning methods, offering a novel tool for non-invasive identification of high-risk plaques using a single time-point baseline scan.

Stone G, Maehara A, Lansky A, et al., 2011, A Prospective Natural-History Study of Coronary Atherosclerosis. New England Journal of Medicine, 364(3): 226–35.

Erlinge D, Maehara A, Ben-Yehuda O, et al., 2021, Identification of Vulnerable Plaques and Patients by Intracoronary Near-Infrared Spectroscopy and Ultrasound (PROSPECT II): A Prospective Natural History Study. The Lancet, 397(10278): 985–995.

Yokoya K, Takatsu H, Suzuki T, et al., 1999, Process of Progression of Coronary Artery Lesions from Mild or Moderate Stenosis to Moderate or Severe Stenosis: A Study based on Four Serial Coronary Arteriograms per Year. Circulation, 100(9): 903–909.

Ojio S, Takatsu H, Tanaka T, et al., 2000, Considerable Time from the Onset of Plaque Rupture and/or Thrombi until the Onset of Acute Myocardial Infarction in Humans: Coronary Angiographic Findings within 1 Week Before the Onset of Infarction. Circulation, 102(17): 2063–2069.

Ahmadi A, Leipsic J, Blankstein R, et al., 2015, Do Plaques Rapidly Progress Prior to Myocardial Infarction? The Interplay between Plaque Vulnerability and Progression. Circulation Research, 117(5): 450–458.

Jernberg T, Hasvold P, Henriksson M, et al., 2015, Cardiovascular Risk in Post-Myocardial Infarction Patients: Nationwide Real World Data Demonstrate the Importance of a Long-Term Perspective. European Heart Journal, 36(19): 1163–70.

Knuuti J, Wijns W, Saraste A, et al., 2019, ESC Guidelines for the Diagnosis and Management of Chronic Coronary Syndromes. European Heart Journal, 41(3): 407–477.

Serruys P, Hara H, Garg S, et al., 2021, Coronary Computed Tomographic Angiography for Complete Assessment of Coronary Artery Disease: JACC State-of-the-Art Review. Journal of the American College of Cardiology, 78(7): 713–736.

Van Assen M, Varga-Szemes A, Schoepf U, et al., 2020, Automated Plaque Analysis for the Prognostication of Major Adverse Cardiac Events. European Journal of Radiology, 2020(116): 76–83.

Lee S, Sung J, Rizvi A, et al., 2018, Quantification of Coronary Atherosclerosis in the Assessment of Coronary Artery Disease. Circulation: Cardiovascular Imaging, 11(7): e007562.

Gillies R, Kinahan P, Hricak H, 2016, Radiomics: Images are More than Pictures, They are Data. Radiology, 278(2), 563–577.

Chen Q, Xie G, Tang C, et al., 2023, Development and Validation of CCTA-based Radiomics Signature for Predicting Coronary Plaques With Rapid Progression. Circulation: Cardiovascular Imaging, 16(2): e014711.

Chen Q, Pan T, Wang Y, et al., 2023, A Coronary CT Angiography Radiomics Model to Identify Vulnerable Plaque and Predict Cardiovascular Events. Radiology, 307(2): e221693.

Han D, Kolli K, Al’Aref S, et al., 2020, Machine Learning Framework to Identify Individuals at Risk of Rapid Progression of Coronary Atherosclerosis: From the PARADIGM Registry. Journal of the American Heart Association, 9(5): e013958.

Motwani M, Dey D, Berman D, et al., 2017, Machine Learning for Prediction of All-Cause Mortality in Patients with Suspected Coronary Artery Disease: A 5-year Multicentre Prospective Registry Analysis. European Heart Journal, 38(6): 500–507.

Lin A, Manral N, McElhinney P, et al., 2022, Deep Learning-Enabled Coronary CT Angiography for Plaque and Stenosis Quantification and Cardiac Risk Prediction: An International Multicentre Study. The Lancet Digital Health, 4(4): e256–e265.

Sehly A, He A, Jaltotage B, et al., 2024, Coronary Artery Stenosis and Vulnerable Plaque Quantification on CCTA by Deep Learning Methods. European Heart Journal, 43(Supplement_1): ehad655.187.

Nicholls S, Hsu A, Wolski K, et al., 2010, Intravascular Ultrasound-Derived Measures of Coronary Atherosclerotic Plaque Burden and Clinical Outcome. Journal of the American College of Cardiology, 55(21): 2399–2407.

Feng C, Chen R, Dong S, et al., 2023, Predicting Coronary Plaque Progression with Conventional Plaque Parameters and Radiomics Features Derived from Coronary CT Angiography. European Radiology, 33(5): 3132–3143.

Mortensen M, Dzaye O, Steffensen F, et al., 2020, Impact of Plaque Burden Versus Stenosis on Ischemic Events in Patients With Coronary Atherosclerosis. Journal of the American College of Cardiology, 76(19): 2213–2222.

Byrne R, Rossello X, Coughlan J, et al., 2023, ESC Guidelines for the Management of Acute Coronary Syndromes. European Heart Journal, 44(38): 3720–3826.

Williams M, Kwiecinski J, Doris M, et al., 2020, Low-Attenuation Noncalcified Plaque on Coronary Computed Tomography Angiography Predicts Myocardial Infarction: Results From the Multicenter SCOT-HEART Trial (Scottish Computed Tomography of the HEART). Circulation, 141(18): 1452–1462.