Related Experiment Video
Updated: Jan 27, 2026
Novel Percutaneous Approach for Deployment of 3D Printed Coronary Stenosis Implants in Swine Models of Ischemic Heart Disease
Published on: February 18, 2020
The best predictor of ischemic coronary stenosis: subtended myocardial volume, machine learning-based FFRCT, or
Mengmeng Yu1, Zhigang Lu2, Chengxing Shen2
1Institute of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, #600, Yishan Rd, Shanghai, 200233, China.
Insights
Machine learning-based fractional flow reserve computed tomography (FFRCT) and subtended myocardial volume effectively predict significant coronary stenosis. Subtended myocardial volume offers superior accuracy for borderline lesions compared to FFRCT alone.
Area of Science:
- Cardiovascular Imaging
- Artificial Intelligence in Medicine
- Interventional Cardiology
Background:
- Determining the hemodynamic significance of coronary stenosis is crucial for guiding revascularization decisions.
- Current methods like fractional flow reserve invasive (FFRICA) are invasive, while computed tomography angiography (CCTA) alone has limitations.
- Machine learning (ML)-based FFRCT and myocardial volume quantification offer non-invasive alternatives.
Purpose of the Study:
- To compare the diagnostic performance of ML-based FFRCT, quantified subtended myocardial volume (Vratio/MLD), and high-risk plaque features against FFRICA.
- To evaluate the incremental value of these parameters in predicting hemodynamically significant coronary stenosis.
Main Methods:
- Retrospective analysis of 180 patients with 208 lesions who underwent both CCTA and FFRICA.
- Parameters analyzed included ML-based FFRCT, Vratio/MLD, and high-risk plaque features.
- Lesions with FFRICA ≤ 0.8 were defined as hemodynamically significant.
Main Results:
- ML-based FFRCT and Vratio/MLD showed significant value in predicting hemodynamically significant lesions.
- The combination of FFRCT and Vratio/MLD achieved the highest diagnostic performance (AUC 0.935).
- High-risk plaque features did not significantly differentiate between functionally significant and insignificant lesions.
Conclusions:
- ML-based FFRCT and Vratio/MLD provide valuable, non-invasive assessment of coronary stenosis significance.
- Vratio/MLD demonstrated superior accuracy for borderline lesions (FFRCT 0.7-0.8) compared to ML-based FFRCT alone.
- CT-derived high-risk plaque features were not reliable predictors of hemodynamic significance.
Objectives:
The present study aimed to compare the diagnostic performance of a machine learning (ML)-based FFRCT algorithm, quantified subtended myocardial volume, and high-risk plaque features for predicting if a coronary stenosis is hemodynamically significant, with reference to FFRICA.
Methods:
Patients who underwent both CCTA and FFRICA measurement within 2 weeks were retrospectively included. ML-based FFRCT, volume of subtended myocardium (Vsub), percentage of subtended myocardium volume versus total myocardium volume (Vratio), high-risk plaque features, minimal lumen diameter (MLD), and minimal lumen area (MLA) along with other parameters were recorded. Lesions with FFRICA ≤ 0.8 were considered to be functionally significant.
Results:
One hundred eighty patients with 208 lesions were included. The lesion length (LL), diameter stenosis, area stenosis, plaque burden, Vsub, Vratio, Vratio/MLD, Vratio/MLA, and LL/MLD4 were all significantly longer or larger in the group of FFRICA ≤ 0.8 while smaller minimal lumen area, MLD, and FFRCT value were noted. The AUC of FFRCT + Vratio/MLD was significantly better than that of FFRCT alone (0.935 versus 0.873, p < 0.001). High-risk plaque features failed to show difference between functionally significant and insignificant groups. Vratio/MLD-complemented ML-based FFRCT for "gray zone" lesions with FFRCT value ranged from 0.7 to 0.8 and the combined use of these two parameters yielded the best diagnostic performance (86.5%, 180/208).
Conclusions:
ML-based FFRCT simulation and Vratio/MLD both provide incremental value over CCTA-derived diameter stenosis and high-risk plaque features for predicting hemodynamically significant lesions. Vratio/MLD is more accurate than ML-based FFRCT for lesions with simulated FFRCT value from 0.7 to 0.8.
Key Points:
• Machine learning-based FFR CT and subtended myocardium volume both performed well for predicting hemodynamically significant coronary stenosis. • Subtended myocardium volume was more accurate than machine learning-based FFR CT for "gray zone" lesions with simulated FFR value from 0.7 to 0.8. • CT-derived high-risk plaque features failed to correctly identify hemodynamically significant stenosis.
More Related Videos
06:19Constructing and Visualizing Models using Mime-based Machine-learning Framework
Published on: July 22, 2025
09:36A Magnetic Resonance Imaging-based Computational Protocol for Analysis of Plaque Morphology and Hemodynamics in Patients with Carotid Artery Stenosis
Published on: August 12, 2025
Related Concept Videos
01:23Mitral Stenosis II: Clinical features and Diagnostic Tests
01:19Machines
A free-body diagram of the...
01:12Relative Risk
01:30Machines: Problem Solving II
01:22Mitral Stenosis I: Introduction
01:22Machines: Problem Solving I
The toggle clamp system is a machine structure consisting of movable, pin-connected multi-force members that form a stabilized system to transmit forces. The...