Using intravascular ultrasound image-based fluid-structure interaction models and machine learning methods to predict human coronary plaque vulnerability change

Data-driven models for the prediction of coronary atherosclerotic plaque progression/regression

Coronary artery disease is defined by the existence of atherosclerotic plaque on the arterial wall, which can cause blood flow impairment, or plaque rupture, and ultimately lead to myocardial ischemia. Intravascular ultrasound (IVUS) imaging can provide a detailed characterization of lumen and vessel features, and so plaque burden, in coronary vessels. Prediction of the regions in a vascular segment where plaque burden can either increase (progression) or decrease (regression) following a certain therapy, has remained an elusive major milestone in cardiology. Studies like IBIS-4 showed an association between plaque burden regression and high-intensity rosuvastatin therapy over 13 months. Nevertheless, it has not been possible to predict if a patient would respond in a favorable/adverse fashion to such a treatment. This work aims to (i) Develop a framework that processes lumen and vessel cross-sectional contours and extracts geometric descriptors from baseline and follow-up IVUS pullbacks; and to (ii) Develop, train, and validate a machine learning model based on baseline/follow-up IVUS datasets that predicts future percent of atheroma volume changes in coronary vascular segments using only baseline information, i.e. geometric features and clinical data. This is a post hoc analysis, revisiting the IBIS-4 study. We employed 140 arteries, from 81 patients, for which expert delineation of lumen and vessel contours were available at baseline and 13-month follow-up. Contour data from baseline and follow-up pullbacks were co-registered and then processed to extract several frame-wise features, e.g. areas, plaque burden, eccentricity, etc. Each pullback was divided into regions of interest (ROIs), following different criteria. Frame-wise features were condensed into region-wise markers using tools from statistics, signal processing, and information theory. Finally, a stratified 5-fold cross-validation strategy (20 repetitions) was used to train/validate an XGBoost regression models. A feature selection method before the model training was also applied. When the models were trained/validated on ROI defined by the difference between follow-up and baseline plaque burden, the average accuracy and Mathews correlation coefficient were 0.70 and 0.41 respectively. Using a ROI partition criterion based only on the baseline's plaque burden resulted in averages of 0.60 accuracy and 0.23 Mathews correlation coefficient. An XGBoost model was capable of predicting plaque progression/regression changes in coronary vascular segments of patients treated with rosuvastatin therapy in 13 months. The proposed method, first of its kind, successfully managed to address the problem of stratification of patients at risk of coronary plaque progression, using IVUS images and standard patient clinical data.

Artificial Intelligence, Computational Simulations, and Extended Reality in Cardiovascular Interventions

Artificial intelligence, computational simulations, and extended reality, among other 21st century computational technologies, are changing the health care system. To collectively highlight the most recent advances and benefits of artificial intelligence, computational simulations, and extended reality in cardiovascular therapies, we coined the abbreviation AISER. The review particularly focuses on the following applications of AISER: 1) preprocedural planning and clinical decision making; 2) virtual clinical trials, and cardiovascular device research, development, and regulatory approval; and 3) education and training of interventional health care professionals and medical technology innovators. We also discuss the obstacles and constraints associated with the application of AISER technologies, as well as the proposed solutions. Interventional health care professionals, computer scientists, biomedical engineers, experts in bioinformatics and visualization, the device industry, ethics committees, and regulatory agencies are expected to streamline the use of AISER technologies in cardiovascular interventions and medicine in general.

Combining IVUS + OCT Data, Biomechanical Models and Machine Learning Method for Accurate Coronary Plaque Morphology Quantification and Cap Thickness and Stress/Strain Index Predictions

Assessment and prediction of vulnerable plaque progression and rupture risk are of utmost importance for diagnosis, management and treatment of cardiovascular diseases and possible prevention of acute cardiovascular events such as heart attack and stroke. However, accurate assessment of plaque vulnerability assessment and prediction of its future changes require accurate plaque cap thickness, tissue component and structure quantifications and mechanical stress/strain calculations. Multi-modality intravascular ultrasound (IVUS), optical coherence tomography (OCT) and angiography image data with follow-up were acquired from ten patients to obtain accurate and reliable plaque morphology for model construction. Three-dimensional thin-slice finite element models were constructed for 228 matched IVUS + OCT slices to obtain plaque stress/strain data for analysis. Quantitative plaque cap thickness and stress/strain indices were introduced as substitute quantitative plaque vulnerability indices (PVIs) and a machine learning method (random forest) was employed to predict PVI changes with actual patient IVUS + OCT follow-up data as the gold standard. Our prediction results showed that optimal prediction accuracies for changes in cap-PVI (C-PVI), mean cap stress PVI (meanS-PVI) and mean cap strain PVI (meanSn-PVI) were 90.3% (AUC = 0.877), 85.6% (AUC = 0.867) and 83.3% (AUC = 0.809), respectively. The improvements in prediction accuracy by the best combination predictor over the best single predictor were 6.6% for C-PVI, 10.0% for mean S-PVI and 8.0% for mean Sn-PVI. Our results demonstrated the potential using multi-modality IVUS + OCT image to accurately and efficiently predict plaque cap thickness and stress/strain index changes. Combining mechanical and morphological predictors may lead to better prediction accuracies.

The Continuum of Invasive Techniques for the Assessment of Intermediate Coronary Lesions

Ischemic heart disease is one of the most important causes of mortality and morbidity worldwide. Revascularization of coronary stenosis inducing ischemia, either by percutaneous or surgical intervention, significantly reduces major adverse cardiovascular events and improves quality of life. However, in cases of intermediate lesions, classified by a diameter stenosis between 50 and 90% by European guidelines and 40–70% in American counterparts with no clear evidence of ischemia, the indication of revascularization and impact is determined using various methods that altogether comprehensively evaluate the lesions. This review will discuss the various techniques to assess intermediate stenoses, highlighting indications and advantages, but also drawbacks. Fractional flow rate (FFR) and instantaneous wave-free ratio (iFR) are the gold standard for the functional evaluation of intermediate lesions, but there are clinical circumstances in which these pressure-wire-derived indices are not accurate. Complementary invasive investigations, mainly intravascular ultrasound and/or optical coherence tomography, offer parameters that can be correlated with FFR/iFR and additional insights into the morphology of the plaque guiding the eventual percutaneous intervention in terms of length and size of stents, thus improving the outcomes of the procedure. The development of artificial intelligence and machine learning with advanced algorithms of prediction will offer multiple scenarios for treatment, allowing real-time selection of the best strategy for revascularization.

Artificial Intelligence—A Good Assistant to Multi-Modality Imaging in Managing Acute Coronary Syndrome

Acute coronary syndrome is the leading cause of cardiac death and has a significant impact on patient prognosis. Early identification and proper management are key to ensuring better outcomes and have improved significantly with the development of various cardiovascular imaging modalities. Recently, the use of artificial intelligence as a method of enhancing the capability of cardiovascular imaging has grown. AI can inform the decision-making process, as it enables existing modalities to perform more efficiently and make more accurate diagnoses. This review demonstrates recent applications of AI in cardiovascular imaging to facilitate better patient care.

Predicting plaque vulnerability change using intravascular ultrasound + optical coherence tomography image-based fluid-structure interaction models and machine learning methods with patient follow-up data: a feasibility study

BACKGROUND

Coronary plaque vulnerability prediction is difficult because plaque vulnerability is non-trivial to quantify, clinically available medical image modality is not enough to quantify thin cap thickness, prediction methods with high accuracies still need to be developed, and gold-standard data to validate vulnerability prediction are often not available. Patient follow-up intravascular ultrasound (IVUS), optical coherence tomography (OCT) and angiography data were acquired to construct 3D fluid-structure interaction (FSI) coronary models and four machine-learning methods were compared to identify optimal method to predict future plaque vulnerability.

METHODS

Baseline and 10-month follow-up in vivo IVUS and OCT coronary plaque data were acquired from two arteries of one patient using IRB approved protocols with informed consent obtained. IVUS and OCT-based FSI models were constructed to obtain plaque wall stress/strain and wall shear stress. Forty-five slices were selected as machine learning sample database for vulnerability prediction study. Thirteen key morphological factors from IVUS and OCT images and biomechanical factors from FSI model were extracted from 45 slices at baseline for analysis. Lipid percentage index (LPI), cap thickness index (CTI) and morphological plaque vulnerability index (MPVI) were quantified to measure plaque vulnerability. Four machine learning methods (least square support vector machine, discriminant analysis, random forest and ensemble learning) were employed to predict the changes of three indices using all combinations of 13 factors. A standard fivefold cross-validation procedure was used to evaluate prediction results.

RESULTS

For LPI change prediction using support vector machine, wall thickness was the optimal single-factor predictor with area under curve (AUC) 0.883 and the AUC of optimal combinational-factor predictor achieved 0.963. For CTI change prediction using discriminant analysis, minimum cap thickness was the optimal single-factor predictor with AUC 0.818 while optimal combinational-factor predictor achieved an AUC 0.836. Using random forest for predicting MPVI change, minimum cap thickness was the optimal single-factor predictor with AUC 0.785 and the AUC of optimal combinational-factor predictor achieved 0.847.

CONCLUSION

This feasibility study demonstrated that machine learning methods could be used to accurately predict plaque vulnerability change based on morphological and biomechanical factors from multi-modality image-based FSI models. Large-scale studies are needed to verify our findings.