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.

Stenting as porous media in anatomically accurate geometries. A comparison of models and spatial heterogeneity.

Modelling intracranial aneurysm blood flow after flow diverter treatment has proven to be of great scientific and clinical interest. One of the reasons for not having CFD as an everyday clinical tool yet is the time required to set-up such simulations plus the required computational time. The speed-up of these simulations can have a considerable impact during treatment planning and device selection. Modelling flow diverters as a porous medium (PM) can considerably improve the computational time. Many models have been presented in literature, but quantitative comparisons between models are scarce. In this study, the untreated case, the explicit definition of the flow diverter wires as no-slip boundary condition and five different porous medium models were chosen for comparison, and evaluated on intracranial aneurysm of 14 patients with different shapes, sizes, and locations. CFD simulations were made using finite volume method on steady flow conditions. Velocities, kinetic energy, wall shear stress, and computational time were assessed for each model. Then, all models are compared against the no-slip boundary condition using non parametric Kolmogorov-Smirnov test. The model with least performance showed a mean K-S statistic of 0.31 and deviance of 0.2, while the model with best values always gave K-S statistics below 0.2. Kinetic energy between PM models varied between an over estimation of 218.3% and an under estimation of 73.06%. Also, speedups were between 4.75x and 5.3x (stdev: 0.38x and 0.15x) when using PM models. Flow diverters can be simulated with PM with a good agreement to standard CFD simulations were FD wires are represented with no-slip boundary condition in less than a quarter of the time. Best results were obtained on PM models based on geometrical properties, in particular, when using a heterogeneous medium based on equations for flat rhomboidal wire frames.

A comparative study of porous medium CFD models for flow diverter stents: Advantages and shortcomings.

In computational fluid dynamics, there is a high interest in modeling flow diverter stents as porous media due to its reduced computational loads. One of the main difficulties of such models is proper parameter setup. Most authors assume flow diverter's wire screen as an isotropic and homogeneous medium, while others proposes anisotropic configurations, yet very little is discussed about the effect of these assumptions on model's accuracy. In this paper, we compare the effect of different models on hemodynamics in relation to their parameters. The fidelity and efficiency of the different models to capture wire screen effect on fluid flow are quantitatively analyzed and compared.