Image-based biomechanical modeling for coronary atherosclerotic plaque progression and vulnerability prediction

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.

Fully automated construction of three-dimensional finite element simulations from Optical Coherence Tomography

Despite recent advances in diagnosis and treatment, atherosclerotic coronary artery diseases remain a leading cause of death worldwide. Various imaging modalities and metrics can detect lesions and predict patients at risk; however, identifying unstable lesions is still difficult. Current techniques cannot fully capture the complex morphology-modulated mechanical responses that affect plaque stability, leading to catastrophic failure and mute the benefit of device and drug interventions. Finite Element (FE) simulations utilizing intravascular imaging OCT (Optical Coherence Tomography) are effective in defining physiological stress distributions. However, creating 3D FE simulations of coronary arteries from OCT images is challenging to fully automate given OCT frame sparsity, limited material contrast, and restricted penetration depth. To address such limitations, we developed an algorithmic approach to automatically produce 3D FE-ready digital twins from labeled OCT images. The 3D models are anatomically faithful and recapitulate mechanically relevant tissue lesion components, automatically producing morphologies structurally similar to manually constructed models whilst including more minute details. A mesh convergence study highlighted the ability to reach stress and strain convergence with average errors of just 5.9% and 1.6% respectively in comparison to FE models with approximately twice the number of elements in areas of refinement. Such an automated procedure will enable analysis of large clinical cohorts at a previously unattainable scale and opens the possibility for in-silico methods for patient specific diagnoses and treatment planning for coronary artery disease.

Quantification of patient-specific coronary material properties and their correlations with plaque morphological characteristics: An in vivo IVUS study

BACKGROUND

A method using in vivo Cine IVUS and VH-IVUS data has been proposed to quantify material properties of coronary plaques. However, correlations between plaque morphological characteristics and mechanical properties have not been studied in vivo.

METHOD

In vivo Cine IVUS and VH-IVUS data were acquired at 32 plaque cross-sections from 19 patients. Six morphological factors were extracted for each plaque. These samples were categorized into healthy vessel, fibrous plaque, lipid-rich plaque and calcified plaque for comparisons. Three-dimensional thin-slice models were constructed using VH-IVUS data to quantify in vivo plaque material properties following a finite element updating approach by matching Cine IVUS data. Effective Young's moduli were calculated to represent plaque stiffness for easy comparison. Spearman's rank correlation analysis was performed to identify correlations between plaque stiffness and morphological factor. Kruskal-Wallis test with Bonferroni correction was used to determine whether significant differences in plaque stiffness exist among four plaque groups.

RESULT

Our results show that lumen circumference change has a significantly negative correlation with plaque stiffness (r = -0.7807, p = 0.0001). Plaque burden and calcification percent also had significant positive correlations with plaque stiffness (r = 0.5105, p < 0.0272 and r = 0.5312, p < 0.0193) respectively. Among the four categorized groups, calcified plaques had highest stiffness while healthy segments had the lowest.

CONCLUSION

There is a close link between plaque morphological characteristics and mechanical properties in vivo. Plaque stiffness tends to be higher as coronary atherosclerosis advances, indicating the potential to assess plaque mechanical properties in vivo based on plaque compositions.

Molecular imaging research in atherosclerosis: A 23-year scientometric and visual analysis

Background: Cardiovascular and cerebrovascular diseases are major global health problems, and the main cause is atherosclerosis. Recently, molecular imaging has been widely employed in the diagnosis and therapeutic applications of a variety of diseases, including atherosclerosis. Substantive facts have announced that molecular imaging has broad prospects in the early diagnosis and targeted treatment of atherosclerosis. Objective: We conducted a scientometric analysis of the scientific publications over the past 23 years on molecular imaging research in atherosclerosis, so as to identify the key progress, hotspots, and emerging trends. Methods: Original research and reviews regarding molecular imaging in atherosclerosis were retrieved from the Web of Science Core Collection database. Microsoft Excel 2021 was used to analyze the main findings. CiteSpace, VOSviewer, and a scientometric online platform were used to perform visualization analysis of the co-citation of journals and references, co-occurrence of keywords, and collaboration between countries/regions, institutions, and authors. Results: A total of 1755 publications were finally included, which were published by 795 authors in 443 institutions from 59 countries/regions. The United States was the top country in terms of the number and centrality of publications in this domain, with 810 papers and a centrality of 0.38, and Harvard University published the largest number of articles (182). Fayad, ZA was the most productive author, with 73 papers, while LIBBY P had the most co-citations (493). CIRCULATION was the top co-cited journal with a frequency of 1,411, followed by ARTERIOSCL THROM VAS (1,128). The co-citation references analysis identified eight clusters with a well-structured network (Q = 0.6439) and highly convincing clustering (S = 0.8865). All the studies calculated by keyword co-occurrence were divided into five clusters: "nanoparticle," "magnetic resonance imaging," "inflammation," "positron emission tomography," and "ultrasonography". Hot topics mainly focused on cardiovascular disease, contrast media, macrophage, vulnerable plaque, and microbubbles. Sodium fluoride ⁃PET, targeted drug delivery, OCT, photoacoustic imaging, ROS, and oxidative stress were identified as the potential trends. Conclusion: Molecular imaging research in atherosclerosis has attracted extensive attention in academia, while the challenges of clinical transformation faced in this field have been described in this review. The findings of the present research can inform funding agencies and researchers toward future directions.