Hemodynamic Modeling, Medical Imaging, and Machine Learning and Their Applications to Cardiovascular Interventions

Kadem, Mason; Garber, Louis; Abdelkhalek, Mohamed; Al‐Khazraji, Baraa K.; Keshavarz‐Motamed, Zahra

doi:10.1109/rbme.2022.3142058

Cited by 35 publications

(15 citation statements)

References 179 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past decade, the use of medical imaging has drastically increased. In spite of amazing advancements in medical imaging, medical imaging on its own cannot quantify local and global hemodynamics in coronaries 120 , 121 . As the need for patient-specific diagnostic methods continues to be studied, understanding the strengths and limitations of imaging modalities for coronaries is critical toward creating precise diagnostic tools:(1) Computed tomography coronary angiography (CTCA) : CTCA has a high spatial resolution allowing for visualization of coronary plaque and stenosis geometry 22 , 122 .…”

Section: Discussionmentioning

confidence: 99%

Long-term prognostic impact of paravalvular leakage on coronary artery disease requires patient-specific quantification of hemodynamics

Khodaei

Garber

Bauer

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

Transcatheter aortic valve replacement (TAVR) is a frequently used minimally invasive intervention for patient with aortic stenosis across a broad risk spectrum. While coronary artery disease (CAD) is present in approximately half of TAVR candidates, correlation of post-TAVR complications such as paravalvular leakage (PVL) or misalignment with CAD are not fully understood. For this purpose, we developed a multiscale computational framework based on a patient-specific lumped-parameter algorithm and a 3-D strongly-coupled fluid–structure interaction model to quantify metrics of global circulatory function, metrics of global cardiac function and local cardiac fluid dynamics in 6 patients. Based on our findings, PVL limits the benefits of TAVR and restricts coronary perfusion due to the lack of sufficient coronary blood flow during diastole phase (e.g., maximum coronary flow rate reduced by 21.73%, 21.43% and 21.43% in the left anterior descending (LAD), left circumflex (LCX) and right coronary artery (RCA) respectively (N = 6)). Moreover, PVL may increase the LV load (e.g., LV load increased by 17.57% (N = 6)) and decrease the coronary wall shear stress (e.g., maximum wall shear stress reduced by 20.62%, 21.92%, 22.28% and 25.66% in the left main coronary artery (LMCA), left anterior descending (LAD), left circumflex (LCX) and right coronary artery (RCA) respectively (N = 6)), which could promote atherosclerosis development through loss of the physiological flow-oriented alignment of endothelial cells. This study demonstrated that a rigorously developed personalized image-based computational framework can provide vital insights into underlying mechanics of TAVR and CAD interactions and assist in treatment planning and patient risk stratification in patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Long-term prognostic impact of paravalvular leakage on coronary artery disease requires patient-specific quantification of hemodynamics

Khodaei

Garber

Bauer

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine learning methods have been predominantly used in conjunction with medical images and other medical data 69 70 to train multiple non-linear classifiers (support vector machine, logistic regression, tree-based models, deep neural networks) to predict mortality rates. 71 72 CTCA applied deep learning applications allowed detection and quantification of calcified plaques, 73–75 as well as correlating calcium score to mortality.…”

Section: Discussionmentioning

confidence: 99%

A new and automated risk prediction of coronary artery disease using clinical endpoints and medical imaging-derived patient-specific insights: protocol for the retrospective GeoCAD cohort study

et al. 2022

View full text Add to dashboard Cite

IntroductionCoronary artery disease (CAD) is the leading cause of death worldwide. More than a quarter of cardiovascular events are unexplained by current absolute cardiovascular disease risk calculators, and individuals without clinical risk factors have been shown to have worse outcomes. The ‘anatomy of risk’ hypothesis recognises that adverse anatomical features of coronary arteries enhance atherogenic haemodynamics, which in turn mediate the localisation and progression of plaques. We propose a new risk prediction method predicated on CT coronary angiography (CTCA) data and state-of-the-art machine learning methods based on a better understanding of anatomical risk for CAD. This may open new pathways in the early implementation of personalised preventive therapies in susceptible individuals as a potential key in addressing the growing burden of CAD.Methods and analysisGeoCAD is a retrospective cohort study in 1000 adult patients who have undergone CTCA for investigation of suspected CAD. It is a proof-of-concept study to test the hypothesis that advanced image-derived patient-specific data can accurately predict long-term cardiovascular events. The objectives are to (1) profile CTCA images with respect to variations in anatomical shape and associated haemodynamic risk expressing, at least in part, an individual’s CAD risk, (2) develop a machine-learning algorithm for the rapid assessment of anatomical risk directly from unprocessed CTCA images and (3) to build a novel CAD risk model combining traditional risk factors with these novel anatomical biomarkers to provide a higher accuracy CAD risk prediction tool.Ethics and disseminationThe study protocol has been approved by the St Vincent’s Hospital Human Research Ethics Committee, Sydney—2020/ETH02127 and the NSW Population and Health Service Research Ethics Committee—2021/ETH00990. The project outcomes will be published in peer-reviewed and biomedical journals, scientific conferences and as a higher degree research thesis.

show abstract

“…It is noteworthy to mention that Newtonian behavior has been used to model the blood, which is adequate for shear rates >100 s −1 [46,47]. The fluid-structure interaction (FSI) has received significant attention in research related to cardiovascular modeling [48][49][50][51][52][53][54][55]. In this study, FSI only pertains to the convective heat-sink (cooling) effect induced by the blood flow during cardiac ablation, as the cardiac tissue has been modeled as a rigid body.…”

Section: Methodsmentioning

confidence: 99%

Three-Phase-Lag Bio-Heat Transfer Model of Cardiac Ablation

Singh

Saccomandi

Melnik

2022

Fluids

View full text Add to dashboard Cite

Significant research efforts have been devoted in the past decades to accurately modelling the complex heat transfer phenomena within biological tissues. These modeling efforts and analysis have assisted in a better understanding of the intricacies of associated biological phenomena and factors that affect the treatment outcomes of hyperthermic therapeutic procedures. In this contribution, we report a three-dimensional non-Fourier bio-heat transfer model of cardiac ablation that accounts for the three-phase-lags (TPL) in the heat propagation, viz., lags due to heat flux, temperature gradient, and thermal displacement gradient. Finite element-based COMSOL Multiphysics software has been utilized to predict the temperature distributions and ablation volumes. A comparative analysis has been conducted to report the variation in the treatment outcomes of cardiac ablation considering different bio-heat transfer models. The effect of variations in the magnitude of different phase lags has been systematically investigated. The fidelity and integrity of the developed model have been evaluated by comparing the results of the developed model with the analytical results of the recent studies available in the literature. This study demonstrates the importance of considering non-Fourier lags within biological tissue for predicting more accurately the characteristics important for the efficient application of thermal therapies.

show abstract

Hemodynamic Modeling, Medical Imaging, and Machine Learning and Their Applications to Cardiovascular Interventions

Cited by 35 publications

References 179 publications

Long-term prognostic impact of paravalvular leakage on coronary artery disease requires patient-specific quantification of hemodynamics

Long-term prognostic impact of paravalvular leakage on coronary artery disease requires patient-specific quantification of hemodynamics

A new and automated risk prediction of coronary artery disease using clinical endpoints and medical imaging-derived patient-specific insights: protocol for the retrospective GeoCAD cohort study

Three-Phase-Lag Bio-Heat Transfer Model of Cardiac Ablation

Contact Info

Product

Resources

About