Lucian Mihai Itu

A machine-learning approach for computation of fractional flow reserve from coronary computed tomography

Fractional flow reserve (FFR) is a functional index quantifying the severity of coronary artery lesions and is clinically obtained using an invasive, catheter-based measurement. Recently, physics-based models have shown great promise in being able to noninvasively estimate FFR from patient-specific anatomical information, e.g., obtained from computed tomography scans of the heart and the coronary arteries. However, these models have high computational demand, limiting their clinical adoption. In this paper, we present a machine-learning-based model for predicting FFR as an alternative to physics-based approaches. The model is trained on a large database of synthetically generated coronary anatomies, where the target values are computed using the physics-based model. The trained model predicts FFR at each point along the centerline of the coronary tree, and its performance was assessed by comparing the predictions against physics-based computations and against invasively measured FFR for 87 patients and 125 lesions in total. Correlation between machine-learning and physics-based predictions was excellent (0.9994, P < 0.001), and no systematic bias was found in Bland-Altman analysis: mean difference was -0.00081 ± 0.0039. Invasive FFR ≤ 0.80 was found in 38 lesions out of 125 and was predicted by the machine-learning algorithm with a sensitivity of 81.6%, a specificity of 83.9%, and an accuracy of 83.2%. The correlation was 0.729 (P < 0.001). Compared with the physics-based computation, average execution time was reduced by more than 80 times, leading to near real-time assessment of FFR. Average execution time went down from 196.3 ± 78.5 s for the CFD model to ∼2.4 ± 0.44 s for the machine-learning model on a workstation with 3.4-GHz Intel i7 8-core processor.

A patient-specific reduced-order model for coronary circulation

We introduce a patient-specific model for coronary circulation, by combining anatomical, hemodynamic and functional information from medical images and other clinical observations. The main components of the coupled model are: a lumped heart model, a reduced-order model for hemodynamics in the arterial vessel tree (both healthy and stenosed), and a physiological model for the microvascular bed. The anatomy of the vessel tree is extracted from Coronary Computed Tomography Angiography (CTA) images, followed by an estimation of the impedance of the distal microvascular network. For the blood flow simulations, three states are modeled: rest, drug-induced hyperemia and intense exercise. The results show an excellent agreement with the literature and provide a model for virtual assessment of the flow and underlying functional measures in healthy and stenosed coronary arteries.

A framework for personalization of coronary flow computations during rest and hyperemia

We introduce a Computational Fluid Dynamics (CFD) based method for performing patient-specific coronary hemodynamic computations under two conditions: at rest and during drug-induced hyperemia. The proposed method is based on a novel estimation procedure for determining the boundary conditions from non-invasively acquired patient data at rest. A multi-variable feedback control framework ensures that the computed mean arterial pressure and the flow distribution matches the estimated values for an individual patient during the rest state. The boundary conditions at hyperemia are derived from the respective rest-state values via a transfer function that models the vasodilation phenomenon. Simulations are performed on a coronary tree where a 65% diameter stenosis is introduced in the left anterior descending (LAD) artery, with the boundary conditions estimated using the proposed method. The results demonstrate that the estimation of the hyperemic resistances is crucial in order to obtain accurate values for pressure and flow rates. Results from an exhaustive sensitivity analysis have been presented for analyzing the variability of trans-stenotic pressure drop and Fractional Flow Reserve (FFR) values with respect to various measurements and assumptions.

Comparison of Fractional Flow Reserve Based on Computational Fluid Dynamics Modeling Using Coronary Angiographic Vessel Morphology Versus Invasively Measured Fractional Flow Reserve

Invasive fractional flow reserve (FFRinvasive), although gold standard to identify hemodynamically relevant coronary stenoses, is time consuming and potentially associated with complications. We developed and evaluated a new approach to determine lesion-specific FFR on the basis of coronary anatomy as visualized by invasive coronary angiography (FFRangio): 100 coronary lesions (50% to 90% diameter stenosis) in 73 patients (48 men, 25 women; mean age 67 ± 9 years) were studied. On the basis of coronary angiograms acquired at rest from 2 views at angulations at least 30° apart, a PC-based computational fluid dynamics modeling software used personalized boundary conditions determined from 3-dimensional reconstructed angiography, heart rate, and blood pressure to derive FFRangio. The results were compared with FFRinvasive. Interobserver variability was determined in a subset of 25 narrowings. Twenty-nine of 100 coronary lesions were hemodynamically significant (FFRinvasive ≤ 0.80). FFRangio identified these with an accuracy of 90%, sensitivity of 79%, specificity of 94%, positive predictive value of 85%, and negative predictive value of 92%. The area under the receiver operating characteristic curve was 0.93. Correlation between FFRinvasive (mean: 0.84 ± 0.11) and FFRangio (mean: 0.85 ± 0.12) was r = 0.85. Interobserver variability of FFRangio was low, with a correlation of r = 0.88. In conclusion, estimation of coronary FFR with PC-based computational fluid dynamics modeling on the basis of lesion morphology as determined by invasive angiography is possible with high diagnostic accuracy compared to invasive measurements.

Coronary CT angiography derived fractional flow reserve: Methodology and evaluation of a point of care algorithm

BACKGROUND Recently several publications described the diagnostic value of coronary CT angiography (coronary CTA) derived fractional flow reserve (CTA-FFR). For a recently introduced on-site CTA-FFR application, detailed methodology and factors potentially affecting performance have not yet been described. OBJECTIVE To provide a methodological background for an on-site CTA-FFR application and evaluate the effect of patient and acquisition characteristics. METHODS The on-site CTA-FFR application utilized a reduced-order hybrid model applying pressure drop models within stenotic regions. In 116 patients and 203 vessels the diagnostic performance of CTA-FFR was investigated using invasive FFR measurements as a reference. The effect of several potentially relevant factors on CTA-FFR was investigated. RESULTS 90 vessels (44%) had a hemodynamically relevant stenosis according to invasive FFR (threshold ≤0.80). The overall vessel-based sensitivity, specificity and accuracy of CTA-FFR were 88% (CI 95%:79-94%), 65% (55-73%) and 75% (69-81%). The specificity was significantly lower in the presence of misalignment artifacts (25%, CI: 6-57%). A non-significant reduction in specificity from 74% (60-85%) to 48% (26-70%) was found for higher coronary artery calcium scores. Left ventricular mass, diabetes mellitus and large vessel size increased the discrepancy between invasive FFR and CTA-FFR values. CONCLUSIONS On-site calculation of CTA-FFR can identify hemodynamically significant CAD with an overall per-vessel accuracy of 75% in comparison to invasive FFR. The diagnostic performance of CTA-FFR is negatively affected by misalignment artifacts. CTA-FFR is potentially affected by left ventricular mass, diabetes mellitus and vessel size.

A parameter estimation framework for patient-specific hemodynamic computations

We propose a fully automated parameter estimation framework for performing patient-specific hemodynamic computations in arterial models. To determine the personalized values of the windkessel models, which are used as part of the geometrical multiscale circulation model, a parameter estimation problem is formulated. Clinical measurements of pressure and/or flow-rate are imposed as constraints to formulate a nonlinear system of equations, whose fixed point solution is sought. A key feature of the proposed method is a warm-start to the optimization procedure, with better initial solution for the nonlinear system of equations, to reduce the number of iterations needed for the calibration of the geometrical multiscale models. To achieve these goals, the initial solution, computed with a lumped parameter model, is adapted before solving the parameter estimation problem for the geometrical multiscale circulation model: the resistance and the compliance of the circulation model are estimated and compensated.The proposed framework is evaluated on a patient-specific aortic model, a full body arterial model, and multiple idealized anatomical models representing different arterial segments. For each case it leads to the best performance in terms of number of iterations required for the computational model to be in close agreement with the clinical measurements.

GPU accelerated blood flow computation using the Lattice Boltzmann Method

We propose a numerical implementation based on a Graphics Processing Unit (GPU) for the acceleration of the execution time of the Lattice Boltzmann Method (LBM). The study focuses on the application of the LBM for patient-specific blood flow computations, and hence, to obtain higher accuracy, double precision computations are employed. The LBM specific operations are grouped into two kernels, whereas only one of them uses information from neighboring nodes. Since for blood flow computations regularly only 1/5 or less of the nodes represent fluid nodes, an indirect addressing scheme is used to reduce the memory requirements. Three GPU cards are evaluated with different 3D benchmark applications (Poisseuille flow, lid-driven cavity flow and flow in an elbow shaped domain) and the best performing card is used to compute blood flow in a patient-specific aorta geometry with coarctation. The speed-up over a multi-threaded CPU code is of 19.42x. The comparison with a basic GPU based LBM implementation demonstrates the importance of the optimization activities.

Hemodynamic assessment of pre- and post-operative aortic coarctation from MRI

Coarctation of the aorta (CoA), is a congenital defect characterized by a severe narrowing of the aorta, usually distal to the aortic arch. The treatment options include surgical repair, stent implantation, and balloon angioplasty. In order to evaluate the physiological significance of the pre-operative coarctation and to assess the post-operative results, the hemodynamic analysis is usually performed by measuring the pressure gradient (deltaP) across the coarctation site via invasive cardiac catheterization. The measure of success is reduction of the (deltaP > 20 mmHg) systolic blood pressure gradient. In this paper, we propose a non-invasive method based on Computational Fluid Dynamics and MR imaging to estimate the pre- and post-operative hemodynamics for both native and recurrent coarctation patients. High correlation of our results and catheter measurements is shown on corresponding pre- and post-operative examination of 5 CoA patients.

Optimized three-dimensional stencil computation on Fermi and Kepler GPUs

Stencil based algorithms are used intensively in scientific computations. Graphics Processing Units (GPU) based implementations of stencil computations speed-up the execution significantly compared to conventional CPU only systems. In this paper we focus on double precision stencil computations, which are required for meeting the high accuracy requirements, inherent for scientific computations. Starting from two baseline implementations (using two dimensional and three dimensional thread block structures respectively), we employ different optimization techniques which lead to seven kernel versions. Both Fermi and Kepler GPUs are used, to evaluate the impact of different optimization techniques for the two architectures. Overall, the GTX680 GPU card performs best for a kernel with 2D thread block structure and optimized register and shared memory usage. We show that, whereas shared memory is not essential for Fermi GPUs, it is a highly efficient optimization technique for Kepler GPUs (mainly due to the different L1 cache usage). Furthermore, we evaluate the performance of Kepler GPU cards designed for desktop PCs and notebook PCs. The results indicate that the ratio of execution time is roughly equal to the inverse of the ratio of power consumption.

Graphics processing unit accelerated one-dimensional blood flow computation in the human arterial tree

One-dimensional blood flow models have been used extensively for computing pressure and flow waveforms in the human arterial circulation. We propose an improved numerical implementation based on a graphics processing unit (GPU) for the acceleration of the execution time of one-dimensional model. A novel parallel hybrid CPU-GPU algorithm with compact copy operations (PHCGCC) and a parallel GPU only (PGO) algorithm are developed, which are compared against previously introduced PHCG versions, a single-threaded CPU only algorithm and a multi-threaded CPU only algorithm. Different second-order numerical schemes (Lax-Wendroff and Taylor series) are evaluated for the numerical solution of one-dimensional model, and the computational setups include physiologically motivated non-periodic (Windkessel) and periodic boundary conditions (BC) (structured tree) and elastic and viscoelastic wall laws. Both the PHCGCC and the PGO implementations improved the execution time significantly. The speed-up values over the single-threaded CPU only implementation range from 5.26 to 8.10 × , whereas the speed-up values over the multi-threaded CPU only implementation range from 1.84 to 4.02 × . The PHCGCC algorithm performs best for an elastic wall law with non-periodic BC and for viscoelastic wall laws, whereas the PGO algorithm performs best for an elastic wall law with periodic BC.