Deep learning-based left ventricular segmentation demonstrates improved performance on respiratory motion-resolved whole-heart reconstructions.

Introduction: Deep learning (DL)-based segmentation has gained popularity for routine cardiac magnetic resonance (CMR) image analysis and in particular, delineation of left ventricular (LV) borders for LV volume determination. Free-breathing, self-navigated, whole-heart CMR exams provide high-resolution, isotropic coverage of the heart for assessment of cardiac anatomy including LV volume. The combination of whole-heart free-breathing CMR and DL-based LV segmentation has the potential to streamline the acquisition and analysis of clinical CMR exams. The purpose of this study was to compare the performance of a DL-based automatic LV segmentation network trained primarily on computed tomography (CT) images in two whole-heart CMR reconstruction methods: (1) an in-line respiratory motion-corrected (Mcorr) reconstruction and (2) an off-line, compressed sensing-based, multi-volume respiratory motion-resolved (Mres) reconstruction. Given that Mres images were shown to have greater image quality in previous studies than Mcorr images, we hypothesized that the LV volumes segmented from Mres images are closer to the manual expert-traced left ventricular endocardial border than the Mcorr images. Method: This retrospective study used 15 patients who underwent clinically indicated 1.5 T CMR exams with a prototype ECG-gated 3D radial phyllotaxis balanced steady state free precession (bSSFP) sequence. For each reconstruction method, the absolute volume difference (AVD) of the automatically and manually segmented LV volumes was used as the primary quantity to investigate whether 3D DL-based LV segmentation generalized better on Mcorr or Mres 3D whole-heart images. Additionally, we assessed the 3D Dice similarity coefficient between the manual and automatic LV masks of each reconstructed 3D whole-heart image and the sharpness of the LV myocardium-blood pool interface. A two-tail paired Student's t-test (alpha = 0.05) was used to test the significance in this study. Results & Discussion: The AVD in the respiratory Mres reconstruction was lower than the AVD in the respiratory Mcorr reconstruction: 7.73 ± 6.54 ml vs. 20.0 ± 22.4 ml, respectively (n = 15, p-value = 0.03). The 3D Dice coefficient between the DL-segmented masks and the manually segmented masks was higher for Mres images than for Mcorr images: 0.90 ± 0.02 vs. 0.87 ± 0.03 respectively, with a p-value = 0.02. Sharpness on Mres images was higher than on Mcorr images: 0.15 ± 0.05 vs. 0.12 ± 0.04, respectively, with a p-value of 0.014 (n = 15). Conclusion: We conclude that the DL-based 3D automatic LV segmentation network trained on CT images and fine-tuned on MR images generalized better on Mres images than on Mcorr images for quantifying LV volumes.

Extrapolation of Ventricular Activation Times From Sparse Electroanatomical Data Using Graph Convolutional Neural Networks.

Electroanatomic mapping is the gold standard for the assessment of ventricular tachycardia. Acquiring high resolution electroanatomic maps is technically challenging and may require interpolation methods to obtain dense measurements. These methods, however, cannot recover activation times in the entire biventricular domain. This work investigates the use of graph convolutional neural networks to estimate biventricular activation times from sparse measurements. Our method is trained on more than 15,000 synthetic examples of realistic ventricular depolarization patterns generated by a computational electrophysiology model. Using geometries sampled from a statistical shape model of biventricular anatomy, diverse wave dynamics are induced by randomly sampling scar and border zone distributions, locations of initial activation, and tissue conduction velocities. Once trained, the method accurately reconstructs biventricular activation times in left-out synthetic simulations with a mean absolute error of 3.9 ms ± 4.2 ms at a sampling density of one measurement sample per cm2. The total activation time is matched with a mean error of 1.4 ms ± 1.4 ms. A significant decrease in errors is observed in all heart zones with an increased number of samples. Without re-training, the network is further evaluated on two datasets: (1) an in-house dataset comprising four ischemic porcine hearts with dense endocardial activation maps; (2) the CRT-EPIGGY19 challenge data comprising endo- and epicardial measurements of 5 infarcted and 6 non-infarcted swines. In both setups the neural network recovers biventricular activation times with a mean absolute error of less than 10 ms even when providing only a subset of endocardial measurements as input. Furthermore, we present a simple approach to suggest new measurement locations in real-time based on the estimated uncertainty of the graph network predictions. The model-guided selection of measurement locations allows to reduce by 40% the number of measurements required in a random sampling strategy, while achieving the same prediction error. In all the tested scenarios, the proposed approach estimates biventricular activation times with comparable or better performance than a personalized computational model and significant runtime advantages.

Deep neural networks for ECG-free cardiac phase and end-diastolic frame detection on coronary angiographies.

Invasive coronary angiography (ICA) is the gold standard in Coronary Artery Disease (CAD) imaging. Detection of the end-diastolic frame (EDF) and, in general, cardiac phase detection on each temporal frame of a coronary angiography acquisition is of significant importance for the anatomical and non-invasive functional assessment of CAD. This task is generally performed via manual frame selection or semi-automated selection based on simultaneously acquired ECG signals - thus introducing the requirement of simultaneous ECG recordings. In this paper, we evaluate the performance of a purely image based workflow relying on deep neural networks for fully automated cardiac phase and EDF detection on coronary angiographies. A first deep neural network (DNN), trained to detect coronary arteries, is employed to preselect a subset of frames in which coronary arteries are well visible. A second DNN predicts cardiac phase labels for each frame. Only in the training and evaluation phases for the second DNN, ECG signals are used to provide ground truth labels for each angiographic frame. The networks were trained on 56,655 coronary angiographies from 6820 patients and evaluated on 20,780 coronary angiographies from 6261 patients. No exclusion criteria related to patient state (stable or acute CAD), previous interventions (PCI or CABG), or pathology were formulated. Cardiac phase detection had an accuracy of 98.8 %, a sensitivity of 99.3 % and a specificity of 97.6 % on the evaluation set. EDF prediction had a precision of 98.4 % and a recall of 97.9 %. Several sub-group analyses were performed, indicating that the cardiac phase detection performance is largely independent from acquisition angles, the heart rate of the patient, and the angiographic view (LCA / RCA). The average execution time of cardiac phase detection for one angiographic series was on average less than five seconds on a standard workstation. We conclude that the proposed image based workflow potentially obviates the need for manual frame selection and ECG acquisition, representing a relevant step towards automated CAD assessment.

Comprehensive preclinical evaluation of a multi-physics model of liver tumor radiofrequency ablation.

PURPOSE: We aim at developing a framework for the validation of a subject-specific multi-physics model of liver tumor radiofrequency ablation (RFA). METHODS: The RFA computation becomes subject specific after several levels of personalization: geometrical and biophysical (hemodynamics, heat transfer and an extended cellular necrosis model). We present a comprehensive experimental setup combining multimodal, pre- and postoperative anatomical and functional images, as well as the interventional monitoring of intra-operative signals: the temperature and delivered power. RESULTS: To exploit this dataset, an efficient processing pipeline is introduced, which copes with image noise, variable resolution and anisotropy. The validation study includes twelve ablations from five healthy pig livers: a mean point-to-mesh error between predicted and actual ablation extent of 5.3 ± 3.6 mm is achieved. CONCLUSION: This enables an end-to-end preclinical validation framework that considers the available dataset.

Personalized Computer Simulation of Diastolic Function in Heart Failure.

The search for a parameter representing left ventricular relaxation from non-invasive and invasive diagnostic tools has been extensive, since heart failure (HF) with preserved ejection fraction (HF-pEF) is a global health problem. We explore here the feasibility using patient-specific cardiac computer modeling to capture diastolic parameters in patients suffering from different degrees of systolic HF. Fifty eight patients with idiopathic dilated cardiomyopathy have undergone thorough clinical evaluation, including cardiac magnetic resonance imaging (MRI), heart catheterization, echocardiography, and cardiac biomarker assessment. A previously-introduced framework for creating multi-scale patient-specific cardiac models has been applied on all these patients. Novel parameters, such as global stiffness factor and maximum left ventricular active stress, representing cardiac active and passive tissue properties have been computed for all patients. Invasive pressure measurements from heart catheterization were then used to evaluate ventricular relaxation using the time constant of isovolumic relaxation Tau (τ). Parameters from heart catheterization and the multi-scale model have been evaluated and compared to patient clinical presentation. The model parameter global stiffness factor, representing diastolic passive tissue properties, is correlated significantly across the patient population with τ. This study shows that multi-modal cardiac models can successfully capture diastolic (dys) function, a prerequisite for future clinical trials on HF-pEF.

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.

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.

Computational fluid dynamics applied to virtually deployed drug-eluting coronary bioresorbable scaffolds: Clinical translations derived from a proof-of-concept.

BACKGROUND: Three-dimensional design simulations of coronary metallic stents utilizing mathematical and computational algorithms have emerged as important tools for understanding biomechanical stent properties, predicting the interaction of the implanted platform with the adjacent tissue, and informing stent design enhancements. Herein, we demonstrate the hemodynamic implications following virtual implantation of bioresorbable scaffolds using finite element methods and advanced computational fluid dynamics (CFD) simulations to visualize the device-flow interaction immediately after implantation and following scaffold resorption over time. METHODS AND RESULTS: CFD simulations with time averaged wall shear stress (WSS) quantification following virtual bioresorbable scaffold deployment in idealized straight and curved geometries were performed. WSS was calculated at the inflow, endoluminal surface (top surface of the strut), and outflow of each strut surface post-procedure (stage I) and at a time point when 33% of scaffold resorption has occurred (stage II). The average WSS at stage I over the inflow and outflow surfaces was 3.2 and 3.1 dynes/cm(2) respectively and 87.5 dynes/cm(2) over endoluminal strut surface in the straight vessel. From stage I to stage II, WSS increased by 100% and 142% over the inflow and outflow surfaces, respectively, and decreased by 27% over the endoluminal strut surface. In a curved vessel, WSS change became more evident in the inner curvature with an increase of 63% over the inflow and 66% over the outflow strut surfaces. Similar analysis at the proximal and distal edges demonstrated a large increase of 486% at the lateral outflow surface of the proximal scaffold edge. CONCLUSIONS: The implementation of CFD simulations over virtually deployed bioresorbable scaffolds demonstrates the transient nature of device/flow interactions as the bioresorption process progresses over time. Such hemodynamic device modeling is expected to guide future bioresorbable scaffold design.

Treatment planning for a TCPC test case: a numerical investigation under rigid and moving wall assumptions.

The hemodynamics in patients with total cavopulmonary connections (TCPC) is generally very complex and characterized by patient-to-patient variability. To better understand its effect on patients' outcome, CFD models are widely used, also to test and optimize surgical options before their implementation. These models often assume rigid geometries, despite the motion experienced by thoracic vessels that could influence the hemodynamics predictions. By improving their accuracy and expanding the range of simulated interventions, the benefit of treatment planning for patients is expected to increase. We simulate three types of intervention on a patient-specific 3D model, and compare their predicted outcome with baseline condition: a decrease in pulmonary vascular resistance obtainable with medications; a surgical revision of the connection design; the introduction of a fenestration in the TCPC wall. The simulations are performed both with rigid wall assumption and including patient-specific TCPC wall motion, reconstructed from a 4DMRI dataset. The results show the effect of each option on clinically important metrics and highlight the impact of patient-specific wall motion. The largest differences between rigid and moving wall models are observed in measures of energetic efficiency of TCPC as well as in hepatic flow distribution and transit time of seeded particles through the connection.

Assisted Fontan procedure: animal and in vitro models and computational fluid dynamics study.

Fontan connection with intermittent compression by wrapped latissimus dorsi (LD) was tested in vivo, in vitro and by means of computational fluid dynamics (CFD). Experimental study: LD was conditioned in four pigs for three weeks before Fontan connection by valved conduit wrapped with LD. Mock circuit: Inflatable cuff wrapped around valved conduit provided intermittent external compression, with pressure and flow measured at driving pressure of 8 or 16 mmHg. CFD study: A circuit was tested for possible increase above basal flow (4 l/min) with intermittent external compression. Experimental study: Intermittent conduit compression by LD provided mean 7% decrease of baseline PA pressure, with simultaneous flow increase of 2%. Mock circuit: By raising the driving pressure from 8 to 16 mmHg, the flow increased with baseline PVR (56%) and with elevated PVR (80%). Total pulmonary flow was reduced during intermittent external compression with both baseline and elevated PVR. CFD study: Compression with 13.0 mmHg provided 4.9% increase of total pulmonary flow with substantial increase of the peak flow (92%). In vivo and in vitro, the increased flow produced by compressing a conduit was confounded by the inevitable intermittent flow restriction. Mathematical model using lower pressure for intermittent external compression showed potential for increase in pulmonary flow.