RESUMEN
PURPOSE: Use a conference challenge format to compare machine learning-based gamma-aminobutyric acid (GABA)-edited magnetic resonance spectroscopy (MRS) reconstruction models using one-quarter of the transients typically acquired during a complete scan. METHODS: There were three tracks: Track 1: simulated data, Track 2: identical acquisition parameters with in vivo data, and Track 3: different acquisition parameters with in vivo data. The mean squared error, signal-to-noise ratio, linewidth, and a proposed shape score metric were used to quantify model performance. Challenge organizers provided open access to a baseline model, simulated noise-free data, guides for adding synthetic noise, and in vivo data. RESULTS: Three submissions were compared. A covariance matrix convolutional neural network model was most successful for Track 1. A vision transformer model operating on a spectrogram data representation was most successful for Tracks 2 and 3. Deep learning (DL) reconstructions with 80 transients achieved equivalent or better SNR, linewidth and fit error compared to conventional 320 transient reconstructions. However, some DL models optimized linewidth and SNR without actually improving overall spectral quality, indicating a need for more robust metrics. CONCLUSION: DL-based reconstruction pipelines have the promise to reduce the number of transients required for GABA-edited MRS.
Asunto(s)
Aprendizaje Profundo , Espectroscopía de Resonancia Magnética , Relación Señal-Ruido , Ácido gamma-Aminobutírico , Ácido gamma-Aminobutírico/metabolismo , Humanos , Espectroscopía de Resonancia Magnética/métodos , Redes Neurales de la Computación , Algoritmos , Encéfalo/diagnóstico por imagen , Encéfalo/metabolismo , Aprendizaje Automático , Procesamiento de Imagen Asistido por Computador/métodos , Simulación por ComputadorRESUMEN
To enable large in silico trials and personalized model predictions on clinical timescales, it is imperative that models can be constructed quickly and reproducibly. First, we aimed to overcome the challenges of constructing cardiac models at scale through developing a robust, open-source pipeline for bilayer and volumetric atrial models. Second, we aimed to investigate the effects of fibres, fibrosis and model representation on fibrillatory dynamics. To construct bilayer and volumetric models, we extended our previously developed coordinate system to incorporate transmurality, atrial regions and fibres (rule-based or data driven diffusion tensor magnetic resonance imaging (MRI)). We created a cohort of 1000 biatrial bilayer and volumetric models derived from computed tomography (CT) data, as well as models from MRI, and electroanatomical mapping. Fibrillatory dynamics diverged between bilayer and volumetric simulations across the CT cohort (correlation coefficient for phase singularity maps: left atrial (LA) 0.27 ± 0.19, right atrial (RA) 0.41 ± 0.14). Adding fibrotic remodelling stabilized re-entries and reduced the impact of model type (LA: 0.52 ± 0.20, RA: 0.36 ± 0.18). The choice of fibre field has a small effect on paced activation data (less than 12 ms), but a larger effect on fibrillatory dynamics. Overall, we developed an open-source user-friendly pipeline for generating atrial models from imaging or electroanatomical mapping data enabling in silico clinical trials at scale (https://github.com/pcmlab/atrialmtk).
RESUMEN
Computational models of the heart are now being used to assess the effectiveness and feasibility of interventions through in-silico clinical trials (ISCTs). As the adoption and acceptance of ISCTs increases, best practices for reporting the methodology and analysing the results will emerge. Focusing in the area of cardiology, we aim to evaluate the types of ISCTs, their analysis methods and their reporting standards. To this end, we conducted a systematic review of cardiac ISCTs over the period of 1 January 2012-1 January 2022, following the preferred reporting items for systematic reviews and meta-analysis (PRISMA). We considered cardiac ISCTs of human patient cohorts, and excluded studies of single individuals and those in which models were used to guide a procedure without comparing against a control group. We identified 36 publications that described cardiac ISCTs, with most of the studies coming from the US and the UK. In 75% of the studies, a validation step was performed, although the specific type of validation varied between the studies. ANSYS FLUENT was the most commonly used software in 19% of ISCTs. The specific software used was not reported in 14% of the studies. Unlike clinical trials, we found a lack of consistent reporting of patient demographics, with 28% of the studies not reporting them. Uncertainty quantification was limited, with sensitivity analysis performed in only 19% of the studies. In 97% of the ISCTs, no link was provided to provide easy access to the data or models used in the study. There was no consistent naming of study types with a wide range of studies that could potentially be considered ISCTs. There is a clear need for community agreement on minimal reporting standards on patient demographics, accepted standards for ISCT cohort quality control, uncertainty quantification, and increased model and data sharing.
RESUMEN
AIMS: Anti-tachycardia pacing (ATP) is a reliable electrotherapy to painlessly terminate ventricular tachycardia (VT). However, ATP is often ineffective, particularly for fast VTs. The efficacy may be enhanced by optimized delivery closer to the re-entrant circuit driving the VT. This study aims to compare ATP efficacy for different delivery locations with respect to the re-entrant circuit, and further optimize ATP by minimizing failure through re-initiation. METHODS AND RESULTS: Seventy-three sustained VTs were induced in a cohort of seven infarcted porcine ventricular computational models, largely dominated by a single re-entrant pathway. The efficacy of burst ATP delivered from three locations proximal to the re-entrant circuit (septum) and three distal locations (lateral/posterior left ventricle) was compared. Re-initiation episodes were used to develop an algorithm utilizing correlations between successive sensed electrogram morphologies to automatically truncate ATP pulse delivery. Anti-tachycardia pacing was more efficacious at terminating slow compared with fast VTs (65 vs. 46%, P = 0.000039). A separate analysis of slow VTs showed that the efficacy was significantly higher when delivered from distal compared with proximal locations (distal 72%, proximal 59%), being reversed for fast VTs (distal 41%, proximal 51%). Application of our early termination detection algorithm (ETDA) accurately detected VT termination in 79% of re-initiated cases, improving the overall efficacy for proximal delivery with delivery inside the critical isthmus (CI) itself being overall most effective. CONCLUSION: Anti-tachycardia pacing delivery proximal to the re-entrant circuit is more effective at terminating fast VTs, but less so slow VTs, due to frequent re-initiation. Attenuating re-initiation, through ETDA, increases the efficacy of delivery within the CI for all VTs.
Asunto(s)
Desfibriladores Implantables , Taquicardia Ventricular , Porcinos , Animales , Cicatriz/etiología , Cicatriz/terapia , Estimulación Cardíaca Artificial/métodos , Taquicardia Ventricular/terapia , Ventrículos Cardíacos , Adenosina TrifosfatoRESUMEN
Previous patient-specific model calibration techniques have treated each patient independently, making the methods expensive for large-scale clinical adoption. In this work, we show how we can reuse simulations to accelerate the patient-specific model calibration pipeline. To represent anatomy, we used a Statistical Shape Model and to represent function, we ran electrophysiological simulations. We study the use of 14 biomarkers to calibrate the model, training one Gaussian Process Emulator (GPE) per biomarker. To fit the models, we followed a Bayesian History Matching (BHM) strategy, wherein each iteration a region of the parameter space is ruled out if the emulation with that set of parameter values produces is "implausible". We found that without running any extra simulations we can find 87.41% of the non-implausible parameter combinations. Moreover, we showed how reducing the uncertainty of the measurements from 10 to 5% can reduce the final parameter space by 6 orders of magnitude. This innovation allows for a model fitting technique, therefore reducing the computational load of future biomedical studies.
Asunto(s)
Corazón , Modelos Estadísticos , Humanos , Teorema de Bayes , Calibración , IncertidumbreRESUMEN
Cardiac mechanics models are developed to represent a high level of detail, including refined anatomies, accurate cell mechanics models, and platforms to link microscale physiology to whole-organ function. However, cardiac biomechanics models still have limited clinical translation. In this review, we provide a picture of cardiac mechanics models, focusing on their clinical translation. We review the main experimental and clinical data used in cardiac models, as well as the steps followed in the literature to generate anatomical meshes ready for simulations. We describe the main models in active and passive mechanics and the different lumped parameter models to represent the circulatory system. Lastly, we provide a summary of the state-of-the-art in terms of ventricular, atrial, and four-chamber cardiac biomechanics models. We discuss the steps that may facilitate clinical translation of the biomechanics models we describe. A well-established software to simulate cardiac biomechanics is lacking, with all available platforms involving different levels of documentation, learning curves, accessibility, and cost. Furthermore, there is no regulatory framework that clearly outlines the verification and validation requirements a model has to satisfy in order to be reliably used in applications. Finally, better integration with increasingly rich clinical and/or experimental datasets as well as machine learning techniques to reduce computational costs might increase model reliability at feasible resources. Cardiac biomechanics models provide excellent opportunities to be integrated into clinical workflows, but more refinement and careful validation against clinical data are needed to improve their credibility. In addition, in each context of use, model complexity must be balanced with the associated high computational cost of running these models.
RESUMEN
[This corrects the article DOI: 10.1371/journal.pcbi.1008851.].
RESUMEN
Computational Fluid Dynamics (CFD) is used to assist in designing artificial valves and planning procedures, focusing on local flow features. However, assessing the impact on overall cardiovascular function or predicting longer-term outcomes may requires more comprehensive whole heart CFD models. Fitting such models to patient data requires numerous computationally expensive simulations, and depends on specific clinical measurements to constrain model parameters, hampering clinical adoption. Surrogate models can help to accelerate the fitting process while accounting for the added uncertainty. We create a validated patient-specific four-chamber heart CFD model based on the Navier-Stokes-Brinkman (NSB) equations and test Gaussian Process Emulators (GPEs) as a surrogate model for performing a variance-based global sensitivity analysis (GSA). GSA identified preload as the dominant driver of flow in both the right and left side of the heart, respectively. Left-right differences were seen in terms of vascular outflow resistances, with pulmonary artery resistance having a much larger impact on flow than aortic resistance. Our results suggest that GPEs can be used to identify parameters in personalized whole heart CFD models, and highlight the importance of accurate preload measurements.
Asunto(s)
Corazón Auxiliar , Modelos Cardiovasculares , Simulación por Computador , Hemodinámica , Humanos , HidrodinámicaRESUMEN
Lead position is an important factor in determining response to Cardiac Resynchronization Therapy (CRT) in dyssynchronous heart failure (HF) patients. Multipoint pacing (MPP) enables pacing from multiple electrodes within the same lead, improving the potential outcome for patients. Virtual quadripolar lead designs were evaluated by simulating pacing from all combinations of 1 and 2 electrodes along the lead in each virtual patient from cohorts of HF (n = 24) and simulated reverse remodelled (RR, n = 20) patients. Electrical synchrony was assessed by the time 90% of the ventricular myocardium is activated (AT090). Optimal 1 and 2 electrode pacing configurations for AT090 were combined to identify the 4-electrode lead design that maximised benefits across all patients. LV pacing in the HF cohort in all possible single and double electrode locations reduced AT090 by 14.48 ± 5.01 ms (11.92 ± 3.51%). The major determinant of reduction in activation time was patient anatomy. Pacing with a single optimal lead design reduced AT090 more in the HF cohort than the RR cohort (12.68 ± 3.29% vs 10.81 ± 2.34%). Pacing with a single combined HF and RR population-optimised lead design achieves electrical resynchronization with near equivalence to personalised lead designs both in HF and RR anatomies. These findings suggest that although lead configurations have to be tailored to each patient, a single optimal lead design is sufficient to obtain near-optimal results across most patients. This study shows the potential of virtual clinical trials as tools to compare existing and explore new lead designs.
RESUMEN
Cardiac anatomy plays a crucial role in determining cardiac function. However, there is a poor understanding of how specific and localised anatomical changes affect different cardiac functional outputs. In this work, we test the hypothesis that in a statistical shape model (SSM), the modes that are most relevant for describing anatomy are also most important for determining the output of cardiac electromechanics simulations. We made patient-specific four-chamber heart meshes (n = 20) from cardiac CT images in asymptomatic subjects and created a SSM from 19 cases. Nine modes captured 90% of the anatomical variation in the SSM. Functional simulation outputs correlated best with modes 2, 3 and 9 on average (R = 0.49 ± 0.17, 0.37 ± 0.23 and 0.34 ± 0.17 respectively). We performed a global sensitivity analysis to identify the different modes responsible for different simulated electrical and mechanical measures of cardiac function. Modes 2 and 9 were the most important for determining simulated left ventricular mechanics and pressure-derived phenotypes. Mode 2 explained 28.56 ± 16.48% and 25.5 ± 20.85, and mode 9 explained 12.1 ± 8.74% and 13.54 ± 16.91% of the variances of mechanics and pressure-derived phenotypes, respectively. Electrophysiological biomarkers were explained by the interaction of 3 ± 1 modes. In the healthy adult human heart, shape modes that explain large portions of anatomical variance do not explain equivalent levels of electromechanical functional variation. As a result, in cardiac models, representing patient anatomy using a limited number of modes of anatomical variation can cause a loss in accuracy of simulated electromechanical function.
Asunto(s)
Corazón/fisiología , Modelos Cardiovasculares , Adulto , Voluntarios Sanos , Corazón/anatomía & histología , Humanos , Tomografía Computarizada por Rayos XRESUMEN
Deep learning can bring time savings and increased reproducibility to medical image analysis. However, acquiring training data is challenging due to the time-intensive nature of labeling and high inter-observer variability in annotations. Rather than labeling images, in this work we propose an alternative pipeline where images are generated from existing high-quality annotations using generative adversarial networks (GANs). Annotations are derived automatically from previously built anatomical models and are transformed into realistic synthetic ultrasound images with paired labels using a CycleGAN. We demonstrate the pipeline by generating synthetic 2D echocardiography images to compare with existing deep learning ultrasound segmentation datasets. A convolutional neural network is trained to segment the left ventricle and left atrium using only synthetic images. Networks trained with synthetic images were extensively tested on four different unseen datasets of real images with median Dice scores of 91, 90, 88, and 87 for left ventricle segmentation. These results match or are better than inter-observer results measured on real ultrasound datasets and are comparable to a network trained on a separate set of real images. Results demonstrate the images produced can effectively be used in place of real data for training. The proposed pipeline opens the door for automatic generation of training data for many tasks in medical imaging as the same process can be applied to other segmentation or landmark detection tasks in any modality. The source code and anatomical models are available to other researchers.1 1https://adgilbert.github.io/data-generation/.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Redes Neurales de la Computación , Ecocardiografía , Humanos , Reproducibilidad de los Resultados , UltrasonografíaRESUMEN
BACKGROUND: Pace-mapping is a commonly used electrophysiological (EP) procedure which aims to identify exit sites of ventricular tachycardia (VT) by matching ventricular activation patterns (assessed by QRS morphology) at specific pacing locations with activation during VT. However, long procedure durations and the need for VT induction render this technique non-optimal. To demonstrate the potential of in-silico pace-mapping, using stored electrogram (EGM) recordings of clinical VT from implanted devices to guide pre-procedural ablation planning. METHOD: Six scar-related VT episodes were simulated in a 3D torso model reconstructed from computed tomography (CT) imaging data, including three different infarct anatomies mapped from infarcted porcine imaging data. In-silico pace-mapping was performed to localise VT exit sites and isthmuses by using 12-lead electrocardiogram (ECG) signals and different combinations of EGM sensing vectors from implanted devices, through the creation of conventional correlation maps and reference-less maps. RESULTS: Our in-silico platform was successful in identifying VT exit sites for a variety of different VT morphologies from both ECG correlation maps and corresponding EGM maps, with the latter dependent upon the number of sensing vectors used. We also showed the added utility of both ECG and EGM reference-less pace-mapping for the identification of slow-conducting isthmuses, uncovering the optimal algorithm parameters. Finally, EGM-based pace-mapping was shown to be more dependent upon the mapped surface (epicardial/endocardial), relative to the VT origin. CONCLUSIONS: In-silico pace-mapping can be used along with EGMs from implanted devices to localise VT ablation targets in pre-procedural planning.
Asunto(s)
Ablación por Catéter , Taquicardia Ventricular , Animales , Electrocardiografía , Electrónica , Porcinos , Taquicardia Ventricular/diagnóstico por imagen , Taquicardia Ventricular/cirugía , TorsoRESUMEN
Providing therapies tailored to each patient is the vision of precision medicine, enabled by the increasing ability to capture extensive data about individual patients. In this position paper, we argue that the second enabling pillar towards this vision is the increasing power of computers and algorithms to learn, reason, and build the 'digital twin' of a patient. Computational models are boosting the capacity to draw diagnosis and prognosis, and future treatments will be tailored not only to current health status and data, but also to an accurate projection of the pathways to restore health by model predictions. The early steps of the digital twin in the area of cardiovascular medicine are reviewed in this article, together with a discussion of the challenges and opportunities ahead. We emphasize the synergies between mechanistic and statistical models in accelerating cardiovascular research and enabling the vision of precision medicine.