On the importance of fundamental computational fluid dynamics toward a robust and reliable model of left atrial flows

Computational fluid dynamics (CFD) studies of left atrial flows have reached a sophisticated level, for example, revealing plausible relationships between hemodynamics and stresses with atrial fibrillation. However, little focus has been on fundamental fluid modeling of LA flows. The purpose of this study was to investigate the spatiotemporal convergence, along with the differences between high- (HR) versus normal-resolution/accuracy (NR) solution strategies, respectively. Rigid wall CFD simulations were conducted on 12 patient-specific left atrial geometries obtained from computed tomography scans, utilizing a second-order accurate and space/time-centered solver. The convergence studies showed an average variability of around 30% and 55% for time averaged wall shear stress (WSS), oscillatory shear index (OSI), relative residence time (RRT), and endothelial cell activation potential (ECAP), even between intermediate spatial and temporal resolutions, in the left atrium (LA) and left atrial appendage (LAA), respectively. The comparison between HR and NR simulations showed good correlation in the LA for WSS, RRT, and ECAP (R 2 > .9 ), but not for OSI (R 2 = .63 ). However, there were poor correlations in the LAA especially for OSI, RRT, and ECAP (R 2 = .55, .63, and .61, respectively), except for WSS (R 2 = .81 ). The errors are comparable to differences previously reported with disease correlations. To robustly predict atrial hemodynamics and stresses, numerical resolutions of 10 M elements (i.e., Δ x = ∼ .5 mm) and 10 k time-steps per cycle seem necessary (i.e., one order of magnitude higher than normally used in both space and time). In conclusion, attention to fundamental numerical aspects is essential toward establishing a plausible, robust, and reliable model of LA flows.

Automatic and interpretable prediction of the site of origin in outflow tract ventricular arrhythmias: machine learning integrating electrocardiograms and clinical data

The treatment of outflow tract ventricular arrhythmias (OTVA) through radiofrequency ablation requires the precise identification of the site of origin (SOO). Pinpointing the SOO enhances the likelihood of a successful procedure, reducing intervention times and recurrence rates. Current clinical methods to identify the SOO are based on qualitative analysis of pre-operative electrocardiograms (ECG), heavily relying on physician's expertise. Although computational models and machine learning (ML) approaches have been proposed to assist OTVA procedures, they either consume substantial time, lack interpretability or do not use clinical information. Here, we propose an alternative strategy for automatically predicting the ventricular origin of OTVA patients using ML. Our objective was to classify ventricular (left/right) origin in the outflow tracts (LVOT and RVOT, respectively), integrating ECG and clinical data from each patient. Extending beyond differentiating ventricle origin, we explored specific SOO characterization. Utilizing four databases, we also trained supervised learning models on the QRS complexes of the ECGs, clinical data, and their combinations. The best model achieved an accuracy of 89%, highlighting the significance of precordial leads V1-V4, especially in the R/S transition and initiation of the QRS complex in V2. Unsupervised analysis revealed that some origins tended to group closer than others, e.g., right coronary cusp (RCC) with a less sparse group than the aortic cusp origins, suggesting identifiable patterns for specific SOOs.

The role of the pulmonary veins on left atrial flow patterns and thrombus formation

Atrial fibrillation (AF) is the most common human arrhythmia, forming thrombi mostly in the left atrial appendage (LAA). However, the relation between LAA morphology, blood patterns and clot formation is not yet fully understood. Furthermore, the impact of anatomical structures like the pulmonary veins (PVs) have not been thoroughly studied due to data acquisition difficulties. In-silico studies with flow simulations provide a detailed analysis of blood flow patterns under different boundary conditions, but a limited number of cases have been reported in the literature. To address these gaps, we investigated the influence of PVs on LA blood flow patterns and thrombus formation risk through computational fluid dynamics simulations conducted on a sizeable cohort of 130 patients, establishing the largest cohort of patient-specific LA fluid simulations reported to date. The investigation encompassed an in-depth analysis of several parameters, including pulmonary vein orientation (e.g., angles) and configuration (e.g., number), LAA and LA volumes as well as their ratio, flow, and mass-less particles. Our findings highlight the total number of particles within the LAA as a key parameter for distinguishing between the thrombus and non-thrombus groups. Moreover, the angles between the different PVs play an important role to determine the flow going inside the LAA and consequently the risk of thrombus formation. The alignment between the LAA and the main direction of the left superior pulmonary vein, or the position of the right pulmonary vein when it exhibits greater inclination, had an impact to distinguish the control group vs. the thrombus group. These insights shed light on the intricate relationship between PV configuration, LAA morphology, and thrombus formation, underscoring the importance of comprehensive blood flow pattern analyses.

Artificial intelligence for detection of ventricular oversensing: Machine learning approaches for noise detection within nonsustained ventricular tachycardia episodes remotely transmitted by pacemakers and implantable cardioverter-defibrillators

BACKGROUND

Pacemakers (PMs) and implantable cardioverter-defibrillators (ICDs) increasingly automatically record and remotely transmit nonsustained ventricular tachycardia (NSVT) episodes, which may reveal ventricular oversensing.

OBJECTIVES

We aimed to develop and validate a machine learning algorithm that accurately classifies NSVT episodes transmitted by PMs and ICDs in order to lighten health care workload burden and improve patient safety.

METHODS

PMs or ICDs (Boston Scientific, St Paul, MN) from 4 French hospitals with ≥1 transmitted NSVT episode were split into 3 subgroups: training set, validation set, and test set. Each NSVT episode was labeled as either physiological or nonphysiological. Four machine learning algorithms-2DTF-CNN, 2D-DenseNet, 2DTF-VGG, and 1D-AgResNet-were developed using training and validation data sets. Accuracies of the classifiers were compared with an analysis of the remote monitoring team of the Bordeaux University Hospital using F2 scores (favoring sensitivity over predictive positive value) using an independent test set.

RESULTS

A total of 807 devices transmitted 10,471 NSVT recordings (82% ICD; 18% PM), of which 87 devices (10.8%) transmitted 544 NSVT recordings with nonphysiological signals. The classification by the remote monitoring team resulted in an F2 score of 0.932 (sensitivity 95%; specificity 99%) The 4 machine learning algorithms showed high and comparable F2 scores (2DTF-CNN: 0.914; 2D-DenseNet: 0.906; 2DTF-VGG: 0.863; 1D-AgResNet: 0.791), and only 1D-AgResNet had significantly different labeling from that of the remote monitoring team.

CONCLUSION

Machine learning algorithms were accurate in detecting nonphysiological signals within electrograms transmitted by PMs and ICDs. An artificial intelligence approach may render remote monitoring less resourceful and improve patient safety.

Fetal brain tissue annotation and segmentation challenge results

In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral structures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, gray matter, white matter, ventricles, cerebellum, brainstem, deep gray matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre- and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre- and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other submissions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero.

Assessment of Risk for Ventricular Tachycardia based on Extensive Electrophysiology Simulations

Patients that have suffered a myocardial infarction are at high risk of developing ventricular tachycardia. Patient stratification is often determined by characterization of the underlying myocardial substrate by cardiac imaging methods. In this study, we show that computer modeling of cardiac electrophysiology based on personalized fast 3D simulations can help to assess patient risk to arrhythmia. We perform a large simulation study on 21 patient digital twins and reproduce successfully the clinical outcomes. In addition, we provide the sites which are prone to sustain ventricular tachycardias, i.e, onset sites around the scar region, and validate if they colocalize with exit sites from slow conduction channels.Clinical relevance- Fast electrophysiological simulations can provide advanced patient stratification indices and predict arrhythmic susceptibility to suffer from ventricular tachycardia in patients that have suffered a myocardial infarction.

Left Atrial Thrombus-Are All Atria and Appendages Equal?

Although the left atrial appendage (LAA) seems useless, it has several critical functions that are not fully known yet, such as the causes for being the main origin of cardioembolic stroke. Difficulties arise due to the extreme range of LAA morphologic variability, making the definition of normality challenging and hampering the stratification of thrombotic risk. Furthermore, obtaining quantitative metrics of its anatomy and function from patient data is not straightforward. A multimodality imaging approach, using advanced computational tools for their analysis, allows a complete characterization of the LAA to individualize medical decisions related to left atrial thrombosis patients.

MITEA: A dataset for machine learning segmentation of the left ventricle in 3D echocardiography using subject-specific labels from cardiac magnetic resonance imaging

Segmentation of the left ventricle (LV) in echocardiography is an important task for the quantification of volume and mass in heart disease. Continuing advances in echocardiography have extended imaging capabilities into the 3D domain, subsequently overcoming the geometric assumptions associated with conventional 2D acquisitions. Nevertheless, the analysis of 3D echocardiography (3DE) poses several challenges associated with limited spatial resolution, poor contrast-to-noise ratio, complex noise characteristics, and image anisotropy. To develop automated methods for 3DE analysis, a sufficiently large, labeled dataset is typically required. However, ground truth segmentations have historically been difficult to obtain due to the high inter-observer variability associated with manual analysis. We address this lack of expert consensus by registering labels derived from higher-resolution subject-specific cardiac magnetic resonance (CMR) images, producing 536 annotated 3DE images from 143 human subjects (10 of which were excluded). This heterogeneous population consists of healthy controls and patients with cardiac disease, across a range of demographics. To demonstrate the utility of such a dataset, a state-of-the-art, self-configuring deep learning network for semantic segmentation was employed for automated 3DE analysis. Using the proposed dataset for training, the network produced measurement biases of -9 ± 16 ml, -1 ± 10 ml, -2 ± 5 %, and 5 ± 23 g, for end-diastolic volume, end-systolic volume, ejection fraction, and mass, respectively, outperforming an expert human observer in terms of accuracy as well as scan-rescan reproducibility. As part of the Cardiac Atlas Project, we present here a large, publicly available 3DE dataset with ground truth labels that leverage the higher resolution and contrast of CMR, to provide a new benchmark for automated 3DE analysis. Such an approach not only reduces the effect of observer-specific bias present in manual 3DE annotations, but also enables the development of analysis techniques which exhibit better agreement with CMR compared to conventional methods. This represents an important step for enabling more efficient and accurate diagnostic and prognostic information to be obtained from echocardiography.

Domain expert evaluation of advanced visual computing solutions and 3D printing for the planning of the left atrial appendage occluder interventions

Advanced visual computing solutions and three-dimensional (3D) printing are moving from engineering to clinical pipelines for training, planning, and guidance of complex interventions. 3D imaging and rendering, virtual reality (VR), and in-silico simulations, as well as 3D printing technologies provide complementary information to better understand the structure and function of the organs, thereby improving and personalizing clinical decisions. In this study, we evaluated several advanced visual computing solutions, such as web-based 3D imaging visualization, VR, and computational fluid simulations, together with 3D printing, for the planning of the left atrial appendage occluder (LAAO) device implantations. Six cardiologists tested different technologies in pre-operative data of five patients to identify the usability, limitations, and requirements for the clinical translation of each technology through a qualitative questionnaire. The obtained results demonstrate the potential impact of advanced visual computing solutions and 3D printing to improve the planning of LAAO interventions as well as the need for their integration into a single workflow to be used in a clinical environment.

Detection of lesions in the optic nerve with magnetic resonance imaging using a 3D convolutional neural network

BACKGROUND

Optic neuritis (ON) is one of the first manifestations of multiple sclerosis, a disabling disease with rising prevalence. Detecting optic nerve lesions could be a relevant diagnostic marker in patients with multiple sclerosis.

OBJECTIVES

We aim to create an automated, interpretable method for optic nerve lesion detection from MRI scans.

MATERIALS AND METHODS

We present a 3D convolutional neural network (CNN) model that learns to detect optic nerve lesions based on T2-weighted fat-saturated MRI scans. We validated our system on two different datasets (N = 107 and 62) and interpreted the behaviour of the model using saliency maps.

RESULTS

The model showed good performance (68.11% balanced accuracy) that generalizes to unseen data (64.11%). The developed network focuses its attention to the areas that correspond to lesions in the optic nerve.

CONCLUSIONS

The method shows robustness and, when using only a single imaging sequence, its performance is not far from diagnosis by trained radiologists with the same constraint. Given its speed and performance, the developed methodology could serve as a first step to develop methods that could be translated into a clinical setting.

Machine learning for the automatic assessment of aortic rotational flow and wall shear stress from 4D flow cardiac magnetic resonance imaging

OBJECTIVE

Three-dimensional (3D) time-resolved phase-contrast cardiac magnetic resonance (4D flow CMR) allows for unparalleled quantification of blood velocity. Despite established potential in aortic diseases, the analysis is time-consuming and requires expert knowledge, hindering clinical application. The present research aimed to develop and test a fully automatic machine learning-based pipeline for aortic 4D flow CMR analysis.

METHODS

Four hundred and four subjects were prospectively included. Ground-truth to train the algorithms was generated by experts. The cohort was divided into training (323 patients) and testing (81) sets and used to train and test a 3D nnU-Net for segmentation and a Deep Q-Network algorithm for landmark detection. In-plane (IRF) and through-plane (SFRR) rotational flow descriptors and axial and circumferential wall shear stress (WSS) were computed at ten planes covering the ascending aorta and arch.

RESULTS

Automatic aortic segmentation resulted in a median Dice score (DS) of 0.949 and average symmetric surface distance of 0.839 (0.632-1.071) mm, comparable with the state of the art. Aortic landmarks were located with a precision comparable with experts in the sinotubular junction and first and third supra-aortic vessels (p = 0.513, 0.592 and 0.905, respectively) but with lower precision in the pulmonary bifurcation (p = 0.028), resulting in precise localisation of analysis planes. Automatic flow assessment showed excellent (ICC > 0.9) agreement with manual quantification of SFRR and good-to-excellent agreement (ICC > 0.75) in the measurement of IRF and axial and circumferential WSS.

CONCLUSION

Fully automatic analysis of complex aortic flow dynamics from 4D flow CMR is feasible. Its implementation could foster the clinical use of 4D flow CMR.

KEY POINTS

• 4D flow CMR allows for unparalleled aortic blood flow analysis but requires aortic segmentation and anatomical landmark identification, which are time-consuming, limiting 4D flow CMR widespread use. • A fully automatic machine learning pipeline for aortic 4D flow CMR analysis was trained with data of 323 patients and tested in 81 patients, ensuring a balanced distribution of aneurysm aetiologies. • Automatic assessment of complex flow characteristics such as rotational flow and wall shear stress showed good-to-excellent agreement with manual quantification.

Training machine learning models with synthetic data improves the prediction of ventricular origin in outflow tract ventricular arrhythmias

In order to determine the site of origin (SOO) in outflow tract ventricular arrhythmias (OTVAs) before an ablation procedure, several algorithms based on manual identification of electrocardiogram (ECG) features, have been developed. However, the reported accuracy decreases when tested with different datasets. Machine learning algorithms can automatize the process and improve generalization, but their performance is hampered by the lack of large enough OTVA databases. We propose the use of detailed electrophysiological simulations of OTVAs to train a machine learning classification model to predict the ventricular origin of the SOO of ectopic beats. We generated a synthetic database of 12-lead ECGs (2,496 signals) by running multiple simulations from the most typical OTVA SOO in 16 patient-specific geometries. Two types of input data were considered in the classification, raw and feature ECG signals. From the simulated raw 12-lead ECG, we analyzed the contribution of each lead in the predictions, keeping the best ones for the training process. For feature-based analysis, we used entropy-based methods to rank the obtained features. A cross-validation process was included to evaluate the machine learning model. Following, two clinical OTVA databases from different hospitals, including ECGs from 365 patients, were used as test-sets to assess the generalization of the proposed approach. The results show that V2 was the best lead for classification. Prediction of the SOO in OTVA, using both raw signals or features for classification, presented high accuracy values (>0.96). Generalization of the network trained on simulated data was good for both patient datasets (accuracy of 0.86 and 0.84, respectively) and presented better values than using exclusively real ECGs for classification (accuracy of 0.84 and 0.76 for each dataset). The use of simulated ECG data for training machine learning-based classification algorithms is critical to obtain good SOO predictions in OTVA compared to real data alone. The fast implementation and generalization of the proposed methodology may contribute towards its application to a clinical routine.

Riemannian Geometry of Functional Connectivity Matrices for Multi-Site Attention-Deficit/Hyperactivity Disorder Data Harmonization

The use of multi-site datasets in neuroimaging provides neuroscientists with more statistical power to perform their analyses. However, it has been shown that the imaging-site introduces variability in the data that cannot be attributed to biological sources. In this work, we show that functional connectivity matrices derived from resting-state multi-site data contain a significant imaging-site bias. To this aim, we exploited the fact that functional connectivity matrices belong to the manifold of symmetric positive-definite (SPD) matrices, making it possible to operate on them with Riemannian geometry. We hereby propose a geometry-aware harmonization approach, Rigid Log-Euclidean Translation, that accounts for this site bias. Moreover, we adapted other Riemannian-geometric methods designed for other domain adaptation tasks and compared them to our proposal. Based on our results, Rigid Log-Euclidean Translation of multi-site functional connectivity matrices seems to be among the studied methods the most suitable in a clinical setting. This represents an advance with respect to previous functional connectivity data harmonization approaches, which do not respect the geometric constraints imposed by the underlying structure of the manifold. In particular, when applying our proposed method to data from the ADHD-200 dataset, a multi-site dataset built for the study of attention-deficit/hyperactivity disorder, we obtained results that display a remarkable correlation with established pathophysiological findings and, therefore, represent a substantial improvement when compared to the non-harmonization analysis. Thus, we present evidence supporting that harmonization should be extended to other functional neuroimaging datasets and provide a simple geometric method to address it.

Left Atrial Thrombus-Are All Atria and Appendages Equal?

Although the left atrial appendage (LAA) seems useless, it has several critical functions that are not fully known yet, such as the causes for being the main origin of cardioembolic stroke. Difficulties arise due to the extreme range of LAA morphologic variability, making the definition of normality challenging and hampering the stratification of thrombotic risk. Furthermore, obtaining quantitative metrics of its anatomy and function from patient data is not straightforward. A multimodality imaging approach, using advanced computational tools for their analysis, allows a complete characterization of the LAA to individualize medical decisions related to left atrial thrombosis patients.

Machine learning-based phenotyping and risk assessment of hypertrophic cardiomyopathy - linking ECGs, morphology and genotypes

Funding Acknowledgements

Type of funding sources: None.

Background

Integrating clinical data to distinguish hypertrophic cardiomyopathy (HCM) phenotypes is relevant in clinical practice. Machine learning (ML) can help - deep learning (DL) networks can automate detection and segmentation of 12-lead electrocardiograms (ECGs), whereas unsupervised learning can group patients to compare ECG, imaging and genetic characteristics. The aim is to automate ECG morphology analysis from all 12 ECG leads and multiple beats, and relate this to HCM genotypes and imaging phenotypes. 

Methods

The single-center cohort included phenotype- and genotype-positive (G+) HCM patients (n = 104) and their phenotype-negative relatives (n = 50, 42% G+). All patients had a digital 12-lead ECG, echocardiography, and a magnetic resonance (CMR) study performed. The workflow is shown in Fig 1. A U-Net DL network was used for ECG delineation (P, QRS, T onsets/offsets) for all cardiac cycles. Three heartbeats were selected for each patient based on their morphology, with the aim of capturing beat-to-beat variability. An unsupervised representation learning algorithm was used to fuse ECG data and assess inter-patient similarities. Patients were clustered based on similarities of ECG biomarkers, and compared with regards to genotypes, family history of sudden cardiac death (SCD), history of ventricular arrhythmias/syncope/aborted SCD, implanted defibrillators (ICD), left ventricular (LV) obstruction, maximal wall thickness, late gadolinium enhancement (LGE), and HCM risk-SCD score.

Results

ML based on ECG biomarkers provided a good separation of HCM patients and relatives (Fig 1A), also showing G- and patients with variants of uncertain significance grouping together (Fig 1B). Clustering resulted in 6 ECG phenogroups (C1-6). C1 and 2 were related to less comorbidities, cardiac remodeling, and HCM risk score, capturing the majority of G- patients. C3 and 4 were related to LV obstruction – where C4 consisted of symptomatic patients with high ICD implantation and event rates, high LGE, and impaired systolic function. C5 captured patients with high comorbidities, extremely remodeled hearts, but no obstruction, whereas C6 patients with positive family history and high arrhythmic events (Fig 1C, Table 1). The average ECG morphology is shown side-by-side for C1 and C5 in Fig 1D – negative T waves, increased R/S wave amplitudes, left axis deviation (LAD) and ST elevation can be recognized as macro-biomarkers in C5 (yellow arrows).

Conclusion

ML can automate the analysis of complex clinical data, simultaneously taking into account the morphology of all ECG components in all 12-leads, throughout multiple beats, compare it with clinical and imaging data, and identify clinically sensible phenogroups as validated by structural and functional findings, as well as with genotypes and clinical information. Automated and comprehensive cardiac data analysis has diagnostic and research potential to help screen populations and phenotype disease etiologies. Abstract Figure 1: analysis pipeline  Abstract Table 1: clinical variables

Machine Learning for Clinical Decision-Making: Challenges and Opportunities in Cardiovascular Imaging

The use of machine learning (ML) approaches to target clinical problems is called to revolutionize clinical decision-making in cardiology. The success of these tools is dependent on the understanding of the intrinsic processes being used during the conventional pathway by which clinicians make decisions. In a parallelism with this pathway, ML can have an impact at four levels: for data acquisition, predominantly by extracting standardized, high-quality information with the smallest possible learning curve; for feature extraction, by discharging healthcare practitioners from performing tedious measurements on raw data; for interpretation, by digesting complex, heterogeneous data in order to augment the understanding of the patient status; and for decision support, by leveraging the previous steps to predict clinical outcomes, response to treatment or to recommend a specific intervention. This paper discusses the state-of-the-art, as well as the current clinical status and challenges associated with the two later tasks of interpretation and decision support, together with the challenges related to the learning process, the auditability/traceability, the system infrastructure and the integration within clinical processes in cardiovascular imaging.

Automatic segmentation of the aorta on multi-center and multi-vendor phase-contrast enhanced magnetic resonance angiographies and the advantages of transfer learning

Funding Acknowledgements

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Guala A. received funding from the Spanish Ministry of Science, Innovation and Universities

Background

Phase-contrast (PC) enhanced magnetic resonance (MR) angiography (MRA) is a class of angiogram exploiting velocity data to increase the signal-to-noise ratio, thus avoiding the administration of external contrast agent, normally used to segment 4D flow MR data. To train deep-learning algorithms to segment PC-MRA a large amount of manually annotated data is needed: however, the relatively novelty of the sequence, its rapid evolution and the extensive time needed to manually segment data limit its availability.

Purpose

The aim of this study was to test a deep learning algorithm in the segmentation of multi-center and multi-vendor PC-MRA and to test if transfer learning (TL) improves performance.

Methods

A large dataset (LD) of 262 and a small one (SD) of 22 PC-MRA, acquired without contrast agent at 1.5 T in a General Electric and a Siemens scanner, respectively, were manually annotated and divided into training (232 and 15 cases) and testing (30 and 7) sets. They both included PC-MRA of healthy subjects and patients with aortic diseases (excluding dissections) and native aorta. A convolutional neural networks (CNN) based on nnU-Net framework [1] was trained in the LD and another in the SD. The left ventricle was removed semi-automatically from the DL segmentations of the LD as it was not relevant for this application. Networks were then tested on the test sets of the dataset there were trained and the other dataset to assess generalizability. Finally, a fine-tuning transfer learning approach was applied to LD network and the performance on both test sets were tested. Dice score, Hausdorff distance, Jaccard score and Average Symmetrical Surface Distance were used as segmentation quality metrics.

Results

LD network achieved good performance in LD test set, with a DS of 0.904, ASSD of 1.47, J of 0.827 and HD of 6.35, which further improve after removing the left ventricle in the post-processing to a DS of 0.942, ASSD of 0.93, J of 0.892 and HD of 3.32. SD network results in an average DS of 0.895, ASSD of 0.59, J of 0.812 and HD of 2.05. Once tested on the testing set of the other dataset, LD network resulted in a DS of 0.612 while SD network in DS of 0.375, thus showing limited generalizability. However, the application of transfer learning to LD network resulted in the improvement of the evaluation metrics on the SD from a DS of 0.612 to 0.858, while slightly worsening in the first one without post-processing to 0.882.

Conclusions

nnU-net framework is effective for fast automatic segmentation of the aorta from multi-center and multi-vendor PC-MRA, showing performance comparable with the state of the art. The application of transfer learning allows for increased generalization to data from center not included in the original training. These results unlock the possibility for fully-automatic analysis of multi-vendor multi-center 4D flow MR.

Machine learning to automatically detect anatomical landmarks on phase-contrast enhanced magnetic resonance angiography

Funding Acknowledgements

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Guala A. received funding from the Spanish Ministry of Science, Innovation and Universities

Introduction

The heterogeneous characteristic of the thoracic aorta implies that all biomarkers with potential for risk stratification need to be references to a specific location. This is the case, for example, of diameter [1], stiffness [2] and wall shear stress [3]. This is normally achieved by the manual identification of a limited number of key anatomic landmarks [4], which is a time-demanding task and may impact biomarkers accuracy and reproducibility. Automatic identification of these anatomic landmarks may speed-up the analysis and allow for the creation of fully automatic image analysis pipelines. Machine learning (ML) algorithms might be suitable for this task.

Purpose

The aim of this study was to test the performance of a ML algorithm in localizing key thoracic anatomical landmarks on phase-contrast enhanced magnetic resonance angiograms (PC-MRA).

Methods

PC-MRA of 323 patients with native aorta and aortic valve and a variety of aortic conditions (141 bicuspid aortic valve patients, 60 patients with degenerative aortic aneurysms, 82 patients with genetic aortopathy and 40 healthy volunteers) were included in this study. Four anatomical landmarks were manually identified on PC-MRA by an experienced researcher: sinotubular junction, the pulmonary artery bifurcation and the first and third supra-aortic vessel braches. A reinforcement learning algorithm (DQN), combining Q-learning with deep neural networks, was trained. The algorithm was tested in a separate set of 30 PC-MRA with similar distribution of aortic conditions in which human intra-observer reproducibility was quantified. The distance between points was used as quality metric and human annotation was considered as ground-truth. Repeated-measures ANOVA was used for statistical testing.

Results

ML algorithm resulted in performance similar to the intra-observer variability obtained by the experienced human reader in the identification of the sinotubular junction (11.1 ± 8.6 vs 11.0 ± 8.1 mm, p = 0.949) and first (6.8 ± 5.6 vs 6.6 ± 3.9 mm, p = 0.886) and third (8.4 ± 7.4 vs 6.8 ± 4.0 mm, p = 0.161) supra-aortic vessels branches. However, the algorithm did not reach human-level performance in the localization of the pulmonary artery bifurcation (15.2 ± 13.1 vs 10.2 ± 7.0 mm, p = 0.008). The time needed to the ML algorithm to locate all points ranged between 0.8 and 1.6 seconds on a standard computer while manual annotation required around two minutes to be performed.

Conclusions

The rapid identification of key aortic anatomical landmarks by a reinforced learning algorithm is feasible with human-level performance. This approach may thus be used for the design of fully-automatic pipeline for 4D flow CMR analysis.

High-power short-duration vs. standard radiofrequency cardiac ablation: comparative study based on an in-silico model

PURPOSE

While the standard setting during radiofrequency catheter ablation (RFCA) consists of applying low power for long times, a new setting based on high power and short duration (HPSD) has recently been suggested as safer and more effective. Our aim was to compare the electrical and thermal performance of standard vs. HPSD settings, especially to assess the effect of the catheter orientation.

METHODS

A 3D computational model was built based on a coupled electric-thermal-flow problem. Standard (20 W-45 s and 30 W-30 s) and HPSD settings (70 W-7 s and 90 W-4 s) were compared. Since the model only included a cardiac tissue fragment, the power values were adjusted to 80% of the clinical values (15, 23, 53 and 69 W). Three catheter-tissue orientations were considered (90°, 45° and 0°). Thermal lesions were assessed by the Arrhenius equation. Safety was assessed by checking the occurrence of steam pops (100 °C in tissue) and thrombus formation (80 °C in blood).

RESULTS

The computed thermal lesions were in close agreement with the experimental data in the literature, in particular with in vivo studies. HPSD created shallower and wider lesions than standard settings, especially with the catheter at 45°. Steam pops occurred earlier with HPSD, regardless of catheter orientation.

CONCLUSION

HPSD seems to be more effective in cases that need shallow and extensive lesions, especially when the catheter is at 0° or at 45°, as used in pulmonary vein isolation.

Deep Learning Framework for Real-Time Estimation of in-silico Thrombotic Risk Indices in the Left Atrial Appendage

Patient-specific computational fluid dynamics (CFD) simulations can provide invaluable insight into the interaction of left atrial appendage (LAA) morphology, hemodynamics, and the formation of thrombi in atrial fibrillation (AF) patients. Nonetheless, CFD solvers are notoriously time-consuming and computationally demanding, which has sparked an ever-growing body of literature aiming to develop surrogate models of fluid simulations based on neural networks. The present study aims at developing a deep learning (DL) framework capable of predicting the endothelial cell activation potential (ECAP), an in-silico index linked to the risk of thrombosis, typically derived from CFD simulations, solely from the patient-specific LAA morphology. To this end, a set of popular DL approaches were evaluated, including fully connected networks (FCN), convolutional neural networks (CNN), and geometric deep learning. While the latter directly operated over non-Euclidean domains, the FCN and CNN approaches required previous registration or 2D mapping of the input LAA mesh. First, the superior performance of the graph-based DL model was demonstrated in a dataset consisting of 256 synthetic and real LAA, where CFD simulations with simplified boundary conditions were run. Subsequently, the adaptability of the geometric DL model was further proven in a more realistic dataset of 114 cases, which included the complete patient-specific LA and CFD simulations with more complex boundary conditions. The resulting DL framework successfully predicted the overall distribution of the ECAP in both datasets, based solely on anatomical features, while reducing computational times by orders of magnitude compared to conventional CFD solvers.

Anomalous nucleation of crystals within amorphous germanium nanowires during thermal annealing

In this work, germanium nanowires rendered fully amorphous via xenon ion irradiation have been annealed within a transmission electron microscope to induce crystallization. During annealing crystallites appeared in some nanowires whilst others remained fully amorphous. Remarkably, even when nucleation occurred, large sections of the nanowires remained amorphous even though the few crystallites embedded in the amorphous phase were formed at a minimum of 200 °C above the temperature for epitaxial growth and 100 °C above the temperature for random nucleation and growth in bulk germanium. Furthermore, the presence of crystallites was observed to depend on the diameter of the nanowire. Indeed, the formation of crystallites occurred at a higher annealing temperature in thin nanowires compared with thicker ones. Additionally, nanowires with a diameter above 55 nm were made entirely crystalline when the annealing was performed at the temperature normally required for crystallization in germanium (i.e. 500 °C). It is proposed that oxygen atoms hinder both the formation and the growth of crystallites. Furthermore, as crystallites must reach a minimum size to survive and grow within the amorphous nanowires, the instability of crystallites may also play a limited role for the thinnest nanowires.

Biophysics-based statistical learning: Application to heart and brain interactions

Initiatives such as the UK Biobank provide joint cardiac and brain imaging information for thousands of individuals, representing a unique opportunity to study the relationship between heart and brain. Most of research on large multimodal databases has been focusing on studying the associations among the available measurements by means of univariate and multivariate association models. However, these approaches do not provide insights about the underlying mechanisms and are often hampered by the lack of prior knowledge on the physiological relationships between measurements. For instance, important indices of the cardiovascular function, such as cardiac contractility, cannot be measured in-vivo. While these non-observable parameters can be estimated by means of biophysical models, their personalisation is generally an ill-posed problem, often lacking critical data and only applied to small datasets. Therefore, to jointly study brain and heart, we propose an approach in which the parameter personalisation of a lumped cardiovascular model is constrained by the statistical relationships observed between model parameters and brain-volumetric indices extracted from imaging, i.e. ventricles or white matter hyperintensities volumes, and clinical information such as age or body surface area. We explored the plausibility of the learnt relationships by inferring the model parameters conditioned on the absence of part of the target clinical features, applying this framework in a cohort of more than 3 000 subjects and in a pathological subgroup of 59 subjects diagnosed with atrial fibrillation. Our results demonstrate the impact of such external features in the cardiovascular model personalisation by learning more informative parameter-space constraints. Moreover, physiologically plausible mechanisms are captured through these personalised models as well as significant differences associated to specific clinical conditions.

Automated analysis of 3D-echocardiography using spatially registered patient-specific CMR meshes

Funding Acknowledgements

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): National Heart Foundation (NHF) of New Zealand Health Research Council (HRC) of New Zealand

Artificial intelligence shows considerable promise for automated analysis and interpretation of medical images, particularly in the domain of cardiovascular imaging. While application to cardiac magnetic resonance (CMR) has demonstrated excellent results, automated analysis of 3D echocardiography (3D-echo) remains challenging, due to the lower signal-to-noise ratio (SNR), signal dropout, and greater interobserver variability in manual annotations. As 3D-echo is becoming increasingly widespread, robust analysis methods will substantially benefit patient evaluation. 

We sought to leverage the high SNR of CMR to provide training data for a convolutional neural network (CNN) capable of analysing 3D-echo. We imaged 73 participants (53 healthy volunteers, 20 patients with non-ischaemic cardiac disease) under both CMR and 3D-echo (<1 hour between scans). 3D models of the left ventricle (LV) were independently constructed from CMR and 3D-echo, and used to spatially align the image volumes using least squares fitting to a cardiac template. The resultant transformation was used to map the CMR mesh to the 3D-echo image. Alignment of mesh and image was verified through volume slicing and visual inspection (Fig. 1) for 120 paired datasets (including 47 rescans) each at end-diastole and end-systole.

100 datasets (80 for training, 20 for validation) were used to train a shallow CNN for mesh extraction from 3D-echo, optimised with a composite loss function consisting of normalised Euclidian distance (for 290 mesh points) and volume. Data augmentation was applied in the form of rotations and tilts (<15 degrees) about the long axis. The network was tested on the remaining 20 datasets (different participants) of varying image quality (Tab. I). For comparison, corresponding LV measurements from conventional manual analysis of 3D-echo and associated interobserver variability (for two observers) were also estimated.

Initial results indicate that the use of embedded CMR meshes as training data for 3D-echo analysis is a promising alternative to manual analysis, with improved accuracy and precision compared with conventional methods. Further optimisations and a larger dataset are expected to improve network performance.

(n = 20) LV EDV (ml) LV ESV (ml) LV EF (%) LV mass (g) Ground truth CMR 150.5 ± 29.5 57.9 ± 12.7 61.5 ± 3.4 128.1 ± 29.8 Algorithm error -13.3 ± 15.7 -1.4 ± 7.6 -2.8 ± 5.5 0.1 ± 20.9 Manual error -30.1 ± 21.0 -15.1 ± 12.4 3.0 ± 5.0 Not available Interobserver error 19.1 ± 14.3 14.4 ± 7.6 -6.4 ± 4.8 Not available Tab. 1. LV mass and volume differences (means ± standard deviations) for 20 test cases. Algorithm: CNN – CMR (as ground truth). Abstract Figure. Fig 1. CMR mesh registered to 3D-echo.

Reinforcement machine learning-based aortic anatomical landmarks detection from phase-contrast enhanced magnetic resonance angiography

Funding Acknowledgements

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Spanish Ministry of Science, Innovation and Universities; La Marató de TV3

Introduction

Automatic analysis of medical imaging data may improve their clinical impact by reducing analysis time and improving reproducibility. Many medical imaging data, like 4D-flow magnetic resonance imaging (MRI), are often quantified regionally, implying the need for anatomical landmark identification to locate correspondences in the extracted data and compare among patients. Machine learning (ML) techniques hold potential for automatic analysis of medical imaging. Phase-contrast enhanced magnetic resonance angiography (PC-MRA) is a class of angiograms not requiring the administration of contrast agents.

Purpose

We aimed to test whether a machine learning algorithm can be trained to identify key anatomical cardiovascular landmarks on PC-MRA images and compare its performance with humans.

Methods

Three-hundred twenty-three aortic PC-MRA were manually annotated with the location of 4 landmarks: sinotubular junction, pulmonary artery bifurcation and first and third supra-aortic vessels (Figure 1), often used to separate the aorta in sub-regions. Patients included in the training dataset comprised healthy volunteers (40), bicuspid aortic valve patients (141), patients with degenerative aortic disease (60) and patients with genetically-triggered aortic disease (82), all without previous aortic surgery and with native aortic valve. PC-MRA images and manual annotations were used to train a DQN, a reinforcement learning algorithm that combines Q-learning with deep neural networks. The agents can navigate the images and optimally find the landmarks by following the policies learned during training. Data from thirty patients, distributed in terms of aortic condition as the training set, unseen by the algorithm in the training phase, were used to quantify intra-observer reproducibility and to assess ML algorithm performance. Distance between points was used as metric for comparisons, original human annotation was used as ground-truth and repeated-measures ANOVA was used for statistical testing.

Results

Human and machine learning performed similarly in the identification of the sinotubular junction (distance between points of 11.0 ± 8.1 vs. 11.1 ± 8.6 mm, respectively, p = 0.949) and first (6.6 ± 3.9 vs. 6.8 ± 5.6 mm, p = 0.886) and third (6.8 ± 4.0 vs. 8.4 ± 7.4 mm, p = 0.161) supra-aortic vessels branches but human annotation outperformed ML landmark detection in the identification of the pulmonary artery bifurcation (10.2 ± 7.0 vs. 15.2 ± 13.1 mm, p = 0.008). Computation time for landmark detection by ML was between 0.8 and 1.6 seconds on a standard computer while human annotation took approximatively two minutes.

Conclusions

ML-based aortic landmarks detection from phase-contrast enhanced magnetic resonance angiography is feasible and fast and performs similarly to human. Reinforced learning anatomical landmark identification unlock automatic extraction of a variety of regional aortic data, including complex 4D flow parameters.

Abstract Figure

4D flow magnetic resonance imaging to assess left atrial haemodynamics in healthy and hypertrophic subjects

Funding Acknowledgements

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): - University, research centre and hospital foundation grants for the contracting of new research staff (FI 2020) - Spanish Ministry of Economy and Competitiveness Retos investigacion project

Introduction

The assessment of the left atrium (LA) haemodynamics is key to better understand the development of LA-related pathological processes. In this regard 4D flow magnetic resonance imaging (MRI) can provide complementary information to standard Doppler echocardiographic studies and identify complex blood flow patterns. Yet, until recently, the left atrium (LA) has been largely left aside in 4D flow MRI studies.

Purpose

We aimed at assessing the LA haemodynamics of healthy and hypertrophic cardiomyopathy (HCM) subjects with a qualitative visualization of flow patterns and deriving quantitative indices related to ventricular dysfunction from pulmonary veins (PV)  and mitral valve (MV) velocity profiles.

Methods

Segmentation was performed directly over 4D flow angiograms. A total of 20 cases were processed, 11 healthy and 9 HCM subjects. 4D velocity matrices were masked with the segmented mask to isolate LA haemodynamics. Velocity profiles were then obtained in the PV and MV and integrated over planes perpendicular to the lumen of the vessels to create velocity spectrograms. Fourier spectral analysis was applied to the velocity curves to highlight differences that might go unnoticed in the time domain. In addition, the Q-Criterion was computed for vortex identification, visually inspecting both cohorts across the whole cardiac cycle.

Results

Fourier spectral analysis of the velocity curves suggested that overall, healthy patients have higher dynamic range of the velocity curves. It can be observed in Figure 1, that the usual E/A MV velocity pattern is preserved in 10 of the 11 healthy subjects while 5 of the HCM patients present significant alterations of said curve. In fact, patients 4, 6, 7 and 8 seem to present a 3 peaked MV velocity curve. The vortex analysis identified 3 main types of vortices in healthy subjects: a ‘filling’ systolic vortex (10/11) arising near the most dominant PV (usually the left superior PV) as seen in Figure 2; a conduit phase vortex (7/11), similar in nature to the preceding systolic vortex; and an E-wave vortex (9/11) attached to the LA ostium. Four of the HCM patients (out of the five with altered MV velocity profile) also showed a systolic vortex, but with more complex blood flow patterns and emerging far from the PVs. One of such vortices is shown in Figure 2, composed of two distinct eddies near the MV. The E-wave vortex was also observed but was less predominant than in healthy subjects (3/9).

Conclusions

4D Flow analysis of the LA is feasible and might hold promise in the understanding of the complex haemodynamics in ventricular dysfunction.

Abstract Figure. Velocity Spectrograms and Vortices

Delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks

Detection and delineation are key steps for retrieving and structuring information of the electrocardiogram (ECG), being thus crucial for numerous tasks in clinical practice. Digital signal processing (DSP) algorithms are often considered state-of-the-art for this purpose but require laborious rule readaptation for adapting to unseen morphologies. This work explores the adaptation of the the U-Net, a deep learning (DL) network employed for image segmentation, to electrocardiographic data. The model was trained using PhysioNet's QT database, a small dataset of 105 2-lead ambulatory recordings, while being independently tested for many architectural variations, comprising changes in the model's capacity (depth, width) and inference strategy (single- and multi-lead) in a fivefold cross-validation manner. This work features several regularization techniques to alleviate data scarcity, such as semi-supervised pre-training with low-quality data labels, performing ECG-based data augmentation and applying in-built model regularizers. The best performing configuration reached precisions of 90.12%, 99.14% and 98.25% and recalls of 98.73%, 99.94% and 99.88% for the P, QRS and T waves, respectively, on par with DSP-based approaches. Despite being a data-hungry technique trained on a small dataset, a U-Net based approach demonstrates to be a viable alternative for this task.

A global benchmark of algorithms for segmenting the left atrium from late gadolinium-enhanced cardiac magnetic resonance imaging

Segmentation of medical images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) used for visualizing diseased atrial structures, is a crucial first step for ablation treatment of atrial fibrillation. However, direct segmentation of LGE-MRIs is challenging due to the varying intensities caused by contrast agents. Since most clinical studies have relied on manual, labor-intensive approaches, automatic methods are of high interest, particularly optimized machine learning approaches. To address this, we organized the 2018 Left Atrium Segmentation Challenge using 154 3D LGE-MRIs, currently the world's largest atrial LGE-MRI dataset, and associated labels of the left atrium segmented by three medical experts, ultimately attracting the participation of 27 international teams. In this paper, extensive analysis of the submitted algorithms using technical and biological metrics was performed by undergoing subgroup analysis and conducting hyper-parameter analysis, offering an overall picture of the major design choices of convolutional neural networks (CNNs) and practical considerations for achieving state-of-the-art left atrium segmentation. Results show that the top method achieved a Dice score of 93.2% and a mean surface to surface distance of 0.7 mm, significantly outperforming prior state-of-the-art. Particularly, our analysis demonstrated that double sequentially used CNNs, in which a first CNN is used for automatic region-of-interest localization and a subsequent CNN is used for refined regional segmentation, achieved superior results than traditional methods and machine learning approaches containing single CNNs. This large-scale benchmarking study makes a significant step towards much-improved segmentation methods for atrial LGE-MRIs, and will serve as an important benchmark for evaluating and comparing the future works in the field. Furthermore, the findings from this study can potentially be extended to other imaging datasets and modalities, having an impact on the wider medical imaging community.

Radiomics Signatures of Cardiovascular Risk Factors in Cardiac MRI: Results From the UK Biobank

Cardiovascular magnetic resonance (CMR) radiomics is a novel technique for advanced cardiac image phenotyping by analyzing multiple quantifiers of shape and tissue texture. In this paper, we assess, in the largest sample published to date, the performance of CMR radiomics models for identifying changes in cardiac structure and tissue texture due to cardiovascular risk factors. We evaluated five risk factor groups from the first 5,065 UK Biobank participants: hypertension (n = 1,394), diabetes (n = 243), high cholesterol (n = 779), current smoker (n = 320), and previous smoker (n = 1,394). Each group was randomly matched with an equal number of healthy comparators (without known cardiovascular disease or risk factors). Radiomics analysis was applied to short axis images of the left and right ventricles at end-diastole and end-systole, yielding a total of 684 features per study. Sequential forward feature selection in combination with machine learning (ML) algorithms (support vector machine, random forest, and logistic regression) were used to build radiomics signatures for each specific risk group. We evaluated the degree of separation achieved by the identified radiomics signatures using area under curve (AUC), receiver operating characteristic (ROC), and statistical testing. Logistic regression with L1-regularization was the optimal ML model. Compared to conventional imaging indices, radiomics signatures improved the discrimination of risk factor vs. healthy subgroups as assessed by AUC [diabetes: 0.80 vs. 0.70, hypertension: 0.72 vs. 0.69, high cholesterol: 0.71 vs. 0.65, current smoker: 0.68 vs. 0.65, previous smoker: 0.63 vs. 0.60]. Furthermore, we considered clinical interpretation of risk-specific radiomics signatures. For hypertensive individuals and previous smokers, the surface area to volume ratio was smaller in the risk factor vs. healthy subjects; perhaps reflecting a pattern of global concentric hypertrophy in these conditions. In the diabetes subgroup, the most discriminatory radiomics feature was the median intensity of the myocardium at end-systole, which suggests a global alteration at the myocardial tissue level. This study confirms the feasibility and potential of CMR radiomics for deeper image phenotyping of cardiovascular health and disease. We demonstrate such analysis may have utility beyond conventional CMR metrics for improved detection and understanding of the early effects of cardiovascular risk factors on cardiac structure and tissue.

In silico pace-mapping: prediction of left vs. right outflow tract origin in idiopathic ventricular arrhythmias with patient-specific electrophysiological simulations

AIMS

A pre-operative non-invasive identification of the site of origin (SOO) of outflow tract ventricular arrhythmias (OTVAs) is important to properly plan radiofrequency ablation procedures. Although some algorithms based on electrocardiograms (ECGs) have been developed to predict left vs. right ventricular origins, their accuracy is still limited, especially in complex anatomies. The aim of this work is to use patient-specific electrophysiological simulations of the heart to predict the SOO in OTVA patients.

METHODS AND RESULTS

An in silico pace-mapping procedure was designed and used on 11 heart geometries, generating for each case simulated ECGs from 12 clinically plausible SOO. Subsequently, the simulated ECGs were compared with patient ECG data obtained during the clinical tachycardia using the 12-lead correlation coefficient (12-lead ρ). Left ventricle (LV) vs. right ventricle (RV) SOO was estimated by computing the LV/RV ratio for each patient, obtained by dividing the average 12-lead ρ value of the LV- and RV-SOO simulated ECGs, respectively. Simulated ECGs that had virtual sites close to the ablation points that stopped the arrhythmia presented higher correlation coefficients. The LV/RV ratio correctly predicted LV vs. RV SOO in 10/11 cases; 1.07 vs. 0.93 P < 0.05 for 12-lead ρ.

CONCLUSION

The obtained results demonstrate the potential of the developed in silico pace-mapping technique to complement standard ECG for the pre-operative planning of complex ventricular arrhythmias.

Integration of artificial intelligence into clinical patient management: focus on cardiac imaging

Cardiac imaging is a crucial component in the management of patients with heart disease, and as such it influences multiple, inter-related parts of the clinical workflow: physician-patient contact, image acquisition, image pre- and postprocessing, study reporting, diagnostics and outcome predictions, medical interventions, and, finally, knowledge-building through clinical research. With the gradual and ubiquitous infiltration of artificial intelligence into cardiology, it has become clear that, when used appropriately, it will influence and potentially improve-through automation, standardization and data integration-all components of the clinical workflow. This review aims to present a comprehensive view of full integration of artificial intelligence into the standard clinical patient management-with a focus on cardiac imaging, but applicable to all information handling-and to discuss current barriers that remain to be overcome before its widespread implementation and integration.

Cardiac computational modelling

Cardiovascular diseases currently have a major social and economic impact, constituting one of the leading causes of mortality and morbidity. Personalized computational models of the heart are demonstrating their usefulness both to help understand the mechanisms underlying cardiac disease, and to optimize their treatment and predict the patient's response. Within this framework, the Spanish Research Network for Cardiac Computational Modelling (VHeart-SN) has been launched. The general objective of the VHeart-SN network is the development of an integrated, modular and multiscale multiphysical computational model of the heart. This general objective is addressed through the following specific objectives: a) to integrate the different numerical methods and models taking into account the specificity of patients; b) to assist in advancing knowledge of the mechanisms associated with cardiac and vascular diseases; and c) to support the application of different personalized therapies. This article presents the current state of cardiac computational modelling and different scientific works conducted by the members of the network to gain greater understanding of the characteristics and usefulness of these models.

Fast Quasi-Conformal Regional Flattening of the Left Atrium

Two-dimensional representation of 3D anatomical structures is a simple and intuitive way for analysing patient information across populations and image modalities. While cardiac ventricles, especially the left ventricle, have an established standard representation (bull's eye plot), the 2D depiction of the left atrium (LA) remains challenging due to its sub-structural complexity including the pulmonary veins (PV) and the left atrial appendage (LAA). Quasi-conformal flattening techniques, successfully applied to cardiac ventricles, require additional constraints in the case of the LA to place the PV and LAA in the same geometrical 2D location for different cases. Some registration-based methods have been proposed but surface registration is time-consuming and prone to errors when the geometries are very different. We propose a novel atrial flattening methodology where a 2D standardised map of the LA is obtained quickly and without errors related to registration. The LA is divided into five regions which are then mapped to their analogue two-dimensional regions. 67 human left atria from magnetic resonance images (MRI) were studied to derive a population-based template representing the averaged relative locations of the PVs and LAA. The clinical application of our methodology is illustrated on different use cases including the integration of MRI and electroanatomical data.

Cardiac Magnetic Resonance-Guided Ventricular Tachycardia Substrate Ablation

OBJECTIVES

This study assessed the feasibility and potential benefit of performing ventricular tachycardia (VT) substrate ablation procedures guided by cardiac magnetic resonance (CMR)-derived pixel signal intensity (PSI) maps.

BACKGROUND

CMR-aided VT ablation using PSI maps from late gadolinium enhancement-CMR (LGE-CMR), together with electroanatomical map (EAM) information, has been shown to improve outcomes of VT substrate ablation.

METHODS

Eighty-four patients with scar-dependent monomorphic VT who underwent substrate ablation were included in the study. In the last 28 (33%) consecutive patients, the procedure was guided by CMR. Procedural data, as well as acute and follow-up outcomes, were compared between patients who underwent guided CMR and 2 control groups: 1) patients who had PSI maps were available but the EAM was acquired and used to select the ablation targets (CMR aided); and 2) patients with no CMR-derived PSI maps available (no CMR).

RESULTS

Mean procedure duration was lower in CMR-guided substrate ablation compared with CMR-aided and no CMR (107 ± 59 min vs. 203 ± 68 min and 227 ± 52 min; p < 0.001 for both comparisons). CMR-guided ablation required less fluoroscopy time than CMR-aided ablation and no CMR (10 ± 4 min vs. 23 ± 11 min and 20 ± 9 min, respectively; p < 0.001 for both comparisons) and less radiofrequency time (15 ± 8 min vs. 20 ± 15 min and 26 ± 10 min; p = 0.16 and p < 0.001, respectively). After substrate ablation, VT inducibility was lower in CMR-guided ablation compared with CMR-aided ablation and no CMR (18% vs. 32% and 46%; p = 0.35 and p = 0.04, respectively), without significant differences in complications. After 12 months, VT recurrence was lower in those who underwent CMR-guided ablation compared with no CMR (log-rank: 0.019), with no differences with CMR-aided ablation.

CONCLUSIONS

CMR-guided VT ablation is feasible and safe, significantly reduces the procedural, fluoroscopy, and radiofrequency times, and is associated with a higher noninducibility rate and lower VT recurrence after substrate ablation.

Preferential regional distribution of atrial fibrosis in posterior wall around left inferior pulmonary vein as identified by late gadolinium enhancement cardiac magnetic resonance in patients with atrial fibrillation

Aims

Left atrial (LA) fibrosis can be identified by late gadolinium enhancement cardiac magnetic resonance (LGE-CMR) in patients with atrial fibrillation (AF). However, there is limited information about anatomical fibrosis distribution in the left atrium. The aim is to determine whether there is a preferential spatial distribution of fibrosis in the left atrium in patients with AF.

Methods and results

A 3-Tesla LGE-CMR was performed in 113 consecutive patients referred for AF ablation. Images were post-processed and analysed using ADAS-AF software (Galgo Medical), which allows fibrosis identification in 3D colour-coded shells. A regional semiautomatic LA parcellation software was used to divide the atrial wall into 12 segments: 1-4, posterior wall; 5-6, floor; 7, septal wall; 8-11, anterior wall; 12, lateral wall. The presence and amount of fibrosis in each segment was obtained for analysis. After exclusions for artefacts and insufficient image quality, 76 LGE-MRI images (68%) were suitable for fibrosis analysis. Segments 3 and 5, closest to the left inferior pulmonary vein, had significantly higher fibrosis (40.42% ± 23.96 and 25.82% ± 21.24, respectively; P < 0.001), compared with other segments. Segments 8 and 10 in the anterior wall contained the lowest fibrosis (2.54% ± 5.78 and 3.82% ± 11.59, respectively; P < 0.001). Age >60 years was significantly associated with increased LA fibrosis [95% confidence interval (CI) 0.19-8.39, P = 0.04] and persistent AF approached significance (95% CI -0.19% to 7.83%, P = 0.08).

Conclusion

In patients with AF, the fibrotic area is preferentially located at the posterior wall and floor around the antrum of the left inferior pulmonary vein. Age >60 years was associated with increased fibrosis.

A rule-based method to model myocardial fiber orientation in cardiac biventricular geometries with outflow tracts

Rule-based methods are often used for assigning fiber orientation to cardiac anatomical models. However, existing methods have been developed using data mostly from the left ventricle. As a consequence, fiber information obtained from rule-based methods often does not match histological data in other areas of the heart such as the right ventricle, having a negative impact in cardiac simulations beyond the left ventricle. In this work, we present a rule-based method where fiber orientation is separately modeled in each ventricle following observations from histology. This allows to create detailed fiber orientation in specific regions such as the endocardium of the right ventricle, the interventricular septum, and the outflow tracts. We also carried out electrophysiological simulations involving these structures and with different fiber configurations. In particular, we built a modeling pipeline for creating patient-specific volumetric meshes of biventricular geometries, including the outflow tracts, and subsequently simulate the electrical wavefront propagation in outflow tract ventricular arrhythmias with different origins for the ectopic focus. The resulting simulations with the proposed rule-based method showed a very good agreement with clinical parameters such as the 10 ms isochrone ratio in a cohort of nine patients suffering from this type of arrhythmia. The developed modeling pipeline confirms its potential for an in silico identification of the site of origin in outflow tract ventricular arrhythmias before clinical intervention.

In silico Optimization of Left Atrial Appendage Occluder Implantation Using Interactive and Modeling Tools

According to clinical studies, around one third of patients with atrial fibrillation (AF) will suffer a stroke during their lifetime. Between 70 and 90% of these strokes are caused by thrombus formed in the left atrial appendage. In patients with contraindications to oral anticoagulants, a left atrial appendage occluder (LAAO) is often implanted to prevent blood flow entering in the LAA. A limited range of LAAO devices is available, with different designs and sizes. Together with the heterogeneity of LAA morphology, these factors make LAAO success dependent on clinician's experience. A sub-optimal LAAO implantation can generate thrombi outside the device, eventually leading to stroke if not treated. The aim of this study was to develop clinician-friendly tools based on biophysical models to optimize LAAO device therapies. A web-based 3D interactive virtual implantation platform, so-called VIDAA, was created to select the most appropriate LAAO configurations (type of device, size, landing zone) for a given patient-specific LAA morphology. An initial LAAO configuration is proposed in VIDAA, automatically computed from LAA shape features (centreline, diameters). The most promising LAAO settings and LAA geometries were exported from VIDAA to build volumetric meshes and run Computational Fluid Dynamics (CFD) simulations to assess blood flow patterns after implantation. Risk of thrombus formation was estimated from the simulated hemodynamics with an index combining information from blood flow velocity and complexity. The combination of the VIDAA platform with in silico indices allowed to identify the LAAO configurations associated to a lower risk of thrombus formation; device positioning was key to the creation of regions with turbulent flows after implantation. Our results demonstrate the potential for optimizing LAAO therapy settings during pre-implant planning based on modeling tools and contribute to reduce the risk of thrombus formation after treatment.

Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?

Delineation of the left ventricular cavity, myocardium, and right ventricle from cardiac magnetic resonance images (multi-slice 2-D cine MRI) is a common clinical task to establish diagnosis. The automation of the corresponding tasks has thus been the subject of intense research over the past decades. In this paper, we introduce the "Automatic Cardiac Diagnosis Challenge" dataset (ACDC), the largest publicly available and fully annotated dataset for the purpose of cardiac MRI (CMR) assessment. The dataset contains data from 150 multi-equipments CMRI recordings with reference measurements and classification from two medical experts. The overarching objective of this paper is to measure how far state-of-the-art deep learning methods can go at assessing CMRI, i.e., segmenting the myocardium and the two ventricles as well as classifying pathologies. In the wake of the 2017 MICCAI-ACDC challenge, we report results from deep learning methods provided by nine research groups for the segmentation task and four groups for the classification task. Results show that the best methods faithfully reproduce the expert analysis, leading to a mean value of 0.97 correlation score for the automatic extraction of clinical indices and an accuracy of 0.96 for automatic diagnosis. These results clearly open the door to highly accurate and fully automatic analysis of cardiac CMRI. We also identify scenarios for which deep learning methods are still failing. Both the dataset and detailed results are publicly available online, while the platform will remain open for new submissions.

Mind the gap: Quantification of incomplete ablation patterns after pulmonary vein isolation using minimum path search

Pulmonary vein isolation (PVI) is a common procedure for the treatment of atrial fibrillation (AF) since the initial trigger for AF frequently originates in the pulmonary veins. A successful isolation produces a continuous lesion (scar) completely encircling the veins that stops activation waves from propagating to the atrial body. Unfortunately, the encircling lesion is often incomplete, becoming a combination of scar and gaps of healthy tissue. These gaps are potential causes of AF recurrence, which requires a redo of the isolation procedure. Late-gadolinium enhanced cardiac magnetic resonance (LGE-CMR) is a non-invasive method that may also be used to detect gaps, but it is currently a time-consuming process, prone to high inter-observer variability. In this paper, we present a method to semi-automatically identify and quantify ablation gaps. Gap quantification is performed through minimum path search in a graph where every node is a scar patch and the edges are the geodesic distances between patches. We propose the Relative Gap Measure (RGM) to estimate the percentage of gap around a vein, which is defined as the ratio of the overall gap length and the total length of the path that encircles the vein. Additionally, an advanced version of the RGM has been developed to integrate gap quantification estimates from different scar segmentation techniques into a single figure-of-merit. Population-based statistical and regional analysis of gap distribution was performed using a standardised parcellation of the left atrium. We have evaluated our method on synthetic and clinical data from 50 AF patients who underwent PVI with radiofrequency ablation. The population-based analysis concluded that the left superior PV is more prone to lesion gaps while the left inferior PV tends to have less gaps (p < .05 in both cases), in the processed data. This type of information can be very useful for the optimization and objective assessment of PVI interventions.

Dielectric properties of colon polyps, cancer, and normal mucosa: Ex vivo measurements from 0.5 to 20 GHz

PURPOSE

Colorectal cancer is highly preventable by detecting and removing polyps, which are the precursors. Currently, the most accurate test is colonoscopy, but still misses 22% of polyps due to visualization limitations. In this paper, we preliminary assess the potential of microwave imaging and dielectric properties (e.g., complex permittivity) as a complementary method for detecting polyps and cancer tissue in the colon. The dielectric properties of biological tissues have been used in a wide variety of applications, including safety assessment of wireless technologies and design of medical diagnostic or therapeutic techniques (microwave imaging, hyperthermia, and ablation). The main purpose of this work is to measure the complex permittivity of different types of colon polyps, cancer, and normal mucosa in ex vivo human samples to study if the dielectric properties are appropriate for classification purposes.

METHODS

The complex permittivity of freshly excised healthy colon tissue, cancer, and histological samples of different types of polyps from 23 patients was characterized using an open-ended coaxial probe between 0.5 and 20 GHz. The obtained measurements were classified into five tissue groups before applying a data reduction step with a frequency dispersive single-pole Debye model. The classification was finally compared with pathological analysis of tissue samples, which is the gold standard.

RESULTS

The complex permittivity progressively increases as the tissue degenerates from normal to cancer. When comparing to the gold-standard histological tissue analysis, the sensitivity and specificity of the proposed method is the following: 100% and 95% for cancer diagnosis; 91% and 62% for adenomas with high-grade dysplasia; 100% and 61% for adenomas with low-grade dysplasia; and 100% and 74% for hyperplastic polyps, respectively. In addition, complex permittivity measurements were independent of the lesion shape and size, which is also an interesting property comparing to current colonoscopy techniques.

CONCLUSIONS

The contrast in complex permittivities between normal and abnormal colon tissues presented here for the first time demonstrate the potential of these measurements for tissue classification. It also opens the door to the development of a microwave endoscopic device to complement the outcomes of colonoscopy with functional tissue information.