Delineation of intracavitary electrograms for the automatic quantification of decrement-evoked potentials in the coronary sinus with deep-learning techniques.

Cardiac arrhythmias cause depolarization waves to conduct unevenly on the myocardial surface, potentially delaying local components with respect to a previous beat when stimulated at faster frequencies. Despite the diagnostic value of localizing the distinct local electrocardiogram (EGM) components for identifying regions with decrement-evoked potentials (DEEPs), current software solutions do not perform automatic signal quantification. Electrophysiologists must manually measure distances on the EGM signals to assess the existence of DEEPs during pacing or extra-stimuli protocols. In this work, we present a deep learning (DL)-based algorithm to identify decrement in atrial components (measured in the coronary sinus) with respect to their ventricular counterparts from EGM signals, for disambiguating between accessory pathways (APs) and atrioventricular re-entrant tachycardias (AVRTs). Several U-Net and W-Net neural networks with different configurations were trained on a private dataset of signals from the coronary sinus (312 EGM recordings from 77 patients who underwent AP or AVRT ablation). A second, separate dataset was annotated for clinical validation, with clinical labels associated to EGM fragments in which decremental conduction was elucidated. To alleviate data scarcity, a synthetic data augmentation method was developed for generating EGM recordings. Moreover, two novel loss functions were developed to minimize false negatives and delineation errors. Finally, the addition of self-attention mechanisms and their effect on model performance was explored. The best performing model was a W-Net model with 6 levels, optimized solely with the Dice loss. The model obtained precisions of 91.28%, 77.78% and of 100.0%, and recalls of 94.86%, 95.25% and 100.0% for localizing local field, far field activations, and extra-stimuli, respectively. The clinical validation model demonstrated good overall agreement with respect to the evaluation of decremental properties. When compared to the criteria of electrophysiologists, the automatic exclusion step reached a sensitivity of 87.06% and a specificity of 97.03%. Out of the non-excluded signals, a sensitivity of 96.77% and a specificity of 95.24% was obtained for classifying them into decremental and non-decremental potentials. Current results show great promise while being, to the best of our knowledge, the first tool in the literature allowing the delineation of all local components present in an EGM recording. This is of capital importance at advancing processing for cardiac electrophysiological procedures and reducing intervention times, as many diagnosis procedures are performed by comparing segments or late potentials in subsequent cardiac cycles.

Impact of left atrial wall motion assumptions in fluid simulations on proposed predictors of thrombus formation.

Atrial fibrillation (AF) poses a significant risk of stroke due to thrombus formation, which primarily occurs in the left atrial appendage (LAA). Medical image-based computational fluid dynamics (CFD) simulations can provide valuable insight into patient-specific hemodynamics and could potentially enhance personalized assessment of thrombus risk. However, the importance of accurately representing the left atrial (LA) wall dynamics has not been fully resolved. In this study, we compared four modeling scenarios; rigid walls, a generic wall motion based on a reference motion, a semi-generic wall motion based on patient-specific motion, and patient-specific wall motion based on medical images. We considered a LA geometry acquired from 4D computed tomography during AF, systematically performed convergence tests to assess the numerical accuracy of our solution strategy, and quantified the differences between the four approaches. The results revealed that wall motion had no discernible impact on LA cavity hemodynamics, nor on the markers that indicate thrombus formation. However, the flow patterns within the LAA deviated significantly in the rigid model, indicating that the assumption of rigid walls may lead to errors in the estimated risk factors. In contrast, the generic, semi-generic, and patient-specific cases were qualitatively similar. The results highlight the crucial role of wall motion on hemodynamics and predictors of thrombus formation, and also demonstrate the potential of using a generic motion model as a surrogate for the more complex patient-specific motion. While the present study considered a single case, the employed CFD framework is entirely open-source and designed for adaptability, allowing for integration of additional models and generic motions.

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.

Personalized pulmonary vein isolation with very high-power short-duration lesions guided by left atrial wall thickness: the QDOT-by-LAWT randomized trial.

AIMS: Pulmonary vein isolation (PVI) for paroxysmal atrial fibrillation (PAF) using very high-power short-duration (vHPSD) radiofrequency (RF) ablation proved to be safe and effective. However, vHPSD applications result in shallower lesions that might not be always transmural. Multidetector computed tomography-derived left atrial wall thickness (LAWT) maps could enable a thickness-guided switching from vHPSD to the standard-power ablation mode. The aim of this randomized trial was to compare the safety, the efficacy, and the efficiency of a LAWT-guided vHPSD PVI approach with those of the CLOSE protocol for PAF ablation (NCT04298177). METHODS AND RESULTS: Consecutive patients referred for first-time PAF ablation were randomized on a 1:1 basis. In the QDOT-by-LAWT arm, for LAWT ≤2.5 mm, vHPSD ablation was performed; for points with LAWT > 2.5 mm, standard-power RF ablation titrating ablation index (AI) according to the local LAWT was performed. In the CLOSE arm, LAWT information was not available to the operator; ablation was performed according to the CLOSE study settings: AI ≥400 at the posterior wall and ≥550 at the anterior wall. A total of 162 patients were included. In the QDOT-by-LAWT group, a significant reduction in procedure time (40 vs. 70 min; P < 0.001) and RF time (6.6 vs. 25.7 min; P < 0.001) was observed. No difference was observed between the groups regarding complication rate (P = 0.99) and first-pass isolation (P = 0.99). At 12-month follow-up, no significant differences occurred in atrial arrhythmia-free survival between groups (P = 0.88). CONCLUSION: LAWT-guided PVI combining vHPSD and standard-power ablation is not inferior to the CLOSE protocol in terms of 1-year atrial arrhythmia-free survival and demonstrated a reduction in procedural and RF times.

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.

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.

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.

Personalized pulmonary vein antrum isolation guided by left atrial wall thickness for persistent atrial fibrillation.

AIMS: Pulmonary vein (PV) antrum isolation proved to be effective for treating persistent atrial fibrillation (PeAF). We sought to investigate the results of a personalized approach aimed at adapting the ablation index (AI) to the local left atrial wall thickness (LAWT) in a cohort of consecutive patients with PeAF. METHODS AND RESULTS: Consecutive patients referred for PeAF first ablation were prospectively enrolled. The LAWT three-dimensional maps were obtained from pre-procedure multidetector computed tomography and integrated into the navigation system. Ablation index was titrated according to the local LAWT, and the ablation line was personalized to avoid the thickest regions while encircling the PV antrum. A total of 121 patients (69.4% male, age 64.5 ± 9.5 years) were included. Procedure time was 57 min (IQR 50-67), fluoroscopy time was 43 s (IQR 20-71), and radiofrequency (RF) time was 16.5 min (IQR 14.3-18.4). The median AI tailored to the local LAWT was 387 (IQR 360-410) for the anterior wall and 335 (IQR 300-375) for the posterior wall. First-pass PV antrum isolation was obtained in 103 (85%) of the right PVs and 103 (85%) of the left PVs. Median LAWT values were higher for PVs without first-pass isolation as compared to the whole cohort (P = 0.02 for left PVs and P = 0.03 for right PVs). Recurrence-free survival was 79% at 12 month follow-up. CONCLUSION: In this prospective study, LAWT-guided PV antrum isolation for PeAF was effective and efficient, requiring low procedure, fluoroscopy, and RF time. A randomized trial comparing the LAWT-guided ablation with the standard of practice is in progress (ClinicalTrials.gov, NCT05396534).

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.

A hybrid clinical and electrocardiographic score to predict the origin of outflow tract ventricular arrhythmias.

BACKGROUND: To predict the outflow tract ventricular arrhythmias (OTVA) site of origin (SOO) before the ablation procedure has important practical implications. The present study sought to prospectively evaluate the accuracy of a clinical and electrocardiographic hybrid algorithm (HA) for the prediction of OTVAs-SOO, and at the same time to develop and to prospectively validate a new score with improved discriminatory capacity. METHODS: In this multicenter study, we prospectively enrolled consecutive patients referred for OTVA ablation (N = 202), and we divided them in a derivation sample and a validation cohort. Surface ECGs during OTVA were analyzed to compare previous published ECG-only criteria and to develop a new score. RESULTS: In the derivation sample (N = 105), the correct prediction rate of HA and ECG-only criteria ranged from 74 to 89%. R-wave amplitude in V3 was the best ECG parameter for discriminating LVOT origin in V3 precordial transition (V3PT) patients, and was incorporated to the novel weighted hybrid score (WHS). WHS correctly classified 99 (94.2%) patients, presenting 90% sensitivity and 96% specificity (AUC 0.97) in the entire population; WHS mantained a 87% sensitivity and 91% specificity (AUC 0.95) in patients with V3PT subgroup. The high discriminatory capacity was confirmed in the validation sample (N = 97): the WHS exhibited an AUC (0.93), and a WHS ≥ 2 allowed a correct prediction of LVOT origin in 87 (90.0%) cases, yielding a sensitivity of 87% and specificity of 90%; moreover, the V3PT subgroup showed an AUC of 0.92, and a punctuation ≥ 2 predicted an LVOT origin with a sensitivity of 94% and specificity of 78%. CONCLUSIONS: The novel hybrid score has proved to accurately anticipate the OTVA's origin, even in those with a V3 precordial transition. A Weighted hybrid score. B Typical examples of the use of the weighted hybrid score. C ROC analysis of WHS and previous ECG criteria for prediction of LVOT origin in the derivation cohort. D ROC analysis of WHS and previous ECG criteria for prediction of LVOT origin in the V3 precordial transition OTVA subgroup.

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.

Attri-VAE: Attribute-based interpretable representations of medical images with variational autoencoders.

Deep learning (DL) methods where interpretability is intrinsically considered as part of the model are required to better understand the relationship of clinical and imaging-based attributes with DL outcomes, thus facilitating their use in the reasoning behind the medical decisions. Latent space representations built with variational autoencoders (VAE) do not ensure individual control of data attributes. Attribute-based methods enforcing attribute disentanglement have been proposed in the literature for classical computer vision tasks in benchmark data. In this paper, we propose a VAE approach, the Attri-VAE, that includes an attribute regularization term to associate clinical and medical imaging attributes with different regularized dimensions in the generated latent space, enabling a better-disentangled interpretation of the attributes. Furthermore, the generated attention maps explained the attribute encoding in the regularized latent space dimensions. Using the Attri-VAE approach we analyzed healthy and myocardial infarction patients with clinical, cardiac morphology, and radiomics attributes. The proposed model provided an excellent trade-off between reconstruction fidelity, disentanglement, and interpretability, outperforming state-of-the-art VAE approaches according to several quantitative metrics. The resulting latent space allowed the generation of realistic synthetic data in the trajectory between two distinct input samples or along a specific attribute dimension to better interpret changes between different cardiac conditions.

Preventive substrate ablation in chronic post-myocardial infarction patients with high-risk scar characteristics for ventricular arrhythmias: rationale and design of PREVENT-VT study.

BACKGROUND: Recent studies showed that an early strategy for ventricular tachycardia (VT) ablation resulted in reduction of VT episodes or mortality. Cardiac magnetic resonance (CMR)-derived border zone channel (BZC) mass has proved to be a strong non-invasive predictor of VT in post-myocardial infarction (MI). CMR-guided VT substrate ablation proved to be safe and effective for reducing sudden cardiac death (SCD) and VA occurrence. METHODS: PREVENT-VT is a prospective, randomized, multicenter, and controlled trial designed to evaluate the safety and efficacy of prophylactic CMR-guided VT substrate ablation in chronic post-MI patients with CMR-derived arrhythmogenic scar characteristics. Chronic post-MI patients with late gadolinium enhancement (LGE) CMR will be evaluated. CMR images will be post-processed and the BZC mass measured: patients with a BZC mass > 5.15 g will be eligible. Consecutive patients will be enrolled at 3 centers and randomized on a 1:1 basis to undergo a VT substrate ablation (ABLATE arm) or optimal medical treatment (OMT arm). Primary prevention ICD will be implanted following guideline recommendations, while non-ICD candidates will be implanted with an implantable cardiac monitor (ICM). The primary endpoint is a composite outcome of sudden cardiac death (SCD) or sustained monomorphic VT, either treated by an ICD or documented with ICM. Secondary endpoints are procedural safety and efficiency outcomes of CMR-guided ablation. DISCUSSION: In some patients, the first VA episode causes SCD or severe neurological damage. The aim of the PREVENT-VT is to evaluate whether primary preventive substrate ablation may be a safe and effective prophylactic therapy for reducing SCD and VA occurrence in patients with previous MI and high-risk scar characteristics based on CMR. TRIAL REGISTRATION: ClinicalTrials.gov, NCT04675073, registered on January 1, 2021.

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.

Relationship between the posterior atrial wall and the esophagus: esophageal position and temperature measurement during atrial fibrillation ablation (AWESOME-AF). A randomized controlled trial.

BACKGROUND: Pulmonary vein isolation (PVI) implies unavoidable ablation lesions to the left atrial posterior wall, which is closely related to the esophagus, leading to several potential complications. This study evaluates the usefulness of the esophageal fingerprint in avoiding temperature rises during paroxysmal atrial fibrillation (PAF) ablation. METHODS: Isodistance maps of the atrio-esophageal relationship (esophageal fingerprint) were derived from the preprocedural computerized tomography. Patients were randomized (1:1) into two groups: (1) PRINT group, the PVI line was modified according to the esophageal fingerprint; (2) CONTROL group, standard PVI with operator blinded to the fingerprint. The primary endpoint was temperature rise detected by intraluminal esophageal temperature probe monitoring. Ablation settings were as specified on the Ablate BY-LAW study protocol. RESULTS: Sixty consecutive patients referred for paroxysmal AF ablation were randomized (42 (70%) men, mean age 60 ± 11 years). Temperature rise (> 39.1 °C) occurred in 5 (16%) patients in the PRINT group vs. 17 (56%) in the CONTROL group (p < 0.01). Three AF recurrences were documented at a mean follow-up of 12 ± 3 months (one (3%) in the PRINT group and 2 (6.6%) in the CONTROL group, p = 0.4). CONCLUSION: The esophageal fingerprint allows for a reliable identification of the esophageal position and its use for PVI line deployment results in less frequent esophageal temperature rises when compared to the standard approach. Further studies are needed to evaluate the impact of PVI line modification to avoid esophageal heating on long-term outcomes. The development of new imaging-derived tools could ultimately improve patient safety (NCT04394923).

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.