A machine learning-based score for precise echocardiographic assessment of cardiac remodelling in hypertensive young adults.

Aims: Accurate staging of hypertension-related cardiac changes, before the development of significant left ventricular hypertrophy, could help guide early prevention advice. We evaluated whether a novel semi-supervised machine learning approach could generate a clinically meaningful summary score of cardiac remodelling in hypertension. Methods and results: A contrastive trajectories inference approach was applied to data collected from three UK studies of young adults. Low-dimensional variance was identified in 66 echocardiography variables from participants with hypertension (systolic ≥160 mmHg) relative to a normotensive group (systolic < 120 mmHg) using a contrasted principal component analysis. A minimum spanning tree was constructed to derive a normalized score for each individual reflecting extent of cardiac remodelling between zero (health) and one (disease). Model stability and clinical interpretability were evaluated as well as modifiability in response to a 16-week exercise intervention. A total of 411 young adults (29 ± 6 years) were included in the analysis, and, after contrastive dimensionality reduction, 21 variables characterized >80% of data variance. Repeated scores for an individual in cross-validation were stable (root mean squared deviation = 0.1 ± 0.002) with good differentiation of normotensive and hypertensive individuals (area under the receiver operating characteristics 0.98). The derived score followed expected hypertension-related patterns in individual cardiac parameters at baseline and reduced after exercise, proportional to intervention compliance (P = 0.04) and improvement in ventilatory threshold (P = 0.01). Conclusion: A quantitative score that summarizes hypertension-related cardiac remodelling in young adults can be generated from a computational model. This score might allow more personalized early prevention advice, but further evaluation of clinical applicability is required.

The role of artificial intelligence in hypertensive disorders of pregnancy: towards personalized healthcare.

INTRODUCTION: Guidelines advise ongoing follow-up of patients after hypertensive disorders of pregnancy (HDP) to assess cardiovascular risk and manage future patient-specific pregnancy conditions. However, there are limited tools available to monitor patients, with those available tending to be simple risk assessments that lack personalization. A promising approach could be the emerging artificial intelligence (AI)-based techniques, developed from big patient datasets to provide personalized recommendations for preventive advice. AREAS COVERED: In this narrative review, we discuss the impact of integrating AI and big data analysis for personalized cardiovascular care, focusing on the management of HDP. EXPERT OPINION: The pathophysiological response of women to pregnancy varies, and deeper insight into each response can be gained through a deeper analysis of the medical history of pregnant women based on clinical records and imaging data. Further research is required to be able to implement AI for clinical cases using multi-modality and multi-organ assessment, and this could expand both knowledge on pregnancy-related disorders and personalized treatment planning.

Automatic 3D Surface Reconstruction of the Left Atrium From Clinically Mapped Point Clouds Using Convolutional Neural Networks.

Point clouds are a widely used format for storing information in a memory-efficient and easily manipulatable representation. However, research in the application of point cloud mapping and subsequent organ reconstruction with deep learning, is limited. In particular, current methods for left atrium (LA) visualization using point clouds recorded from clinical mapping during cardiac ablation are proprietary and remain difficult to validate. Many clinics rely on additional imaging such as MRIs/CTs to improve the accuracy of LA mapping. In this study, for the first time, we proposed a novel deep learning framework for the automatic 3D surface reconstruction of the LA directly from point clouds acquired via widely used clinical mapping systems. The backbone of our framework consists of a 30-layer 3D fully convolutional neural network (CNN). The architecture contains skip connections that perform multi-resolution processing to maximize information extraction from the point clouds and ensure a high-resolution prediction by combining features at different receptive levels. We used large kernels with increased receptive fields to address the sparsity of the point clouds. Residual blocks and activation normalization were further implemented to improve the feature learning on sparse inputs. By utilizing a light-weight design with low-depth layers, our CNN took approximately 10 s per patient. Independent testing on two cross-modality clinical datasets showed excellent dice scores of 93% and surface-to-surface distances below 1 pixel. Overall, our study may provide a more efficient, cost-effective 3D LA reconstruction approach during ablation procedures, and potentially lead to improved treatment of cardiac diseases.

Enhancing the detection of atrial fibrillation from wearable sensors with neural style transfer and convolutional recurrent networks.

Electrocardiograms (ECG) provide an effective, non-invasive approach for clinical diagnosis and monitoring treatment in patients with cardiac diseases including the most common cardiac arrhythmia, atrial fibrillation (AF). Portable ECG recording devices including Apple Watch and Kardia devices have been developed for AF detection. However, the efficacy of these smart devices has not been fully validated. We aimed to develop an open-source deep learning framework for automatic AF detection using the largest publicly available single-lead ECG dataset through a mobile Kardia device enhanced with style transfer-driven data augmentation. We developed and validated a 37-layer convolutional recurrent network (CRN) using 5,834 single-lead ECGs with a mean length of 30 seconds from the 2017 PhysioNet Challenge to automatically detect sinus rhythm and AF. To address the challenge of a lack of a large number of AF samples, we proposed a novel style transfer generator that fuses patient-specific clinical ECGs and mathematically modelled ECG features to synthesize realistic ECGs by five-fold. The differences between synthesized and clinical ECGs were analyzed by studying their average ECG morphologies and frequency distributions. Our results indicated the style transfer-driven data augmentation was not classifier-dependent. Validation on 2,917 clinical ECGs showed an F1 score of 96.4%, with the generated ECGs contributing to a 3% improvement in AF detection for the Kardia event recorder. By developing and evaluating our approach on an open-source ECG dataset, we have demonstrated that our framework is both robust and verifiable, and potentially can be used in portable devices for effective AF classification.

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.

Mini Review: Deep Learning for Atrial Segmentation From Late Gadolinium-Enhanced MRIs.

Segmentation and 3D reconstruction of the human atria is of crucial importance for precise diagnosis and treatment of atrial fibrillation, the most common cardiac arrhythmia. However, the current manual segmentation of the atria from medical images is a time-consuming, labor-intensive, and error-prone process. The recent emergence of artificial intelligence, particularly deep learning, provides an alternative solution to the traditional methods that fail to accurately segment atrial structures from clinical images. This has been illustrated during the recent 2018 Atrial Segmentation Challenge for which most of the challengers developed deep learning approaches for atrial segmentation, reaching high accuracy (>90% Dice score). However, as significant discrepancies exist between the approaches developed, many important questions remain unanswered, such as which deep learning architectures and methods to ensure reliability while achieving the best performance. In this paper, we conduct an in-depth review of the current state-of-the-art of deep learning approaches for atrial segmentation from late gadolinium-enhanced MRIs, and provide critical insights for overcoming the main hindrances faced in this task.

A robust computational framework for estimating 3D Bi-Atrial chamber wall thickness.

Atrial fibrillation (AF) is the most prevalent form of cardiac arrhythmia. The atrial wall thickness (AWT) can potentially improve our understanding of the mechanism underlying atrial structure that drives AF and provides important clinical information. However, most existing studies for estimating AWT rely on ruler-based measurements performed on only a few selected locations in 2D or 3D using digital calipers. Only a few studies have developed automatic approaches to estimate the AWT in the left atrium, and there are currently no methods to robustly estimate the AWT of both atrial chambers. Therefore, we have developed a computational pipeline to automatically calculate the 3D AWT across bi-atrial chambers and extensively validated our pipeline on both ex vivo and in vivo human atria data. The atrial geometry was first obtained by segmenting the atrial wall from the MRIs using a novel machine learning approach. The epicardial and endocardial surfaces were then separated using a multi-planar convex hull approach to define boundary conditions, from which, a Laplace equation was solved numerically to automatically separate bi-atrial chambers. To robustly estimate the AWT in each atrial chamber, coupled partial differential equations by coupling the Laplace solution with two surface trajectory functions were formulated and solved. Our pipeline enabled the reconstruction and visualization of the 3D AWT for bi-atrial chambers with a relative error of 8% and outperformed existing algorithms by >7%. Our approach can potentially lead to improved clinical diagnosis, patient stratification, and clinical guidance during ablation treatment for patients with AF.

Fully Automatic Left Atrium Segmentation From Late Gadolinium Enhanced Magnetic Resonance Imaging Using a Dual Fully Convolutional Neural Network.

Atrial fibrillation (AF) is the most prevalent form of cardiac arrhythmia. Current treatments for AF remain suboptimal due to a lack of understanding of the underlying atrial structures that directly sustain AF. Existing approaches for analyzing atrial structures in 3-D, especially from late gadolinium-enhanced (LGE) magnetic resonance imaging, rely heavily on manual segmentation methods that are extremely labor-intensive and prone to errors. As a result, a robust and automated method for analyzing atrial structures in 3-D is of high interest. We have, therefore, developed AtriaNet, a 16-layer convolutional neural network (CNN), on 154 3-D LGE-MRIs with a spatial resolution of 0.625 mm ×0.625 mm ×1.25 mm from patients with AF, to automatically segment the left atrial (LA) epicardium and endocardium. AtriaNet consists of a multi-scaled, dual-pathway architecture that captures both the local atrial tissue geometry and the global positional information of LA using 13 successive convolutions and three further convolutions for merging. By utilizing computationally efficient batch prediction, AtriaNet was able to successfully process each 3-D LGE-MRI within 1 min. Furthermore, benchmarking experiments have shown that AtriaNet has outperformed the state-of-the-art CNNs, with a DICE score of 0.940 and 0.942 for the LA epicardium and endocardium, respectively, and an inter-patient variance of <0.001. The estimated LA diameter and volume computed from the automatic segmentations were accurate to within 1.59 mm and 4.01 cm3 of the ground truths. Our proposed CNN was tested on the largest known data set for LA segmentation, and to the best of our knowledge, it is the most robust approach that has ever been developed for segmenting LGE-MRIs. The increased accuracy of atrial reconstruction and analysis could potentially improve the understanding and treatment of AF.

ECG signal classification for the detection of cardiac arrhythmias using a convolutional recurrent neural network.

OBJECTIVE: The electrocardiogram (ECG) provides an effective, non-invasive approach for clinical diagnosis in patients with cardiac diseases such as atrial fibrillation (AF). AF is the most common cardiac rhythm disturbance and affects ~2% of the general population in industrialized countries. Automatic AF detection in clinics remains a challenging task due to the high inter-patient variability of ECGs, and unsatisfactory existing approaches for AF diagnosis (e.g. atrial or ventricular activity-based analyses). APPROACH: We have developed RhythmNet, a 21-layer 1D convolutional recurrent neural network, trained using 8528 single-lead ECG recordings from the 2017 PhysioNet/Computing in Cardiology (CinC) Challenge, to classify ECGs of different rhythms including AF automatically. Our RhythmNet architecture contained 16 convolutions to extract features directly from raw ECG waveforms, followed by three recurrent layers to process ECGs of varying lengths and to detect arrhythmia events in long recordings. Large 15 × 1 convolutional filters were used to effectively learn the detailed variations of the signal within small time-frames such as the P-waves and QRS complexes. We employed residual connections throughout RhythmNet, along with batch-normalization and rectified linear activation units to improve convergence during training. MAIN RESULTS: We evaluated our algorithm on 3658 testing data and obtained an F 1 accuracy of 82% for classifying sinus rhythm, AF, and other arrhythmias. RhythmNet was also ranked 5th in the 2017 CinC Challenge. SIGNIFICANCE: Potentially, our approach could aid AF diagnosis in clinics and be used for patient self-monitoring to improve the early detection and effective treatment of AF.

A Machine Learning Aided Systematic Review and Meta-Analysis of the Relative Risk of Atrial Fibrillation in Patients With Diabetes Mellitus.

Background: Meta-analysis is a widely used tool in which weighted information from multiple similar studies is aggregated to increase statistical power. However, the exponential growth of publications in key areas of medical science has rendered manual identification of relevant studies increasingly time-consuming. The aim of this work was to develop a machine learning technique capable of robust automatic study selection for meta-analysis. We have validated this approach with an up-to-date meta-analysis to investigate the association between diabetes mellitus (DM) and new-onset atrial fibrillation (AF). Methods: The PubMed online database was searched from 1960 to September 2017 where 4,177 publications that mentioned both DM and AF were identified. Relevant studies were selected as follows. First, publications were clustered based on common text features using an unsupervised K-means algorithm. Clusters that best matched the selected set of potentially relevant studies (a "training" set of 139 articles) were then identified by using maximum entropy classification. The 139 articles selected automatically on this basis were screened manually to identify potentially relevant studies. To determine the validity of the automated process, a parallel set of studies was also assembled by manually screening all initially searched publications. Finally, detailed manual selection was performed on the full texts of the studies in both sets using standard criteria. Quality assessment, meta-regression random-effects models, sensitivity analysis and publication bias assessment were then conducted. Results: Machine learning-assisted screening identified the same 29 studies for meta-analysis as those identified by using manual screening alone. Machine learning enabled more robust and efficient study selection, reducing the number of studies needed for manual screening from 4,177 to 556 articles. A pooled analysis using the most conservative estimates indicated that patients with DM had ~49% greater risk of developing AF compared with individuals without DM. After adjusting for three additional risk factors i.e., hypertension, obesity and heart disease, the relative risk was 23%. Using multivariate adjusted models, the risk for developing AF in patients with DM was similar for all DM subtypes. Women with DM were 24% more likely to develop AF than men with DM. The risk for new-onset AF in patients with DM has also increased over the years. Conclusions: We have developed a novel machine learning method to identify publications suitable for inclusion in meta-analysis.This approach has the capacity to provide for a more efficient and more objective study selection process for future such studies. We have used it to demonstrate that DM is a strong, independent risk factor for AF, particularly for women.

Segmentation of histological images and fibrosis identification with a convolutional neural network.

Segmentation of histological images is one of the most crucial tasks for many biomedical analyses involving quantification of certain tissue types, such as fibrosis via Masson's trichrome staining. However, challenges are posed by the high variability and complexity of structural features in such images, in addition to imaging artifacts. Further, the conventional approach of manual thresholding is labor-intensive, and highly sensitive to inter- and intra-image intensity variations. An accurate and robust automated segmentation method is of high interest. We propose and evaluate an elegant convolutional neural network (CNN) designed for segmentation of histological images, particularly those with Masson's trichrome stain. The network comprises 11 successive convolutional - rectified linear unit - batch normalization layers. It outperformed state-of-the-art CNNs on a dataset of cardiac histological images (labeling fibrosis, myocytes, and background) with a Dice similarity coefficient of 0.947. With 100 times fewer (only 300,000) trainable parameters than the state-of-the-art, our CNN is less susceptible to overfitting, and is efficient. Additionally, it retains image resolution from input to output, captures fine-grained details, and can be trained end-to-end smoothly. To the best of our knowledge, this is the first deep CNN tailored to the problem of concern, and may potentially be extended to solve similar segmentation tasks to facilitate investigations into pathology and clinical treatment.