Fully Automated Myocardial Strain Estimation from Cardiovascular MRI-tagged Images Using a Deep Learning Framework in the UK Biobank

Deriving phenotype-representative left ventricular flow patterns by reduced-order modeling and classification

BACKGROUND

Extracting phenotype-representative flow patterns and their associated numerical metrics is a bottleneck in the clinical translation of advanced cardiac flow imaging modalities. We hypothesized that reduced-order models (ROMs) are a suitable strategy for deriving simple and interpretable clinical metrics of intraventricular flow suitable for further assessments. Combined with machine learning (ML) flow-based ROMs could provide new insight to help diagnose and risk-stratify patients.

METHODS

We analyzed 2D color-Doppler echocardiograms of 81 non-ischemic dilated cardiomyopathy (DCM) patients, 51 hypertrophic cardiomyopathy (HCM) patients, and 77 normal volunteers (Control). We applied proper orthogonal decomposition (POD) to build patient-specific and cohort-specific ROMs of LV flow. Each ROM aggregates a low number of components representing a spatially dependent velocity map modulated along the cardiac cycle by a time-dependent coefficient. We tested three classifiers using deliberately simple ML analyses of these ROMs with varying supervision levels. In supervised models, hyperparameter grid search was used to derive the ROMs that maximize classification power. The classifiers were blinded to LV chamber geometry and function. We ran vector flow mapping on the color-Doppler sequences to help visualize flow patterns and interpret the ML results.

RESULTS

POD-based ROMs stably represented each cohort through 10-fold cross-validation. The principal POD mode captured >80 % of the flow kinetic energy (KE) in all cohorts and represented the LV filling/emptying jets. Mode 2 represented the diastolic vortex and its KE contribution ranged from <1 % (HCM) to 13 % (DCM). Semi-unsupervised classification using patient-specific ROMs revealed that the KE ratio of these two principal modes, the vortex-to-jet (V2J) energy ratio, is a simple, interpretable metric that discriminates DCM, HCM, and Control patients. Receiver operating characteristic curves using V2J as classifier had areas under the curve of 0.81, 0.91, and 0.95 for distinguishing HCM vs. Control, DCM vs. Control, and DCM vs. HCM, respectively.

CONCLUSIONS

Modal decomposition of cardiac flow can be used to create ROMs of normal and pathological flow patterns, uncovering simple interpretable flow metrics with power to discriminate disease states, and particularly suitable for further processing using ML.

The Role of Artificial Intelligence in Cardiac Imaging

Artificial intelligence (AI) is having a significant impact in medical imaging, advancing almost every aspect of the field, from image acquisition and postprocessing to automated image analysis with outreach toward supporting decision making. Noninvasive cardiac imaging is one of the main and most exciting fields for AI development. The aim of this review is to describe the main applications of AI in cardiac imaging, including CT and MR imaging, and provide an overview of recent advancements and available clinical applications that can improve clinical workflow, disease detection, and prognostication in cardiac disease.

Cardiovascular magnetic resonance (CMR) and positron emission tomography (PET) imaging in the diagnosis and follow-up of patients with acute myocarditis and chronic inflammatory cardiomyopathy : A review paper with practical recommendations on behalf of the European Society of Cardiovascular Radiology (ESCR)

Advanced cardiac imaging techniques such as cardiovascular magnetic resonance (CMR) and positron emission tomography (PET) are widely used in clinical practice in patients with acute myocarditis and chronic inflammatory cardiomyopathies (I-CMP). We aimed to provide a review article with practical recommendations from the European Society of Cardiovascular Radiology (ESCR), in order to guide physicians in the use and interpretation of CMR and PET in clinical practice both for acute myocarditis and follow-up in chronic forms of I-CMP.

Deriving Explainable Metrics of Left Ventricular Flow by Reduced-Order Modeling and Classification

Background

Extracting explainable flow metrics is a bottleneck to the clinical translation of advanced cardiac flow imaging modalities. We hypothesized that reduced-order models (ROMs) of intraventricular flow are a suitable strategy for deriving simple and interpretable clinical metrics suitable for further assessments. Combined with machine learning (ML) flow-based ROMs could provide new insight to help diagnose and risk-stratify patients.

Methods

We analyzed 2D color-Doppler echocardiograms of 81 non-ischemic dilated cardiomyopathy (DCM) patients, 51 hypertrophic cardiomyopathy (HCM) patients, and 77 normal volunteers (Control). We applied proper orthogonal decomposition (POD) to build patient-specific and cohort-specific ROMs of LV flow. Each ROM aggregates a low number of components representing a spatially dependent velocity map modulated along the cardiac cycle by a time-dependent coefficient. We tested three classifiers using deliberately simple ML analyses of these ROMs with varying supervision levels. In supervised models, hyperparameter gridsearch was used to derive the ROMs that maximize classification power. The classifiers were blinded to LV chamber geometry and function. We ran vector flow mapping on the color-Doppler sequences to help visualize flow patterns and interpret the ML results.

Results

POD-based ROMs stably represented each cohort through 10-fold cross-validation. The principal POD mode captured >80% of the flow kinetic energy (KE) in all cohorts and represented the LV filling/emptying jets. Mode 2 represented the diastolic vortex and its KE contribution ranged from <1% (HCM) to 13% (DCM). Semi-unsupervised classification using patient-specific ROMs revealed that the KE ratio of these two principal modes, the vortex-to-jet (V2J) energy ratio, is a simple, interpretable metric that discriminates DCM, HCM, and Control patients. Receiver operating characteristic curves using V2J as classifier had areas under the curve of 0.81, 0.91, and 0.95 for distinguishing HCM vs. Control, DCM vs. Control, and DCM vs. HCM, respectively.

Conclusions

Modal decomposition of cardiac flow can be used to create ROMs of normal and pathological flow patterns, uncovering simple interpretable flow metrics with power to discriminate disease states, and particularly suitable for further processing using ML.

Siamese pyramidal deep learning network for strain estimation in 3D cardiac cine-MR

Strain represents the quantification of regional tissue deformation within a given area. Myocardial strain has demonstrated considerable utility as an indicator for the assessment of cardiac function. Notably, it exhibits greater sensitivity in detecting subtle myocardial abnormalities compared to conventional cardiac function indices, like left ventricle ejection fraction (LVEF). Nonetheless, the estimation of strain poses considerable challenges due to the necessity for precise tracking of myocardial motion throughout the complete cardiac cycle. This study introduces a novel deep learning-based pipeline, designed to automatically and accurately estimate myocardial strain from three-dimensional (3D) cine-MR images. Consequently, our investigation presents a comprehensive pipeline for the precise quantification of local and global myocardial strain. This pipeline incorporates a supervised Convolutional Neural Network (CNN) for accurate segmentation of the cardiac muscle and an unsupervised CNN for robust left ventricle motion tracking, enabling the estimation of strain in both artificial phantoms and real cine-MR images. Our investigation involved a comprehensive comparison of our findings with those obtained from two commonly utilized commercial software in this field. This analysis encompassed the examination of both intra- and inter-user variability. The proposed pipeline exhibited demonstrable reliability and reduced divergence levels when compared to alternative systems. Additionally, our approach is entirely independent of previous user data, effectively eliminating any potential user bias that could influence the strain analyses.

Deep Learning Synthetic Strain: Quantitative Assessment of Regional Myocardial Wall Motion at MRI

Purpose

To assess the feasibility of a newly developed algorithm, called deep learning synthetic strain (DLSS), to infer myocardial velocity from cine steady-state free precession (SSFP) images and detect wall motion abnormalities in patients with ischemic heart disease.

Materials and Methods

In this retrospective study, DLSS was developed by using a data set of 223 cardiac MRI examinations including cine SSFP images and four-dimensional flow velocity data (November 2017 to May 2021). To establish normal ranges, segmental strain was measured in 40 individuals (mean age, 41 years ± 17 [SD]; 30 men) without cardiac disease. Then, DLSS performance in the detection of wall motion abnormalities was assessed in a separate group of patients with coronary artery disease, and these findings were compared with consensus results of four independent cardiothoracic radiologists (ground truth). Algorithm performance was evaluated by using receiver operating characteristic curve analysis.

Results

Median peak segmental radial strain in individuals with normal cardiac MRI findings was 38% (IQR: 30%-48%). Among patients with ischemic heart disease (846 segments in 53 patients; mean age, 61 years ± 12; 41 men), the Cohen κ among four cardiothoracic readers for detecting wall motion abnormalities was 0.60-0.78. DLSS achieved an area under the receiver operating characteristic curve of 0.90. Using a fixed 30% threshold for abnormal peak radial strain, the algorithm achieved a sensitivity, specificity, and accuracy of 86%, 85%, and 86%, respectively.

Conclusion

The deep learning algorithm had comparable performance with subspecialty radiologists in inferring myocardial velocity from cine SSFP images and identifying myocardial wall motion abnormalities at rest in patients with ischemic heart disease.Keywords: Neural Networks, Cardiac, MR Imaging, Ischemia/Infarction Supplemental material is available for this article. © RSNA, 2023.

Artificial Intelligence as a Diagnostic Tool in Non-Invasive Imaging in the Assessment of Coronary Artery Disease

Coronary artery disease (CAD) remains a leading cause of mortality and morbidity worldwide, and it is associated with considerable economic burden. In an ageing, multimorbid population, it has become increasingly important to develop reliable, consistent, low-risk, non-invasive means of diagnosing CAD. The evolution of multiple cardiac modalities in this field has addressed this dilemma to a large extent, not only in providing information regarding anatomical disease, as is the case with coronary computed tomography angiography (CCTA), but also in contributing critical details about functional assessment, for instance, using stress cardiac magnetic resonance (S-CMR). The field of artificial intelligence (AI) is developing at an astounding pace, especially in healthcare. In healthcare, key milestones have been achieved using AI and machine learning (ML) in various clinical settings, from smartwatches detecting arrhythmias to retinal image analysis and skin cancer prediction. In recent times, we have seen an emerging interest in developing AI-based technology in the field of cardiovascular imaging, as it is felt that ML methods have potential to overcome some limitations of current risk models by applying computer algorithms to large databases with multidimensional variables, thus enabling the inclusion of complex relationships to predict outcomes. In this paper, we review the current literature on the various applications of AI in the assessment of CAD, with a focus on multimodality imaging, followed by a discussion on future perspectives and critical challenges that this field is likely to encounter as it continues to evolve in cardiology.

Myocardial Segmentation of Tagged Magnetic Resonance Images with Transfer Learning Using Generative Cine-To-Tagged Dataset Transformation

The use of deep learning (DL) segmentation in cardiac MRI has the potential to streamline the radiology workflow, particularly for the measurement of myocardial strain. Recent efforts in DL motion tracking models have drastically reduced the time needed to measure the heart's displacement field and the subsequent myocardial strain estimation. However, the selection of initial myocardial reference points is not automated and still requires manual input from domain experts. Segmentation of the myocardium is a key step for initializing reference points. While high-performing myocardial segmentation models exist for cine images, this is not the case for tagged images. In this work, we developed and compared two novel DL models (nnU-net and Segmentation ResNet VAE) for the segmentation of myocardium from tagged CMR images. We implemented two methods to transform cardiac cine images into tagged images, allowing us to leverage large public annotated cine datasets. The cine-to-tagged methods included (i) a novel physics-driven transformation model, and (ii) a generative adversarial network (GAN) style transfer model. We show that pretrained models perform better (+2.8 Dice coefficient percentage points) and converge faster (6×) than models trained from scratch. The best-performing method relies on a pretraining with an unpaired, unlabeled, and structure-preserving generative model trained to transform cine images into their tagged-appearing equivalents. Our state-of-the-art myocardium segmentation network reached a Dice coefficient of 0.828 and 95th percentile Hausdorff distance of 4.745 mm on a held-out test set. This performance is comparable to existing state-of-the-art segmentation networks for cine images.

Optimized automated cardiac MR scar quantification with GAN-based data augmentation

BACKGROUND

The clinical utility of late gadolinium enhancement (LGE) cardiac MRI is limited by the lack of standardization, and time-consuming postprocessing. In this work, we tested the hypothesis that a cascaded deep learning pipeline trained with augmentation by synthetically generated data would improve model accuracy and robustness for automated scar quantification.

METHODS

A cascaded pipeline consisting of three consecutive neural networks is proposed, starting with a bounding box regression network to identify a region of interest around the left ventricular (LV) myocardium. Two further nnU-Net models are then used to segment the myocardium and, if present, scar. The models were trained on the data from the EMIDEC challenge, supplemented with an extensive synthetic dataset generated with a conditional GAN.

RESULTS

The cascaded pipeline significantly outperformed a single nnU-Net directly segmenting both the myocardium (mean Dice similarity coefficient (DSC) (standard deviation (SD)): 0.84 (0.09) vs 0.63 (0.20), p < 0.01) and scar (DSC: 0.72 (0.34) vs 0.46 (0.39), p < 0.01) on a per-slice level. The inclusion of the synthetic data as data augmentation during training improved the scar segmentation DSC by 0.06 (p < 0.01). The mean DSC per-subject on the challenge test set, for the cascaded pipeline augmented by synthetic generated data, was 0.86 (0.03) and 0.67 (0.29) for myocardium and scar, respectively.

CONCLUSION

A cascaded deep learning-based pipeline trained with augmentation by synthetically generated data leads to myocardium and scar segmentations that are similar to the manual operator, and outperforms direct segmentation without the synthetic images.

CardiSort: a convolutional neural network for cross vendor automated sorting of cardiac MR images

OBJECTIVES

To develop an image-based automatic deep learning method to classify cardiac MR images by sequence type and imaging plane for improved clinical post-processing efficiency.

METHODS

Multivendor cardiac MRI studies were retrospectively collected from 4 centres and 3 vendors. A two-head convolutional neural network ('CardiSort') was trained to classify 35 sequences by imaging sequence (n = 17) and plane (n = 10). Single vendor training (SVT) on single-centre images (n = 234 patients) and multivendor training (MVT) with multicentre images (n = 434 patients, 3 centres) were performed. Model accuracy and F1 scores on a hold-out test set were calculated, with ground truth labels by an expert radiologist. External validation of MVT (MVTexternal) was performed on data from 3 previously unseen magnet systems from 2 vendors (n = 80 patients).

RESULTS

Model sequence/plane/overall accuracy and F1-scores were 85.2%/93.2%/81.8% and 0.82 for SVT and 96.1%/97.9%/94.3% and 0.94 MVT on the hold-out test set. MVTexternal yielded sequence/plane/combined accuracy and F1-scores of 92.7%/93.0%/86.6% and 0.86. There was high accuracy for common sequences and conventional cardiac planes. Poor accuracy was observed for underrepresented classes and sequences where there was greater variability in acquisition parameters across centres, such as perfusion imaging.

CONCLUSIONS

A deep learning network was developed on multivendor data to classify MRI studies into component sequences and planes, with external validation. With refinement, it has potential to improve workflow by enabling automated sequence selection, an important first step in completely automated post-processing pipelines.

KEY POINTS

• Deep learning can be applied for consistent and efficient classification of cardiac MR image types. • A multicentre, multivendor study using a deep learning algorithm (CardiSort) showed high classification accuracy on a hold-out test set with good generalisation to images from previously unseen magnet systems. • CardiSort has potential to improve clinical workflows, as a vital first step in developing fully automated post-processing pipelines.

MulViMotion: Shape-Aware 3D Myocardial Motion Tracking From Multi-View Cardiac MRI

Recovering the 3D motion of the heart from cine cardiac magnetic resonance (CMR) imaging enables the assessment of regional myocardial function and is important for understanding and analyzing cardiovascular disease. However, 3D cardiac motion estimation is challenging because the acquired cine CMR images are usually 2D slices which limit the accurate estimation of through-plane motion. To address this problem, we propose a novel multi-view motion estimation network (MulViMotion), which integrates 2D cine CMR images acquired in short-axis and long-axis planes to learn a consistent 3D motion field of the heart. In the proposed method, a hybrid 2D/3D network is built to generate dense 3D motion fields by learning fused representations from multi-view images. To ensure that the motion estimation is consistent in 3D, a shape regularization module is introduced during training, where shape information from multi-view images is exploited to provide weak supervision to 3D motion estimation. We extensively evaluate the proposed method on 2D cine CMR images from 580 subjects of the UK Biobank study for 3D motion tracking of the left ventricular myocardium. Experimental results show that the proposed method quantitatively and qualitatively outperforms competing methods.

Novel Approaches to Imaging the Pulmonary Vasculature and Right Heart

There is an increased appreciation for the importance of the right heart and pulmonary circulation in several disease states across the spectrum of pulmonary hypertension and left heart failure. However, assessment of the structure and function of the right heart and pulmonary circulation can be challenging, due to the complex geometry of the right ventricle, comorbid pulmonary airways and parenchymal disease, and the overlap of hemodynamic abnormalities with left heart failure. Several new and evolving imaging modalities interrogate the right heart and pulmonary circulation with greater diagnostic precision. Echocardiographic approaches such as speckle-tracking and 3-dimensional imaging provide detailed assessments of regional systolic and diastolic function and volumetric assessments. Magnetic resonance approaches can provide high-resolution views of cardiac structure/function, tissue characterization, and perfusion through the pulmonary vasculature. Molecular imaging with positron emission tomography allows an assessment of specific pathobiologically relevant targets in the right heart and pulmonary circulation. Machine learning analysis of high-resolution computed tomographic lung scans permits quantitative morphometry of the lung circulation without intravenous contrast. Inhaled magnetic resonance imaging probes, such as hyperpolarized 129Xe magnetic resonance imaging, report on pulmonary gas exchange and pulmonary capillary hemodynamics. These approaches provide important information on right ventricular structure and function along with perfusion through the pulmonary circulation. At this time, the majority of these developing technologies have yet to be clinically validated, with few studies demonstrating the utility of these imaging biomarkers for diagnosis or monitoring disease. These technologies hold promise for earlier diagnosis and noninvasive monitoring of right heart failure and pulmonary hypertension that will aid in preclinical studies, enhance patient selection and provide surrogate end points in clinical trials, and ultimately improve bedside care.

Artificial intelligence with deep learning in nuclear medicine and radiology

The use of deep learning in medical imaging has increased rapidly over the past few years, finding applications throughout the entire radiology pipeline, from improved scanner performance to automatic disease detection and diagnosis. These advancements have resulted in a wide variety of deep learning approaches being developed, solving unique challenges for various imaging modalities. This paper provides a review on these developments from a technical point of view, categorizing the different methodologies and summarizing their implementation. We provide an introduction to the design of neural networks and their training procedure, after which we take an extended look at their uses in medical imaging. We cover the different sections of the radiology pipeline, highlighting some influential works and discussing the merits and limitations of deep learning approaches compared to other traditional methods. As such, this review is intended to provide a broad yet concise overview for the interested reader, facilitating adoption and interdisciplinary research of deep learning in the field of medical imaging.

Direct pixel to pixel principal strain mapping from tagging MRI using end to end deep convolutional neural network (DeepStrain)

Regional soft tissue mechanical strain offers crucial insights into tissue's mechanical function and vital indicators for different related disorders. Tagging magnetic resonance imaging (tMRI) has been the standard method for assessing the mechanical characteristics of organs such as the heart, the liver, and the brain. However, constructing accurate artifact-free pixelwise strain maps at the native resolution of the tagged images has for decades been a challenging unsolved task. In this work, we developed an end-to-end deep-learning framework for pixel-to-pixel mapping of the two-dimensional Eulerian principal strains [Formula: see text] and [Formula: see text] directly from 1-1 spatial modulation of magnetization (SPAMM) tMRI at native image resolution using convolutional neural network (CNN). Four different deep learning conditional generative adversarial network (cGAN) approaches were examined. Validations were performed using Monte Carlo computational model simulations, and in-vivo datasets, and compared to the harmonic phase (HARP) method, a conventional and validated method for tMRI analysis, with six different filter settings. Principal strain maps of Monte Carlo tMRI simulations with various anatomical, functional, and imaging parameters demonstrate artifact-free solid agreements with the corresponding ground-truth maps. Correlations with the ground-truth strain maps were R = 0.90 and 0.92 for the best-proposed cGAN approach compared to R = 0.12 and 0.73 for the best HARP method for [Formula: see text] and [Formula: see text], respectively. The proposed cGAN approach's error was substantially lower than the error in the best HARP method at all strain ranges. In-vivo results are presented for both healthy subjects and patients with cardiac conditions (Pulmonary Hypertension). Strain maps, obtained directly from their corresponding tagged MR images, depict for the first time anatomical, functional, and temporal details at pixelwise native high resolution with unprecedented clarity. This work demonstrates the feasibility of using the deep learning cGAN for direct myocardial and liver Eulerian strain mapping from tMRI at native image resolution with minimal artifacts.

Using synthetic data generation to train a cardiac motion tag tracking neural network

A CNN based method for cardiac MRI tag tracking was developed and validated. A synthetic data simulator was created to generate large amounts of training data using natural images, a Bloch equation simulation, a broad range of tissue properties, and programmed ground-truth motion. The method was validated using both an analytical deforming cardiac phantom and in vivo data with manually tracked reference motion paths. In the analytical phantom, error was investigated relative to SNR, and accurate results were seen for SNR>10 (displacement error <0.3 mm). Excellent agreement was seen in vivo for tag locations (mean displacement difference = -0.02 pixels, 95% CI [-0.73, 0.69]) and calculated cardiac circumferential strain (mean difference = 0.006, 95% CI [-0.012, 0.024]). Automated tag tracking with a CNN trained on synthetic data is both accurate and precise.

DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics

Myocardial strain analysis from cinematic magnetic resonance imaging (cine-MRI) data provides a more thorough characterization of cardiac mechanics than volumetric parameters such as left-ventricular ejection fraction, but sources of variation including segmentation and motion estimation have limited its wider clinical use. We designed and validated a fast, fully-automatic deep learning (DL) workflow to generate both volumetric parameters and strain measures from cine-MRI data consisting of segmentation and motion estimation convolutional neural networks. The final motion network design, loss function, and associated hyperparameters are the result of a thorough ad hoc implementation that we carefully planned specific for strain quantification, tested, and compared to other potential alternatives. The optimal configuration was trained using healthy and cardiovascular disease (CVD) subjects (n = 150). DL-based volumetric parameters were correlated (>0.98) and without significant bias relative to parameters derived from manual segmentations in 50 healthy and CVD test subjects. Compared to landmarks manually-tracked on tagging-MRI images from 15 healthy subjects, landmark deformation using DL-based motion estimates from paired cine-MRI data resulted in an end-point-error of 2.9 ± 1.5 mm. Measures of end-systolic global strain from these cine-MRI data showed no significant biases relative to a tagging-MRI reference method. On 10 healthy subjects, intraclass correlation coefficient for intra-scanner repeatability was good to excellent (>0.75) for all global measures and most polar map segments. In conclusion, we developed and evaluated the first end-to-end learning-based workflow for automated strain analysis from cine-MRI data to quantitatively characterize cardiac mechanics of healthy and CVD subjects.

Arbitrary Point Tracking with Machine Learning to Measure Cardiac Strains in Tagged MRI

Cardiac tagged MR images allow for deformation fields to be measured in the heart by tracking the motion of tag lines throughout the cardiac cycle. Machine learning (ML) algorithms enable accurate and robust tracking of tag lines. Herein, the use of a massive synthetic physics-driven training dataset with known ground truth was used to train an ML network to enable tracking any number of points at arbitrary positions rather than anchored to the tag lines themselves. The tag tracking and strain calculation methods were investigated in a computational deforming cardiac phantom with known (ground truth) strain values. This enabled both tag tracking and strain accuracy to be characterized for a range of image acquisition and tag tracking parameters. The methods were also tested on in vivo volunteer data. Median tracking error was <0.26mm in the computational phantom, and strain measurements were improved in vivo when using the arbitrary point tracking for a standard clinical protocol.

A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises

Since its renaissance, deep learning has been widely used in various medical imaging tasks and has achieved remarkable success in many medical imaging applications, thereby propelling us into the so-called artificial intelligence (AI) era. It is known that the success of AI is mostly attributed to the availability of big data with annotations for a single task and the advances in high performance computing. However, medical imaging presents unique challenges that confront deep learning approaches. In this survey paper, we first present traits of medical imaging, highlight both clinical needs and technical challenges in medical imaging, and describe how emerging trends in deep learning are addressing these issues. We cover the topics of network architecture, sparse and noisy labels, federating learning, interpretability, uncertainty quantification, etc. Then, we present several case studies that are commonly found in clinical practice, including digital pathology and chest, brain, cardiovascular, and abdominal imaging. Rather than presenting an exhaustive literature survey, we instead describe some prominent research highlights related to these case study applications. We conclude with a discussion and presentation of promising future directions.

Fully-automated global and segmental strain analysis of DENSE cardiovascular magnetic resonance using deep learning for segmentation and phase unwrapping

BACKGROUND

Cardiovascular magnetic resonance (CMR) cine displacement encoding with stimulated echoes (DENSE) measures heart motion by encoding myocardial displacement into the signal phase, facilitating high accuracy and reproducibility of global and segmental myocardial strain and providing benefits in clinical performance. While conventional methods for strain analysis of DENSE images are faster than those for myocardial tagging, they still require manual user assistance. The present study developed and evaluated deep learning methods for fully-automatic DENSE strain analysis.

METHODS

Convolutional neural networks (CNNs) were developed and trained to (a) identify the left-ventricular (LV) epicardial and endocardial borders, (b) identify the anterior right-ventricular (RV)-LV insertion point, and (c) perform phase unwrapping. Subsequent conventional automatic steps were employed to compute strain. The networks were trained using 12,415 short-axis DENSE images from 45 healthy subjects and 19 heart disease patients and were tested using 10,510 images from 25 healthy subjects and 19 patients. Each individual CNN was evaluated, and the end-to-end fully-automatic deep learning pipeline was compared to conventional user-assisted DENSE analysis using linear correlation and Bland Altman analysis of circumferential strain.

RESULTS

LV myocardial segmentation U-Nets achieved a DICE similarity coefficient of 0.87 ± 0.04, a Hausdorff distance of 2.7 ± 1.0 pixels, and a mean surface distance of 0.41 ± 0.29 pixels in comparison with manual LV myocardial segmentation by an expert. The anterior RV-LV insertion point was detected within 1.38 ± 0.9 pixels compared to manually annotated data. The phase-unwrapping U-Net had similar or lower mean squared error vs. ground-truth data compared to the conventional path-following method for images with typical signal-to-noise ratio (SNR) or low SNR (p < 0.05), respectively. Bland-Altman analyses showed biases of 0.00 ± 0.03 and limits of agreement of - 0.04 to 0.05 or better for deep learning-based fully-automatic global and segmental end-systolic circumferential strain vs. conventional user-assisted methods.

CONCLUSIONS

Deep learning enables fully-automatic global and segmental circumferential strain analysis of DENSE CMR providing excellent agreement with conventional user-assisted methods. Deep learning-based automatic strain analysis may facilitate greater clinical use of DENSE for the quantification of global and segmental strain in patients with cardiac disease.

Cardiac Magnetic Resonance in Pulmonary Hypertension-an Update

PURPOSE OF REVIEW

This article reviews advances over the past 3 years in cardiac magnetic resonance (CMR) imaging in pulmonary hypertension (PH). We aim to bring the reader up-to-date with CMR applications in diagnosis, prognosis, 4D flow, strain analysis, T1 mapping, machine learning and ongoing research.

RECENT FINDINGS

CMR volumetric and functional metrics are now established as valuable prognostic markers in PH. This imaging modality is increasingly used to assess treatment response and improves risk stratification when incorporated into PH risk scores. Emerging techniques such as myocardial T1 mapping may play a role in the follow-up of selected patients. Myocardial strain may be used as an early marker for right and left ventricular dysfunction and a predictor for mortality. Machine learning has offered a glimpse into future possibilities. Ongoing research of new PH therapies is increasingly using CMR as a clinical endpoint.

SUMMARY

The last 3 years have seen several large studies establishing CMR as a valuable diagnostic and prognostic tool in patients with PH, with CMR increasingly considered as an endpoint in clinical trials of PH therapies. Machine learning approaches to improve automation and accuracy of CMR metrics and identify imaging features of PH is an area of active research interest with promising clinical utility.