Artificial intelligence-based full aortic CT angiography imaging with ultra-low-dose contrast medium: a preliminary study.

OBJECTIVES: To further reduce the contrast medium (CM) dose of full aortic CT angiography (ACTA) imaging using the augmented cycle-consistent adversarial framework (Au-CycleGAN) algorithm. METHODS: We prospectively enrolled 150 consecutive patients with suspected aortic disease. All received ACTA scans of ultra-low-dose CM (ULDCM) protocol and low-dose CM (LDCM) protocol. These data were randomly assigned to the training datasets (n = 100) and the validation datasets (n = 50). The ULDCM images were reconstructed by the Au-CycleGAN algorithm. Then, the AI-based ULDCM images were compared with LDCM images in terms of image quality and diagnostic accuracy. RESULTS: The mean image quality score of each location in the AI-based ULDCM group was higher than that in the ULDCM group but a little lower than that in the LDCM group (all p < 0.05). All AI-based ULDCM images met the diagnostic requirements (score ≥ 3). Except for the image noise, the AI-based ULDCM images had higher attenuation value than the ULDCM and LDCM images as well as higher SNR and CNR in all locations of the aorta analyzed (all p < 0.05). Similar results were also seen in obese patients (BMI > 25, all p < 0.05). Using the findings of LDCM images as the reference, the AI-based ULDCM images showed good diagnostic parameters and no significant differences in any of the analyzed aortic disease diagnoses (all K-values > 0.80, p < 0.05). CONCLUSIONS: The required dose of CM for full ACTA imaging can be reduced to one-third of the CM dose of the LDCM protocol while maintaining image quality and diagnostic accuracy using the Au-CycleGAN algorithm. KEY POINTS: • The required dose of contrast medium (CM) for full ACTA imaging can be reduced to one-third of the CM dose of the low-dose contrast medium (LDCM) protocol using the Au-CycleGAN algorithm. • Except for the image noise, the AI-based ultra-low-dose contrast medium (ULDCM) images had better quantitative image quality parameters than the ULDCM and LDCM images. • No significant diagnostic differences were noted between the AI-based ULDCM and LDCM images regarding all the analyzed aortic disease diagnoses.

HDL: Hybrid Deep Learning for the Synthesis of Myocardial Velocity Maps in Digital Twins for Cardiac Analysis.

Synthetic digital twins based on medical data accelerate the acquisition, labelling and decision making procedure in digital healthcare. A core part of digital healthcare twins is model-based data synthesis, which permits the generation of realistic medical signals without requiring to cope with the modelling complexity of anatomical and biochemical phenomena producing them in reality. Unfortunately, algorithms for cardiac data synthesis have been so far scarcely studied in the literature. An important imaging modality in the cardiac examination is three-directional CINE multi-slice myocardial velocity mapping (3Dir MVM), which provides a quantitative assessment of cardiac motion in three orthogonal directions of the left ventricle. The long acquisition time and complex acquisition produce make it more urgent to produce synthetic digital twins of this imaging modality. In this study, we propose a hybrid deep learning (HDL) network, especially for synthetic 3Dir MVM data. Our algorithm is featured by a hybrid UNet and a Generative Adversarial Network with a foreground-background generation scheme. The experimental results show that from temporally down-sampled magnitude CINE images (six times), our proposed algorithm can still successfully synthesise high temporal resolution 3Dir MVM CMR data (PSNR=42.32) with precise left ventricle segmentation (DICE=0.92). These performance scores indicate that our proposed HDL algorithm can be implemented in real-world digital twins for myocardial velocity mapping data simulation. To the best of our knowledge, this work is the first one investigating digital twins of the 3Dir MVM CMR, which has shown great potential for improving the efficiency of clinical studies via synthesised cardiac data.

Accelerating Cardiac Diffusion Tensor Imaging With a U-Net Based Model: Toward Single Breath-Hold.

BACKGROUND: In vivo cardiac diffusion tensor imaging (cDTI) characterizes myocardial microstructure. Despite its potential clinical impact, considerable technical challenges exist due to the inherent low signal-to-noise ratio. PURPOSE: To reduce scan time toward one breath-hold by reconstructing diffusion tensors for in vivo cDTI with a fitting-free deep learning approach. STUDY TYPE: Retrospective. POPULATION: A total of 197 healthy controls, 547 cardiac patients. FIELD STRENGTH/SEQUENCE: A 3 T, diffusion-weighted stimulated echo acquisition mode single-shot echo-planar imaging sequence. ASSESSMENT: A U-Net was trained to reconstruct the diffusion tensor elements of the reference results from reduced datasets that could be acquired in 5, 3 or 1 breath-hold(s) (BH) per slice. Fractional anisotropy (FA), mean diffusivity (MD), helix angle (HA), and sheetlet angle (E2A) were calculated and compared to the same measures when using a conventional linear-least-square (LLS) tensor fit with the same reduced datasets. A conventional LLS tensor fit with all available data (12 ± 2.0 [mean ± sd] breath-holds) was used as the reference baseline. STATISTICAL TESTS: Wilcoxon signed rank/rank sum and Kruskal-Wallis tests. Statistical significance threshold was set at P = 0.05. Intersubject measures are quoted as median [interquartile range]. RESULTS: For global mean or median results, both the LLS and U-Net methods with reduced datasets present a bias for some of the results. For both LLS and U-Net, there is a small but significant difference from the reference results except for LLS: MD 5BH (P = 0.38) and MD 3BH (P = 0.09). When considering direct pixel-wise errors the U-Net model outperformed significantly the LLS tensor fit for reduced datasets that can be acquired in three or just one breath-hold for all parameters. DATA CONCLUSION: Diffusion tensor prediction with a trained U-Net is a promising approach to minimize the number of breath-holds needed in clinical cDTI studies. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 1.

Development of a cardiovascular magnetic resonance-compatible large animal isolated heart model for direct comparison of beating and arrested hearts.

Cardiac motion results in image artefacts and quantification errors in many cardiovascular magnetic resonance (CMR) techniques, including microstructural assessment using diffusion tensor cardiovascular magnetic resonance (DT-CMR). Here, we develop a CMR-compatible isolated perfused porcine heart model that allows comparison of data obtained in beating and arrested states. Ten porcine hearts (8/10 for protocol optimisation) were harvested using a donor heart retrieval protocol and transported to the remote CMR facility. Langendorff perfusion in a 3D-printed chamber and perfusion circuit re-established contraction. Hearts were imaged using cine, parametric mapping and STEAM DT-CMR at cardiac phases with the minimum and maximum wall thickness. High potassium and lithium perfusates were then used to arrest the heart in a slack and contracted state, respectively. Imaging was repeated in both arrested states. After imaging, tissue was removed for subsequent histology in a location matched to the DT-CMR data using fiducial markers. Regular sustained contraction was successfully established in six out of 10 hearts, including the final five hearts. Imaging was performed in four hearts and one underwent the full protocol, including colocalised histology. The image quality was good and there was good agreement between DT-CMR data in equivalent beating and arrested states. Despite the use of autologous blood and dextran within the perfusate, T2 mapping results, DT-CMR measures and an increase in mass were consistent with development of myocardial oedema, resulting in failure to achieve a true diastolic-like state. A contiguous stack of 313 5-µm histological sections at and a 100-µm thick section showing cell morphology on 3D fluorescent confocal microscopy colocalised to DT-CMR data were obtained. A CMR-compatible isolated perfused beating heart setup for large animal hearts allows direct comparisons of beating and arrested heart data with subsequent colocalised histology, without the need for onsite preclinical facilities.

Reliability of pediatric ventricular function analysis by short-axis "single-cycle-stack-advance" single-shot compressed-sensing cines in minimal breath-hold time.

OBJECTIVES: Cardiovascular magnetic resonance (CMR) cine imaging by compressed sensing (CS) is promising for patients unable to tolerate long breath-holding. However, the need for a steady-state free-precession (SSFP) preparation cardiac cycle for each slice extends the breath-hold duration (e.g. for 10 slices, 20 cardiac cycles) to an impractical length. We investigated a method reducing breath-hold duration by half and assessed its reliability for biventricular volume analysis in a pediatric population. METHODS: Fifty-five consecutive pediatric patients (median age 12 years, range 7-17) referred for assessment of congenital heart disease or cardiomyopathy were included. Conventional multiple breath-hold SSFP short-axis (SAX) stack cines served as the reference. Real-time CS SSFP cines were applied without the steady-state preparation cycle preceding each SAX cine slice, accepting the limitation of omitting late diastole. The total acquisition time was 1 RR interval/slice. Volumetric analysis was performed for conventional and "single-cycle-stack-advance" (SCSA) cine stacks. RESULTS: Bland-Altman analyses [bias (limits of agreement)] showed good agreement in left ventricular (LV) end-diastolic volume (EDV) [3.6 mL (- 5.8, 12.9)], LV end-systolic volume (ESV) [1.3 mL (- 6.0, 8.6)], LV ejection fraction (EF) [0.1% (- 4.9, 5.1)], right ventricular (RV) EDV [3.5 mL (- 3.34, 10.0)], RV ESV [- 0.23 mL (- 7.4, 6.9)], and RV EF [1.70%, (- 3.7, 7.1)] with a trend toward underestimating LV and RV EDVs with the SCSA method. Image quality was comparable for both methods (p = 0.37). CONCLUSIONS: LV and RV volumetric parameters agreed well between the SCSA and the conventional sequences. The SCSA method halves the breath-hold duration of the commercially available CS sequence and is a reliable alternative for volumetric analysis in a pediatric population. KEY POINTS: • Compressed sensing is a promising accelerated cardiovascular magnetic resonance imaging technique. • We omitted the steady-state preparation cardiac cycle preceding each cine slice in compressed sensing and achieved an acquisition speed of 1 RR interval/slice. • This modification called "single-cycle-stack-advance" enabled the acquisition of an entire short-axis cine stack in a single short breath hold. • When tested in a pediatric patient group, the left and right ventricular volumetric parameters agreed well between the "single-cycle-stack-advance" and the conventional sequences.

JAS-GAN: Generative Adversarial Network Based Joint Atrium and Scar Segmentations on Unbalanced Atrial Targets.

Automated and accurate segmentations of left atrium (LA) and atrial scars from late gadolinium-enhanced cardiac magnetic resonance (LGE CMR) images are in high demand for quantifying atrial scars. The previous quantification of atrial scars relies on a two-phase segmentation for LA and atrial scars due to their large volume difference (unbalanced atrial targets). In this paper, we propose an inter-cascade generative adversarial network, namely JAS-GAN, to segment the unbalanced atrial targets from LGE CMR images automatically and accurately in an end-to-end way. Firstly, JAS-GAN investigates an adaptive attention cascade to automatically correlate the segmentation tasks of the unbalanced atrial targets. The adaptive attention cascade mainly models the inclusion relationship of the two unbalanced atrial targets, where the estimated LA acts as the attention map to adaptively focus on the small atrial scars roughly. Then, an adversarial regularization is applied to the segmentation tasks of the unbalanced atrial targets for making a consistent optimization. It mainly forces the estimated joint distribution of LA and atrial scars to match the real ones. We evaluated the performance of our JAS-GAN on a 3D LGE CMR dataset with 192 scans. Compared with the state-of-the-art methods, our proposed approach yielded better segmentation performance (Average Dice Similarity Coefficient (DSC) values of 0.946 and 0.821 for LA and atrial scars, respectively), which indicated the effectiveness of our proposed approach for segmenting unbalanced atrial targets.

Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data.

Semi-supervised learning provides great significance in left atrium (LA) segmentation model learning with insufficient labelled data. Generalising semi-supervised learning to cross-domain data is of high importance to further improve model robustness. However, the widely existing distribution difference and sample mismatch between different data domains hinder the generalisation of semi-supervised learning. In this study, we alleviate these problems by proposing an Adaptive Hierarchical Dual Consistency (AHDC) for the semi-supervised LA segmentation on cross-domain data. The AHDC mainly consists of a Bidirectional Adversarial Inference module (BAI) and a Hierarchical Dual Consistency learning module (HDC). The BAI overcomes the difference of distributions and the sample mismatch between two different domains. It mainly learns two mapping networks adversarially to obtain two matched domains through mutual adaptation. The HDC investigates a hierarchical dual learning paradigm for cross-domain semi-supervised segmentation based on the obtained matched domains. It mainly builds two dual-modelling networks for mining the complementary information in both intra-domain and inter-domain. For the intra-domain learning, a consistency constraint is applied to the dual-modelling targets to exploit the complementary modelling information. For the inter-domain learning, a consistency constraint is applied to the LAs modelled by two dual-modelling networks to exploit the complementary knowledge among different data domains. We demonstrated the performance of our proposed AHDC on four 3D late gadolinium enhancement cardiac MR (LGE-CMR) datasets from different centres and a 3D CT dataset. Compared to other state-of-the-art methods, our proposed AHDC achieved higher segmentation accuracy, which indicated its capability in the cross-domain semi-supervised LA segmentation.

Association Between Left Ventricular Global Function Index and Outcomes in Patients With Dilated Cardiomyopathy.

Purpose: Left ventricular global function index (LVGFI) assessed using cardiac magnetic resonance (CMR) seems promising in the prediction of clinical outcomes. However, the role of the LVGFI is uncertain in patients with heart failure (HF) with dilated cardiomyopathy (DCM). To describe the association of LVGFI and outcomes in patients with DCM, it was hypothesized that LVGFI is associated with decreased major adverse cardiac events (MACEs) in patients with DCM. Materials and Methods: This prospective cohort study was conducted from January 2015 to April 2020 in consecutive patients with DCM who underwent CMR. The association between outcomes and LVGFI was assessed using a multivariable model adjusted with confounders. LVGFI was the primary exposure variable. The long-term outcome was a composite endpoint, including death or heart transplantation. Results: A total of 334 patients (mean age: 55 years) were included in this study. The average of CMR-LVGFI was 16.53%. Over a median follow-up of 565 days, 43 patients reached the composite endpoint. Kaplan-Meier analysis revealed that patients with LVGFI lower than the cutoff values (15.73%) had a higher estimated cumulative incidence of the endpoint compared to those with LVGFI higher than the cutoff values (P = 0.0021). The hazard of MACEs decreased by 38% for each 1 SD increase in LVGFI (hazard ratio 0.62[95%CI 0.43-0.91]) and after adjustment by 46% (HR 0.54 [95%CI 0.32-0.89]). The association was consistent across subgroup analyses. Conclusion: In this study, an increase in CMR-LVGFI was associated with decreasing the long-term risk of MACEs with DCM after adjustment for traditional confounders.

Recent Advances in Fibrosis and Scar Segmentation From Cardiac MRI: A State-of-the-Art Review and Future Perspectives.

Segmentation of cardiac fibrosis and scars is essential for clinical diagnosis and can provide invaluable guidance for the treatment of cardiac diseases. Late Gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) has been successful in guiding the clinical diagnosis and treatment reliably. For LGE CMR, many methods have demonstrated success in accurately segmenting scarring regions. Co-registration with other non-contrast-agent (non-CA) modalities [e.g., balanced steady-state free precession (bSSFP) cine magnetic resonance imaging (MRI)] can further enhance the efficacy of automated segmentation of cardiac anatomies. Many conventional methods have been proposed to provide automated or semi-automated segmentation of scars. With the development of deep learning in recent years, we can also see more advanced methods that are more efficient in providing more accurate segmentations. This paper conducts a state-of-the-art review of conventional and current state-of-the-art approaches utilizing different modalities for accurate cardiac fibrosis and scar segmentation.

Minimisation of slab-selective radiofrequency excitation pulse durations constrained by an acceptable aliasing coefficient.

A technical note is presented on the slab-direction aliasing of 3D imaging, introducing a simple methodology for determining the minimised duration of low flip-angle sinc radiofrequency (RF) excitation pulses, with respect to a required slab profile accuracy. The various interdependent factors affected in modifying an RF pulse duration are considered and analysed in the context of a new metric for quantifying the levels of permitted slab-aliasing. A general framework is presented for the selection of standard sinc RF excitation pulses with system-minimised durations, as well as their analysis and validation, and a demonstration of this methodology is performed for an example requirement and scanner. This methodology enables implementation of standard (vendor-generated) RF pulses with minimised duration for a required application, with high confidence in their operational reliability. Parts of such a methodology may also in theory be extended to more advanced RF pulse designs.

Fast and Automated Segmentation for the Three-Directional Multi-Slice Cine Myocardial Velocity Mapping.

Three-directional cine multi-slice left ventricular myocardial velocity mapping (3Dir MVM) is a cardiac magnetic resonance (CMR) technique that allows the assessment of cardiac motion in three orthogonal directions. Accurate and reproducible delineation of the myocardium is crucial for accurate analysis of peak systolic and diastolic myocardial velocities. In addition to the conventionally available magnitude CMR data, 3Dir MVM also provides three orthogonal phase velocity mapping datasets, which are used to generate velocity maps. These velocity maps may also be used to facilitate and improve the myocardial delineation. Based on the success of deep learning in medical image processing, we propose a novel fast and automated framework that improves the standard U-Net-based methods on these CMR multi-channel data (magnitude and phase velocity mapping) by cross-channel fusion with an attention module and the shape information-based post-processing to achieve accurate delineation of both epicardial and endocardial contours. To evaluate the results, we employ the widely used Dice Scores and the quantification of myocardial longitudinal peak velocities. Our proposed network trained with multi-channel data shows superior performance compared to standard U-Net-based networks trained on single-channel data. The obtained results are promising and provide compelling evidence for the design and application of our multi-channel image analysis of the 3Dir MVM CMR data.

Cardiovascular magnetic resonance predictors of heart failure in hypertrophic cardiomyopathy: the role of myocardial replacement fibrosis and the microcirculation.

INTRODUCTION: Heart failure (HF) in hypertrophic cardiomyopathy (HCM) is associated with high morbidity and mortality. Predictors of HF, in particular the role of myocardial fibrosis and microvascular ischemia remain unclear. We assessed the predictive value of cardiovascular magnetic resonance (CMR) for development of HF in HCM in an observational cohort study. METHODS: Serial patients with HCM underwent CMR, including adenosine first-pass perfusion, left atrial (LA) and left ventricular (LV) volumes indexed to body surface area (i) and late gadolinium enhancement (%LGE- as a % of total myocardial mass). We used a composite endpoint of HF death, cardiac transplantation, and progression to NYHA class III/IV. RESULTS: A total of 543 patients with HCM underwent CMR, of whom 94 met the composite endpoint at baseline. The remaining 449 patients were followed for a median of 5.6 years. Thirty nine patients (8.7%) reached the composite endpoint of HF death (n = 7), cardiac transplantation (n = 2) and progression to NYHA class III/IV (n = 20). The annual incidence of HF was 2.0 per 100 person-years, 95% CI (1.6-2.6). Age, previous non-sustained ventricular tachycardia, LV end-systolic volume indexed to body surface area (LVESVI), LA volume index ; LV ejection fraction, %LGE and presence of mitral regurgitation were significant univariable predictors of HF, with LVESVI (Hazard ratio (HR) 1.44, 95% confidence interval (95% CI) 1.16-1.78, p = 0.001), %LGE per 10% (HR 1.44, 95%CI 1.14-1.82, p = 0.002) age (HR 1.37, 95% CI 1.06-1.77, p = 0.02) and mitral regurgitation (HR 2.6, p = 0.02) remaining independently predictive on multivariable analysis. The presence or extent of inducible perfusion defect assessed using a visual score did not predict outcome (p = 0.16, p = 0.27 respectively). DISCUSSION: The annual incidence of HF in a contemporary ambulatory HCM population undergoing CMR is low. Myocardial fibrosis and LVESVI are strongly predictive of future HF, however CMR visual assessment of myocardial perfusion was not.

Association between right ventricular strain and outcomes in patients with dilated cardiomyopathy.

OBJECTIVE: To explore the association between three-dimensional (3D) cardiac magnetic resonance (CMR) feature tracking (FT) right ventricular peak global longitudinal strain (RVpGLS) and major adverse cardiovascular events (MACEs) in patients with stage C or D heart failure (HF) with non-ischaemic dilated cardiomyopathy (NIDCM) but without atrial fibrillation (AF). METHODS: Patients with dilated cardiomyopathy were enrolled in this prospective cohort study. Comprehensive clinical and biochemical analysis and CMR imaging were performed. All patients were followed up for MACEs. RESULTS: A total of 192 patients (age 53±14 years) were eligible for this study. A combination of cardiovascular death and cardiac transplantation occurred in 18 subjects during the median follow-up of 567 (311, 920) days. Brain natriuretic peptide, creatinine, left ventricular (LV) end-diastolic volume, LV end-systolic volume, right ventricular (RV) end-diastolic volume and RVpGLS from CMR were associated with the outcomes. The multivariate Cox regression model adjusting for traditional risk factors and CMR variables detected a significant association between RVpGLS and MACEs in patients with stage C or D HF with NIDCM without AF. Kaplan-Meier analysis based on RVpGLS cut-off value revealed that patients with RVpGLS <-8.5% showed more favourable clinical outcomes than those with RVpGLS ≥-8.5% (p=0.0037). Subanalysis found that this association remained unchanged. CONCLUSIONS: RVpGLS-derived from 3D CMR FT is associated with a significant prognostic impact in patients with NIDCM with stage C or D HF and without AF.

Simultaneous left atrium anatomy and scar segmentations via deep learning in multiview information with attention.

Three-dimensional late gadolinium enhanced (LGE) cardiac MR (CMR) of left atrial scar in patients with atrial fibrillation (AF) has recently emerged as a promising technique to stratify patients, to guide ablation therapy and to predict treatment success. This requires a segmentation of the high intensity scar tissue and also a segmentation of the left atrium (LA) anatomy, the latter usually being derived from a separate bright-blood acquisition. Performing both segmentations automatically from a single 3D LGE CMR acquisition would eliminate the need for an additional acquisition and avoid subsequent registration issues. In this paper, we propose a joint segmentation method based on multiview two-task (MVTT) recursive attention model working directly on 3D LGE CMR images to segment the LA (and proximal pulmonary veins) and to delineate the scar on the same dataset. Using our MVTT recursive attention model, both the LA anatomy and scar can be segmented accurately (mean Dice score of 93% for the LA anatomy and 87% for the scar segmentations) and efficiently ( ∼ 0.27 s to simultaneously segment the LA anatomy and scars directly from the 3D LGE CMR dataset with 60-68 2D slices). Compared to conventional unsupervised learning and other state-of-the-art deep learning based methods, the proposed MVTT model achieved excellent results, leading to an automatic generation of a patient-specific anatomical model combined with scar segmentation for patients in AF.

Diffusion Tensor Cardiovascular Magnetic Resonance in Cardiac Amyloidosis.

Background Cardiac amyloidosis (CA) is a disease of interstitial myocardial infiltration, usually by light chains or transthyretin. We used diffusion tensor cardiovascular magnetic resonance (DT-CMR) to noninvasively assess the effects of amyloid infiltration on the cardiac microstructure. Methods DT-CMR was performed at diastole and systole in 20 CA, 11 hypertrophic cardiomyopathy, and 10 control subjects with calculation of mean diffusivity, fractional anisotropy, and sheetlet orientation (secondary eigenvector angle). Results Mean diffusivity was elevated and fractional anisotropy reduced in CA compared with both controls and hypertrophic cardiomyopathy (P<0.001). In CA, mean diffusivity was correlated with extracellular volume (r=0.68, P=0.004), and fractional anisotropy was inversely correlated with circumferential strain (r=-0.65, P=0.02). In CA, diastolic secondary eigenvector angle was elevated, and secondary eigenvector angle mobility was reduced compared with controls (both P<0.001). Diastolic secondary eigenvector angle was correlated with amyloid burden measured by extracellular volume in transthyretin, but not light chain amyloidosis. Conclusions DT-CMR can characterize the microstructural effects of amyloid infiltration and is a contrast-free method to identify the location and extent of the expanded disorganized myocardium. The diffusion biomarkers mean diffusivity and fractional anisotropy effectively discriminate CA from hypertrophic cardiomyopathy. DT-CMR demonstrated that failure of sheetlet relaxation in diastole correlated with extracellular volume in transthyretin, but not light chain amyloidosis. This indicates that different mechanisms may be responsible for impaired contractility in CA, with an amyloid burden effect in transthyretin, but an idiosyncratic effect in light chain amyloidosis. Consequently, DT-CMR offers a contrast-free tool to identify novel pathophysiology, improve diagnostics, and monitor disease through noninvasive microstructural assessment.

Automating in vivo cardiac diffusion tensor postprocessing with deep learning-based segmentation.

PURPOSE: In this work we develop and validate a fully automated postprocessing framework for in vivo diffusion tensor cardiac magnetic resonance (DT-CMR) data powered by deep learning. METHODS: A U-Net based convolutional neural network was developed and trained to segment the heart in short-axis DT-CMR images. This was used as the basis to automate and enhance several stages of the DT-CMR tensor calculation workflow, including image registration and removal of data corrupted with artifacts, and to segment the left ventricle. Previously collected and analyzed scans (348 healthy scans and 144 cardiomyopathy patient scans) were used to train and validate the U-Net. All data were acquired at 3 T with a STEAM-EPI sequence. The DT-CMR postprocessing and U-Net training/testing were performed with MATLAB and Python TensorFlow, respectively. RESULTS: The U-Net achieved a median Dice coefficient of 0.93 [0.92, 0.94] for the segmentation of the left-ventricular myocardial region. The image registration of diffusion images improved with the U-Net segmentation (P < .0001), and the identification of corrupted images achieved an F1 score of 0.70 when compared with an experienced user. Finally, the resulting tensor measures showed good agreement between an experienced user and the fully automated method. CONCLUSION: The trained U-Net successfully automated the DT-CMR postprocessing, supporting real-time results and reducing human workload. The automatic segmentation of the heart improved image registration, resulting in improvements of the calculated DT parameters.

Cardiac Diffusion: Technique and Practical Applications.

The 3D microarchitecture of the cardiac muscle underlies the mechanical and electrical properties of the heart. Cardiomyocytes are arranged helically through the depth of the wall, and their shortening leads to macroscopic torsion, twist, and shortening during cardiac contraction. Furthermore, cardiomyocytes are organized in sheetlets separated by shear layers, which reorientate, slip, and shear during macroscopic left ventricle (LV) wall thickening. Cardiac diffusion provides a means for noninvasive interrogation of the 3D microarchitecture of the myocardium. The fundamental principle of MR diffusion is that an MRI signal is attenuated by the self-diffusion of water in the presence of large diffusion-encoding gradients. Since water molecules are constrained by the boundaries in biological tissue (cell membranes, collagen layers, etc.), depicting their diffusion behavior elucidates the shape of the myocardial microarchitecture they are embedded in. Cardiac diffusion therefore provides a noninvasive means to understand not only the dynamic changes in cardiac microstructure of healthy myocardium during cardiac contraction but also the pathophysiological changes in the presence of disease. This unique and innovative technology offers tremendous potential to enable improved clinical diagnosis through novel microstructural and functional assessment. in vivo cardiac diffusion methods are immediately translatable to patients, opening new avenues for diagnostic investigation and treatment evaluation in a range of clinically important cardiac pathologies. This review article describes the 3D microstructure of the LV, explains in vivo and ex vivo cardiac MR diffusion acquisition and postprocessing techniques, as well as clinical applications to date. Level of Evidence: 1 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2019. J. Magn. Reson. Imaging 2020;52:348-368.

Atrial scar quantification via multi-scale CNN in the graph-cuts framework.

Late gadolinium enhancement magnetic resonance imaging (LGE MRI) appears to be a promising alternative for scar assessment in patients with atrial fibrillation (AF). Automating the quantification and analysis of atrial scars can be challenging due to the low image quality. In this work, we propose a fully automated method based on the graph-cuts framework, where the potentials of the graph are learned on a surface mesh of the left atrium (LA) using a multi-scale convolutional neural network (MS-CNN). For validation, we have included fifty-eight images with manual delineations. MS-CNN, which can efficiently incorporate both the local and global texture information of the images, has been shown to evidently improve the segmentation accuracy of the proposed graph-cuts based method. The segmentation could be further improved when the contribution between the t-link and n-link weights of the graph is balanced. The proposed method achieves a mean accuracy of 0.856 ± 0.033 and mean Dice score of 0.702 ± 0.071 for LA scar quantification. Compared to the conventional methods, which are based on the manual delineation of LA for initialization, our method is fully automatic and has demonstrated significantly better Dice score and accuracy (p < 0.01). The method is promising and can be potentially useful in diagnosis and prognosis of AF.