Deep learning-based diffusion tensor cardiac magnetic resonance reconstruction: a comparison study.

In vivo cardiac diffusion tensor imaging (cDTI) is a promising Magnetic Resonance Imaging (MRI) technique for evaluating the microstructure of myocardial tissue in living hearts, providing insights into cardiac function and enabling the development of innovative therapeutic strategies. However, the integration of cDTI into routine clinical practice poses challenging due to the technical obstacles involved in the acquisition, such as low signal-to-noise ratio and prolonged scanning times. In this study, we investigated and implemented three different types of deep learning-based MRI reconstruction models for cDTI reconstruction. We evaluated the performance of these models based on the reconstruction quality assessment, the diffusion tensor parameter assessment as well as the computational cost assessment. Our results indicate that the models discussed in this study can be applied for clinical use at an acceleration factor (AF) of × 2 and × 4 , with the D5C5 model showing superior fidelity for reconstruction and the SwinMR model providing higher perceptual scores. There is no statistical difference from the reference for all diffusion tensor parameters at AF × 2 or most DT parameters at AF × 4 , and the quality of most diffusion tensor parameter maps is visually acceptable. SwinMR is recommended as the optimal approach for reconstruction at AF × 2 and AF × 4 . However, we believe that the models discussed in this study are not yet ready for clinical use at a higher AF. At AF × 8 , the performance of all models discussed remains limited, with only half of the diffusion tensor parameters being recovered to a level with no statistical difference from the reference. Some diffusion tensor parameter maps even provide wrong and misleading information.

STEAM-SASHA: a novel approach for blood- and fat-suppressed native T1 measurement in the right ventricular myocardium.

OBJECTIVE: The excellent blood and fat suppression of stimulated echo acquisition mode (STEAM) can be combined with saturation recovery single-shot acquisition (SASHA) in a novel STEAM-SASHA sequence for right ventricular (RV) native T1 mapping. MATERIALS AND METHODS: STEAM-SASHA splits magnetization preparation over two cardiac cycles, nulling blood signal and allowing fat signal to decay. Breath-hold T1 mapping was performed in a T1 phantom and twice in 10 volunteers using STEAM-SASHA and a modified Look-Locker sequence at peak systole at 3T. T1 was measured in 3 RV regions, the septum and left ventricle (LV). RESULTS: In phantoms, MOLLI under-estimated while STEAM-SASHA over-estimated T1, on average by 3.0% and 7.0% respectively, although at typical 3T myocardial T1 (T1 > 1200 ms) STEAM-SASHA was more accurate. In volunteers, T1 was higher using STEAM-SASHA than MOLLI in the LV and septum (p = 0.03, p = 0.006, respectively), but lower in RV regions (p > 0.05). Inter-study, inter-observer and intra-observer coefficients of variation in all regions were < 15%. Blood suppression was excellent with STEAM-SASHA and noise floor effects were minimal. DISCUSSION: STEAM-SASHA provides accurate and reproducible T1 in the RV with excellent blood and fat suppression. STEAM-SASHA has potential to provide new insights into pathological changes in the RV in future studies.

Referenceless Nyquist ghost correction outperforms standard navigator-based method and improves efficiency of in vivo diffusion tensor cardiovascular magnetic resonance.

PURPOSE: The study aims to assess the potential of referenceless methods of EPI ghost correction to accelerate the acquisition of in vivo diffusion tensor cardiovascular magnetic resonance (DT-CMR) data using both computational simulations and data from in vivo experiments. METHODS: Three referenceless EPI ghost correction methods were evaluated on mid-ventricular short axis DT-CMR spin echo and STEAM datasets from 20 healthy subjects at 3T. The reduced field of view excitation technique was used to automatically quantify the Nyquist ghosts, and DT-CMR images were fit to a linear ghost model for correction. RESULTS: Numerical simulation showed the singular value decomposition (SVD) method is the least sensitive to noise, followed by Ghost/Object method and entropy-based method. In vivo experiments showed significant ghost reduction for all correction methods, with referenceless methods outperforming navigator methods for both spin echo and STEAM sequences at b = 32, 150, 450, and 600 smm - 2 $$ {\mathrm{smm}}^{-2} $$ . It is worth noting that as the strength of the diffusion encoding increases, the performance gap between the referenceless method and the navigator-based method diminishes. CONCLUSION: Referenceless ghost correction effectively reduces Nyquist ghost in DT-CMR data, showing promise for enhancing the accuracy and efficiency of measurements in clinical practice without the need for any additional reference scans.

Biophysical screening and characterisation in medicinal chemistry.

In the last two decades the use of biophysical assays and methods in medicinal chemistry has increased significantly, to meet the demands of the novel targets and modalities that drug discoverers are looking to tackle. The desire to obtain accurate affinities, kinetics, thermodynamics and structural data as early as possible in the drug discovery process has fuelled this innovation. This review introduces the principles underlying the techniques in common use and provides a perspective on the weaknesses and strengths of different methods. Case studies are used to further illustrate some of the applications in medicinal chemistry and a discussion of the emerging biophysical methods on the horizon is presented.

StrainNet: Improved Myocardial Strain Analysis of Cine MRI by Deep Learning from DENSE.

Purpose: To develop a three-dimensional (two dimensions + time) convolutional neural network trained with displacement encoding with stimulated echoes (DENSE) data for displacement and strain analysis of cine MRI. Materials and Methods: In this retrospective multicenter study, a deep learning model (StrainNet) was developed to predict intramyocardial displacement from contour motion. Patients with various heart diseases and healthy controls underwent cardiac MRI examinations with DENSE between August 2008 and January 2022. Network training inputs were a time series of myocardial contours from DENSE magnitude images, and ground truth data were DENSE displacement measurements. Model performance was evaluated using pixelwise end-point error (EPE). For testing, StrainNet was applied to contour motion from cine MRI. Global and segmental circumferential strain (Ecc) derived from commercial feature tracking (FT), StrainNet, and DENSE (reference) were compared using intraclass correlation coefficients (ICCs), Pearson correlations, Bland-Altman analyses, paired t tests, and linear mixed-effects models. Results: The study included 161 patients (110 men; mean age, 61 years ± 14 [SD]), 99 healthy adults (44 men; mean age, 35 years ± 15), and 45 healthy children and adolescents (21 males; mean age, 12 years ± 3). StrainNet showed good agreement with DENSE for intramyocardial displacement, with an average EPE of 0.75 mm ± 0.35. The ICCs between StrainNet and DENSE and FT and DENSE were 0.87 and 0.72, respectively, for global Ecc and 0.75 and 0.48, respectively, for segmental Ecc. Bland-Altman analysis showed that StrainNet had better agreement than FT with DENSE for global and segmental Ecc. Conclusion: StrainNet outperformed FT for global and segmental Ecc analysis of cine MRI.Keywords: Image Postprocessing, MR Imaging, Cardiac, Heart, Pediatrics, Technical Aspects, Technology Assessment, Strain, Deep Learning, DENSE Supplemental material is available for this article. © RSNA, 2023.

Realistic numerical simulations of diffusion tensor cardiovascular magnetic resonance: The effects of perfusion and membrane permeability.

PURPOSE: To study the sensitivity of diffusion tensor cardiovascular magnetic resonance (DT-CMR) to microvascular perfusion and changes in cell permeability. METHODS: Monte Carlo (MC) random walk simulations in the myocardium have been performed to simulate self-diffusion of water molecules in histology-based media with varying extracellular volume fraction (ECV) and permeable membranes. The effect of microvascular perfusion on simulations of the DT-CMR signal has been incorporated by adding the contribution of particles traveling through an anisotropic capillary network to the diffusion signal. The simulations have been performed considering three pulse sequences with clinical gradient strengths: monopolar stimulated echo acquisition mode (STEAM), monopolar pulsed-gradient spin echo (PGSE), and second-order motion-compensated spin echo (MCSE). RESULTS: Reducing ECV intensifies the diffusion restriction and incorporating membrane permeability reduces the anisotropy of the diffusion tensor. Widening the intercapillary velocity distribution results in increased measured diffusion along the cardiomyocytes long axis when the capillary networks are anisotropic. Perfusion amplifies the mean diffusivity for STEAM while the opposite is observed for short diffusion encoding time sequences (PGSE and MCSE). CONCLUSION: The effect of perfusion on the measured diffusion tensor is reduced using an increased reference b-value. Our results pave the way for characterization of the response of DT-CMR to microstructural changes underlying cardiac pathology and highlight the higher sensitivity of STEAM to permeability and microvascular circulation due to its longer diffusion encoding time.

Effects of myocardial sheetlet sliding on left ventricular function.

Left ventricle myocardium has a complex micro-architecture, which was revealed to consist of myocyte bundles arranged in a series of laminar sheetlets. Recent imaging studies demonstrated that these sheetlets re-orientated and likely slided over each other during the deformations between systole and diastole, and that sheetlet dynamics were altered during cardiomyopathy. However, the biomechanical effect of sheetlet sliding is not well-understood, which is the focus here. We conducted finite element simulations of the left ventricle (LV) coupled with a windkessel lumped parameter model to study sheetlet sliding, based on cardiac MRI of a healthy human subject, and modifications to account for hypertrophic and dilated geometric changes during cardiomyopathy remodeling. We modeled sheetlet sliding as a reduced shear stiffness in the sheet-normal direction and observed that (1) the diastolic sheetlet orientations must depart from alignment with the LV wall plane in order for sheetlet sliding to have an effect on cardiac function, that (2) sheetlet sliding modestly aided cardiac function of the healthy and dilated hearts, in terms of ejection fraction, stroke volume, and systolic pressure generation, but its effects were amplified during hypertrophic cardiomyopathy and diminished during dilated cardiomyopathy due to both sheetlet angle configuration and geometry, and that (3) where sheetlet sliding aided cardiac function, it increased tissue stresses, particularly in the myofibre direction. We speculate that sheetlet sliding is a tissue architectural adaptation to allow easier deformations of the LV walls so that LV wall stiffness will not hinder function, and to provide a balance between function and tissue stresses. A limitation here is that sheetlet sliding is modeled as a simple reduction in shear stiffness, without consideration of micro-scale sheetlet mechanics and dynamics.

Automated segmentation of long and short axis DENSE cardiovascular magnetic resonance for myocardial strain analysis using spatio-temporal convolutional neural networks.

BACKGROUND: Cine Displacement Encoding with Stimulated Echoes (DENSE) facilitates the quantification of myocardial deformation, by encoding tissue displacements in the cardiovascular magnetic resonance (CMR) image phase, from which myocardial strain can be estimated with high accuracy and reproducibility. Current methods for analyzing DENSE images still heavily rely on user input, making this process time-consuming and subject to inter-observer variability. The present study sought to develop a spatio-temporal deep learning model for segmentation of the left-ventricular (LV) myocardium, as spatial networks often fail due to contrast-related properties of DENSE images. METHODS: 2D + time nnU-Net-based models have been trained to segment the LV myocardium from DENSE magnitude data in short- and long-axis images. A dataset of 360 short-axis and 124 long-axis slices was used to train the networks, from a combination of healthy subjects and patients with various conditions (hypertrophic and dilated cardiomyopathy, myocardial infarction, myocarditis). Segmentation performance was evaluated using ground-truth manual labels, and a strain analysis using conventional methods was performed to assess strain agreement with manual segmentation. Additional validation was performed using an externally acquired dataset to compare the inter- and intra-scanner reproducibility with respect to conventional methods. RESULTS: Spatio-temporal models gave consistent segmentation performance throughout the cine sequence, while 2D architectures often failed to segment end-diastolic frames due to the limited blood-to-myocardium contrast. Our models achieved a DICE score of 0.83 ± 0.05 and a Hausdorff distance of 4.0 ± 1.1 mm for short-axis segmentation, and 0.82 ± 0.03 and 7.9 ± 3.9 mm respectively for long-axis segmentations. Strain measurements obtained from automatically estimated myocardial contours showed good to excellent agreement with manual pipelines, and remained within the limits of inter-user variability estimated in previous studies. CONCLUSION: Spatio-temporal deep learning shows increased robustness for the segmentation of cine DENSE images. It provides excellent agreement with manual segmentation for strain extraction. Deep learning will facilitate the analysis of DENSE data, bringing it one step closer to clinical routine.

Random walk diffusion simulations in semi-permeable layered media with varying diffusivity.

In this paper we present random walk based solutions to diffusion in semi-permeable layered media with varying diffusivity. We propose a novel transit model for solving the interaction of random walkers with a membrane. This hybrid model is based on treating the membrane permeability and the step change in diffusion coefficient as two interactions separated by an infinitesimally small layer. By conducting an extensive analytical flux analysis, the performance of our hybrid model is compared with a commonly used membrane transit model (reference model). Numerical simulations demonstrate the limitations of the reference model in dealing with step changes in diffusivity and show the capability of the hybrid model to overcome this limitation and to offer substantial gains in computational efficiency. The suitability of both random walk transit models for the application to simulations of diffusion tensor cardiovascular magnetic resonance (DT-CMR) imaging is assessed in a histology-based domain relevant to DT-CMR. In order to demonstrate the usefulness of the new hybrid model for other possible applications, we also consider a larger range of permeabilities beyond those commonly found in biological tissues.

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.

Reproducibility of global and segmental myocardial strain using cine DENSE at 3 T: a multicenter cardiovascular magnetic resonance study in healthy subjects and patients with heart disease.

BACKGROUND: While multiple cardiovascular magnetic resonance (CMR) methods provide excellent reproducibility of global circumferential and global longitudinal strain, achieving highly reproducible segmental strain is more challenging. Previous single-center studies have demonstrated excellent reproducibility of displacement encoding with stimulated echoes (DENSE) segmental circumferential strain. The present study evaluated the reproducibility of DENSE for measurement of whole-slice or global circumferential (Ecc), longitudinal (Ell) and radial (Err) strain, torsion, and segmental Ecc at multiple centers. METHODS: Six centers participated and a total of 81 subjects were studied, including 60 healthy subjects and 21 patients with various types of heart disease. CMR utilized 3 T scanners, and cine DENSE images were acquired in three short-axis planes and in the four-chamber long-axis view. During one imaging session, each subject underwent two separate DENSE scans to assess inter-scan reproducibility. Each subject was taken out of the scanner and repositioned between the scans. Intra-user, inter-user-same-site, inter-user-different-site, and inter-user-Human-Deep-Learning (DL) comparisons assessed the reproducibility of different users analyzing the same data. Inter-scan comparisons assessed the reproducibility of DENSE from scan to scan. The reproducibility of whole-slice or global Ecc, Ell and Err, torsion, and segmental Ecc were quantified using Bland-Altman analysis, the coefficient of variation (CV), and the intraclass correlation coefficient (ICC). CV was considered excellent for CV ≤ 10%, good for 10% < CV ≤ 20%, fair for 20% < CV ≤ 40%, and poor for CV > 40. ICC values were considered excellent for ICC > 0.74, good for ICC 0.6 < ICC ≤ 0.74, fair for ICC 0.4 < ICC ≤ 0.59, poor for ICC < 0.4. RESULTS: Based on CV and ICC, segmental Ecc provided excellent intra-user, inter-user-same-site, inter-user-different-site, inter-user-Human-DL reproducibility and good-excellent inter-scan reproducibility. Whole-slice Ecc and global Ell provided excellent intra-user, inter-user-same-site, inter-user-different-site, inter-user-Human-DL and inter-scan reproducibility. The reproducibility of torsion was good-excellent for all comparisons. For whole-slice Err, CV was in the fair-good range, and ICC was in the good-excellent range. CONCLUSIONS: Multicenter data show that 3 T CMR DENSE provides highly reproducible whole-slice and segmental Ecc, global Ell, and torsion measurements in healthy subjects and heart disease patients.

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.

Validation of cardiac diffusion tensor imaging sequences: A multicentre test-retest phantom study.

Cardiac diffusion tensor imaging (DTI) is an emerging technique for the in vivo characterisation of myocardial microstructure, and there is a growing need for its validation and standardisation. We sought to establish the accuracy, precision, repeatability and reproducibility of state-of-the-art pulse sequences for cardiac DTI among 10 centres internationally. Phantoms comprising 0%-20% polyvinylpyrrolidone (PVP) were scanned with DTI using a product pulsed gradient spin echo (PGSE; N = 10 sites) sequence, and a custom motion-compensated spin echo (SE; N = 5) or stimulated echo acquisition mode (STEAM; N = 5) sequence suitable for cardiac DTI in vivo. A second identical scan was performed 1-9 days later, and the data were analysed centrally. The average mean diffusivities (MDs) in 0% PVP were (1.124, 1.130, 1.113) x 10-3  mm2 /s for PGSE, SE and STEAM, respectively, and accurate to within 1.5% of reference data from the literature. The coefficients of variation in MDs across sites were 2.6%, 3.1% and 2.1% for PGSE, SE and STEAM, respectively, and were similar to previous studies using only PGSE. Reproducibility in MD was excellent, with mean differences in PGSE, SE and STEAM of (0.3 ± 2.3, 0.24 ± 0.95, 0.52 ± 0.58) x 10-5  mm2 /s (mean ± 1.96 SD). We show that custom sequences for cardiac DTI provide accurate, precise, repeatable and reproducible measurements. Further work in anisotropic and/or deforming phantoms is warranted.

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.

Comparison of passive-dosed and solvent spiked exposures of pro-carcinogen, benzo[a]pyrene, to human lymphoblastoid cell line, MCL-5.

Genotoxicity testing methods in vitro provide a means to predict the DNA damaging effects of chemicals on human cells. This is hindered in the case of hydrophobic test compounds, however, which will partition to in vitro components such as plastic-ware and medium proteins, in preference to the aqueous phase of the exposure medium. This affects the freely available test chemical concentration, and as this freely dissolved aqueous concentration is that bioavailable to cells, it is important to define and maintain this exposure. Passive dosing promises to have an advantage over traditional 'solvent spiking' exposure methods and involves the establishment and maintenance of known chemical concentrations in the in vitro medium, and therefore aqueous phase. Passive dosing was applied in a novel format to expose the MCL-5 human lymphoblastoid cell line to the pro-carcinogen, benzo[a]pyrene (B[a]P) and was compared to solvent (dimethyl sulphoxide) spiked B[a]P exposures over 48 h. Passive dosing induced greater changes, at lower concentrations, to micronucleus frequency, p21 mRNA expression, cell cycle abnormalities, and cell and nuclear morphology. This was attributed to a maintained, definable, free chemical concentration using passive dosing and the presence or absence of solvent, and highlights the influence of exposure choice on genotoxic outcomes.

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.