Magnetic Resonance Elastography (MRE) quantifies soft tissue stiffness by measuring induced shear waves. MRE inversion techniques for parameter reconstruction are often affected by noise and compression waves. Neural network-based inversions have emerged as a possible solution to address these challenges. However, current approaches lack generalizability and do not provide uncertainty estimates. Therefore, we propose ElastoNet, a novel neural network-based approach for MRE wave inversion that analyzes multiple wave components independently of resolution and vibration frequency and provides uncertainty quantification maps. ElastoNet was trained on synthetically generated wave patches of 5 × 5 pixels. Uncertainty quantification was implemented using evidential deep learning. ElastoNet was evaluated on synthetically generated plane waves, finite element simulations of abdominal MRE, phantom MRE data, and a prospective wideband multifrequency abdominal MRE study (excitation frequencies of 20 to 80 Hz) in 14 healthy volunteers. ElastoNet was compared with established inversion methods LFE and k-MDEV, as well as neural network-based TWENN. ElastoNet generated shear wave speed maps as a proxy of stiffness with comparable or better accuracy than established methods and did not require retraining for different resolutions and vibration frequencies. ElastoNet achieved a lower root mean square error relative to ground truth values in finite element simulations and phantom data than other inversion methods and provided uncertainty maps. ElastoNet is a promising method for universal neural network-based inversion in MRE, effectively overcoming current challenges and expanding the potential use of neural networks in diagnostic MRE applications.

Abstract To achieve the best treatment of mitral valve disease in a patient, surgeons aim to optimally combine complementary surgical techniques. Image‐based in silico simulation as well as visualization of the mitral valve dynamics can support the visual analysis of the patient‐specific valvular dynamics and enable an exploration of different therapy options. The usage in a time‐constrained clinical environment requires a mitral valve model that is cost‐effective, easy to set up, parameterize and evaluate. Working towards this goal, we develop a simplified model of the mitral valve and analyse its applicability for the sketched use‐case. We propose a novel approach to simulate the mitral valve with position‐based dynamics. The resulting mitral valve model can be deformed to simulate the closing and opening, and incorporate changes caused by virtual interventions in the simulation. Ten mitral valves were reconstructed from transesophageal echocardiogram sequences of patients with normal and abnormal physiology for evaluation. Simulation results showed good agreements with expert annotations of the original image data and reproduced valve closure in all cases. In four of five pathological cases, abnormal closing behaviour was correctly reproduced. In future research, we aim to improve the parameterization of the model in terms of biomechanical correctness and perform a more extensive validation.

Deep learning requires large labeled datasets that are difficult to gather in medical imaging due to data privacy issues and time-consuming manual labeling. Generative Adversarial Networks (GANs) can alleviate these challenges enabling synthesis of shareable data. While 2D GANs have been used to generate 2D images with their corresponding labels, they cannot capture the volumetric information of 3D medical imaging. 3D GANs are more suitable for this and have been used to generate 3D volumes but not their corresponding labels. One reason might be that synthesizing 3D volumes is challenging owing to computational limitations. In this work, we present 3D GANs for the generation of 3D medical image volumes with corresponding labels applying mixed precision to alleviate computational constraints. We generated 3D Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) patches with their corresponding brain blood vessel segmentation labels. We used four variants of 3D Wasserstein GAN (WGAN) with: 1) gradient penalty (GP), 2) GP with spectral normalization (SN), 3) SN with mixed precision (SN-MP), and 4) SN-MP with double filters per layer (c-SN-MP). The generated patches were quantitatively evaluated using the Fréchet Inception Distance (FID) and Precision and Recall of Distributions (PRD). Further, 3D U-Nets were trained with patch-label pairs from different WGAN models and their performance was compared to the performance of a benchmark U-Net trained on real data. The segmentation performance of all U-Net models was assessed using Dice Similarity Coefficient (DSC) and balanced Average Hausdorff Distance (bAVD) for a) all vessels, and b) intracranial vessels only. Our results show that patches generated with WGAN models using mixed precision (SN-MP and c-SN-MP) yielded the lowest FID scores and the best PRD curves. Among the 3D U-Nets trained with synthetic patch-label pairs, c-SN-MP pairs achieved the highest DSC (0.841) and lowest bAVD (0.508) compared to the benchmark U-Net trained on real data (DSC 0.901; bAVD 0.294) for intracranial vessels. In conclusion, our solution generates realistic 3D TOF-MRA patches and labels for brain vessel segmentation. We demonstrate the benefit of using mixed precision for computational efficiency resulting in the best-performing GAN-architecture. Our work paves the way towards sharing of labeled 3D medical data which would increase generalizability of deep learning models for clinical use.

Abstract Cardiac four‐dimensional phase‐contrast magnetic resonance imaging (4D PC‐MRI) acquisitions have gained increasing clinical interest in recent years. They allow to non‐invasively obtain extensive information about patient‐specific hemodynamics, and thus have a great potential to improve the diagnosis, prognosis and therapy planning of cardiovascular diseases. A dataset contains time‐resolved, three‐dimensional blood flow directions and strengths, making comprehensive qualitative and quantitative data analysis possible. Quantitative measures, such as stroke volumes, help to assess the cardiac function and to monitor disease progression. Qualitative analysis allows to investigate abnormal flow characteristics, such as vortices, which are correlated to different pathologies. Processing the data comprises complex image processing methods, as well as flow analysis and visualization. In this work, we mainly focus on the aorta. We provide an overview of data measurement and pre‐processing, as well as current visualization and quantification methods. This allows other researchers to quickly catch up with the topic and take on new challenges to further investigate the potential of 4D PC‐MRI data.

Studies have demonstrated the feasibility of late Gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging for guiding the management of patients with sequelae to myocardial infarction, such as ventricular tachycardia and heart failure. Clinical implementation of these developments necessitates a reproducible and reliable segmentation of the infarcted regions. It is challenging to compare new algorithms for infarct segmentation in the left ventricle (LV) with existing algorithms. Benchmarking datasets with evaluation strategies are much needed to facilitate comparison. This manuscript presents a benchmarking evaluation framework for future algorithms that segment infarct from LGE CMR of the LV. The image database consists of 30 LGE CMR images of both humans and pigs that were acquired from two separate imaging centres. A consensus ground truth was obtained for all data using maximum likelihood estimation. Six widely-used fixed-thresholding methods and five recently developed algorithms are tested on the benchmarking framework. Results demonstrate that the algorithms have better overlap with the consensus ground truth than most of the n-SD fixed-thresholding methods, with the exception of the Full-Width-at-Half-Maximum (FWHM) fixed-thresholding method. Some of the pitfalls of fixed thresholding methods are demonstrated in this work. The benchmarking evaluation framework, which is a contribution of this work, can be used to test and benchmark future algorithms that detect and quantify infarct in LGE CMR images of the LV. The datasets, ground truth and evaluation code have been made publicly available through the website: https://www.cardiacatlas.org/web/guest/challenges.

This paper evaluates five 3D ultrasound tracking algorithms regarding their ability to quantify abnormal deformation in timing or amplitude. A synthetic database of B-mode image sequences modeling healthy, ischemic and dyssynchrony cases was generated for that purpose. This database is made publicly available to the community. It combines recent advances in electromechanical and ultrasound modeling. For modeling heart mechanics, the Bestel-Clement-Sorine electromechanical model was applied to a realistic geometry. For ultrasound modeling, we applied a fast simulation technique to produce realistic images on a set of scatterers moving according to the electromechanical simulation result. Tracking and strain accuracies were computed and compared for all evaluated algorithms. For tracking, all methods were estimating myocardial displacements with an error below 1 mm on the ischemic sequences. The introduction of a dilated geometry was found to have a significant impact on accuracy. Regarding strain, all methods were able to recover timing differences between segments, as well as low strain values. On all cases, radial strain was found to have a low accuracy in comparison to longitudinal and circumferential components.

Abstract Cardiovascular imaging with current multislice spiral computed tomography (MSCT) technology enables a non‐invasive evaluation of the coronary arteries. Contrast‐enhanced MSCT angiography with high spatial resolution allows for a segmentation of the coronary artery tree. We present an automatically adapted transfer function (TF) specification to highlight pathologic changes of the vessel wall based on the segmentation result of the coronary artery tree. The TFs are combined with common visualization techniques, such as multiplanar reformation and direct volume rendering for the evaluation of coronary arteries in MSCT image data. The presented TF‐based mapping of CT values in Hounsfield Units (HU) to color and opacity leads to a different color coding for different plaque types. To account for varying HU values of the vessel lumen caused by the contrast medium, the TFs are adapted to each dataset by local histogram analysis. We describe an informal evaluation with three board‐certified radiologists which indicates that the represented visualizations guide the user's attention to pathologic changes of the vessel wall as well as provide an overview about spatial variations.

Dynamic contrast-enhanced image data (perfusion data) are used to characterize regional tissue perfusion. Perfusion data consist of a sequence of images, acquired after a contrast agent bolus is applied. Perfusion data are used for diagnostic purposes in oncology, ischemic stroke assessment or myocardial ischemia. The diagnostic evaluation of perfusion data is challenging, since the data is complex and exhibits various artifacts, e.g., motion artifacts. We provide an overview on existing methods to analyze, and visualize CT and MR perfusion data. The integrated visualization of several 2D parameter maps, the 3D visualization of parameter volumes and exploration techniques are discussed. An essential aspect in the diagnosis of perfusion data is the correlation between perfusion data and derived time-intensity curves as well as with other image data, in particular with high resolution morphologic image data. We discuss visualization support with respect to the three major application areas: ischemic stroke diagnosis, breast tumor diagnosis and the diagnosis of coronary heart disease.

Current magnetic resonance imaging (MRI) technology allows the determination of patient-individual coronary tree structure, detection of infarctions, and assessment of myocardial perfusion. Joint inspection of these three aspects yields valuable information for therapy planning, e.g., through classification of myocardium into healthy tissue, regions showing a reversible hypoperfusion, and infarction with additional information on the corresponding supplying artery. Standard imaging protocols normally provide image data with different orientations, resolutions and coverages for each of the three aspects, which makes a direct comparison of analysis results difficult. The purpose of this work is to develop methods for the alignment and combined analysis of these images. The proposed approach is applied to 21 datasets of healthy and diseased patients from the clinical routine. The evaluation shows that, despite limitations due to typical MRI artifacts, combined inspection is feasible and can yield clinically useful information.

We present static and dynamic techniques to visualize perfusion data and to relate perfusion data to morphologic image data. In particular, we describe the integrated analysis of MRI myocardial perfusion data with CT coronary angiographies depicting the morphology. We refined the Bull’s-Eye Plot, a wide-spread and accepted analysis tool in cardiac diagnosis, to show aggregated information of perfusion data at rest and under stress. The correlation between regions of the myocard with reduced perfusion and 3d renditions of the coronary vessels can be explored within a synchronized visualization of both. With our research, we attempt to improve the diagnosis of early stage coronary artery disease.