Search

Automatic quantification of the left ventricle (LV) from cardiac magnetic resonance (CMR) images plays an important role in making the diagnosis procedure efficient, reliable, and alleviating the laborious reading work for physicians. Considerable efforts have been devoted to LV quantification using different strategies that include segmentation-based (SG) methods and the recent direct regression (DR) methods. Although both SG and DR methods have obtained great success for the task, a systematic platform to benchmark them remains absent because of differences in label information during model learning. In this paper, we conducted an unbiased evaluation and comparison of cardiac LV quantification methods that were submitted to the Left Ventricle Quantification (LVQuan) challenge, which was held in conjunction with the Statistical Atlases and Computational Modeling of the Heart (STACOM) workshop at the MICCAI 2018. The challenge was targeted at the quantification of 1) areas of LV cavity and myocardium, 2) dimensions of the LV cavity, 3) regional wall thicknesses (RWT), and 4) the cardiac phase, from mid-ventricle short-axis CMR images. First, we constructed a public quantification dataset Cardiac-DIG with ground truth labels for both the myocardium mask and these quantification targets across the entire cardiac cycle. Then, the key techniques employed by each submission were described. Next, quantitative validation of these submissions were conducted with the constructed dataset. The evaluation results revealed that both SG and DR methods can offer good LV quantification performance, even though DR methods do not require densely labeled masks for supervision. Among the 12 submissions, the DR method LDAMT offered the best performance, with a mean estimation error of 301 mm $^2$ for the two areas, 2.15 mm for the cavity dimensions, 2.03 mm for RWTs, and a 9.5% error rate for the cardiac phase classification. Three of the SG methods also delivered comparable performances. Finally, we discussed the advantages and disadvantages of SG and DR methods, as well as the unsolved problems in automatic cardiac quantification for clinical practice applications.

The Covid Symptom Study, a smartphone-based surveillance study on COVID-19 symptoms in the population, is an exemplar of big data citizen science. As of May 23rd, 2021, over 5 million participants have collectively logged over 360 million self-assessment reports since its introduction in March 2020. The success of the Covid Symptom Study creates significant technical challenges around effective data curation. The primary issue is scale. The size of the dataset means that it can no longer be readily processed using standard Python-based data analytics software such as Pandas on commodity hardware. Alternative technologies exist but carry a higher technical complexity and are less accessible to many researchers. We present ExeTera, a Python-based open source software package designed to provide Pandas-like data analytics on datasets that approach terabyte scales. We present its design and capabilities, and show how it is a critical component of a data curation pipeline that enables reproducible research across an international research group for the Covid Symptom Study.

One of the challenges in developing deep learning algorithms for medical image segmentation is the scarcity of annotated training data. To overcome this limitation, data augmentation and semi-supervised learning (SSL) methods have been developed. However, these methods have limited effectiveness as they either exploit the existing data set only (data augmentation) or risk negative impact by adding poor training examples (SSL). Segmentations are rarely the final product of medical image analysis - they are typically used in downstream tasks to infer higher-order patterns to evaluate diseases. Clinicians take into account a wealth of prior knowledge on biophysics and physiology when evaluating image analysis results. We have used these clinical assessments in previous works to create robust quality-control (QC) classifiers for automated cardiac magnetic resonance (CMR) analysis. In this paper, we propose a novel scheme that uses QC of the downstream task to identify high quality outputs of CMR segmentation networks, that are subsequently utilised for further network training. In essence, this provides quality-aware augmentation of training data in a variant of SSL for segmentation networks (semiQCSeg). We evaluate our approach in two CMR segmentation tasks (aortic and short axis cardiac volume segmentation) using UK Biobank data and two commonly used network architectures (U-net and a Fully Convolutional Network) and compare against supervised and SSL strategies. We show that semiQCSeg improves training of the segmentation networks. It decreases the need for labelled data, while outperforming the other methods in terms of Dice and clinical metrics. SemiQCSeg can be an efficient approach for training segmentation networks for medical image data when labelled datasets are scarce., MICCAI STACOM 2020

Valve annuli motion and morphology, measured from non-invasive imaging, can be used to gain a better understanding of healthy and pathological heart function. Measurements such as long-axis strain as well as peak strain rates provide markers of systolic function. Likewise, early and late-diastolic filling velocities are used as indicators of diastolic function. Quantifying global strains, however, requires a fast and precise method of tracking long-axis motion throughout the cardiac cycle. Valve landmarks such as the insertion of leaflets into the myocardial wall provide features that can be tracked to measure global long-axis motion. Feature tracking methods require initialisation, which can be time-consuming in studies with large cohorts. Therefore, this study developed and trained a neural network to identify ten features from unlabeled long-axis MR images: six mitral valve points from three long-axis views, two aortic valve points and two tricuspid valve points. This study used manual annotations of valve landmarks in standard 2-, 3- and 4-chamber long-axis images collected in clinical scans to train the network. The accuracy in the identification of these ten features, in pixel distance, was compared with the accuracy of two commonly used feature tracking methods as well as the inter-observer variability of manual annotations. Clinical measures, such as valve landmark strain and motion between end-diastole and end-systole, are also presented to illustrate the utility and robustness of the method.

Real-time (RT) sequences for cardiac magnetic resonance imaging (CMR) have recently been proposed as alternatives to standard cine CMR sequences for subjects unable to hold the breath or suffering from arrhythmia. RT image acquisitions during free breathing produce comparatively poor quality images, a trade-off necessary to achieve the high temporal resolution needed for RT imaging and hence are less suitable in the clinical assessment of cardiac function. We demonstrate the application of a CycleGAN architecture to train autoencoder networks for synthesising cine-like images from RT images and vice versa. Applying this conversion to real-time data produces clearer images with sharper distinctions between myocardial and surrounding tissues, giving clinicians a more precise means of visually inspecting subjects. Furthermore, applying the transformation to segmented cine data to produce pseudo-real-time images allows this label information to be transferred to the real-time image domain. We demonstrate the feasibility of this approach by training a U-net based architecture using these pseudo-real-time images which can effectively segment actual real-time images.

Estimating dimensional measurements of the left ventricle provides diagnostic values which can be used to assess cardiac health and identify certain pathologies. In this paper we describe our methodology of calculating measurements from left ventricle segmentations automatically generated using deep learning. We use a U-net convolutional neural network architecture built from residual units to segment the left ventricle and then process these segmentations to estimate the area of the cavity and myocardium, the dimensions of the cavity, and the thickness of the myocardium. Determining if an image is part of the diastolic or systolic portion of the cardiac cycle is done by analysing the cavity volume. The quality of our results are dependent on our training regime where we have generated a large derivative dataset by augmenting the original images with free-form deformations. Our expanded training set, in conjunction with simple affine image transforms, creates a sufficiently large training population to prevent over-fitting of the network while still creating an accurate and robust segmentation network. Assessing our method on the STACOM18 LVQuan challenge dataset we find that it significantly outperforms the previously published state-of-the-art on a 5-fold validation all tasks considered.

From basic science to translation, modern biomedical research demands computational models which integrate several interacting physical systems. This paper describes the infrastructural framework for generic multiphysics integration implemented in the software $\boldsymbol{\mathcal{C}}\mathbf{Heart}$, a finite-element code for biomedical research. To generalize the coupling of physics systems, we introduce a framework in which the geometric and operator relationships between the constituent systems are rigorously defined. We then introduce the notion of topological interfaces and define specific operators encompassing many common model coupling requirements. These interfaces enable the evaluation of weak form integrals between mesh subregions of arbitrary finite-element bases' orders, types, and spatial dimensions. Equation maps are introduced which provide abstract representations of the individual physics systems that can be automatically combined to permit a monolithic matrix assembly. Flexible solution strategies for the resulting coupled systems are implemented, permitting fine-tuning of solution updates during fixed point iterations, and subgrouping where several problems are being solved together. Partitioning of coupled mesh domains for optimal load balancing is also supported, taking into account the per-processor cost of the entire coupled problem within the graph problem. The demonstration of the performance is illustrated through important real-world multiphysics problems relevant to cardiac physiology.

We present a methodology for reconstructing full-cycle respiratory and cardiac gated short-axis cine MR sequences from real-time MR data. For patients who are too ill or otherwise incapable of consistent breath holds, real-time MR sequences are the preferred means of acquiring cardiac images, but suffer from inferior image quality compared to standard short-axis sequences and lack cardiac ECG gating. To construct a sequence from real-time images which, as close as possible, replicates the characteristics of short-axis series, the phase of the cardiac cycle must be estimated for each image and the left ventricle identified, to be used as a landmark for slice re-alignment. Our method employs CNN-based deep learning to segment the left ventricle in the real-time sequence, which is then used to estimate the pool volume and thus the position of each image in the cardiac cycle. We then use manifold learning to account for the respiratory cycle so as to select images of the best quality at expiration. From these images a selection is made to automatically reconstruct a single cardiac cycle, and the images and segmentations are then aligned. The aligned pool segmentations can then be used to calculate volume over time and thus volume-based biomarkers.

Sharing data between scientists and with clinicians in cardiac research has been facilitated significantly by the use of web technologies. The potential of this technology has meant that information sharing has been routinely promoted through databases that have encouraged stakeholder participation in communities around these services. In this paper we discuss the Anatomical Model Database (AMDB) (Gianni et al. Functional imaging and modeling of the heart. Springer, Heidelberg, 2009; Gianni et al. Phil Trans Ser A Math Phys Eng Sci 368:3039–3056, 2010) which both facilitate a database-centric approach to collaboration, and also extends this framework with new capabilities for creating new mesh data. AMDB currently stores cardiac \ud geometric models described in Gianni et al. (Functional imaging and modelling of the heart. Springer, Heidelberg, 2009), a number of additional cardiac models describing geometry and functional properties, and most recently models generated using a web service. The functional models represent data from simulations in geometric form, such as electrophysiology or mechanics, many of which are present in AMDB as part of a benchmark study. Finally, the heartgen service has been added for producing left or bi-ventricle models derived from binary image data using the methods described in Lamata et al. (Med Image Anal 15:801–813, 2011). \ud The results can optionally be hosted on AMDB alongside other community-provided anatomical models. AMDB is, therefore, a unique database storing geometric data (rather than abstract models or image data) combined with a powerful web service for generating new geometric models.

Biomedical research, combining multi-modal image and geometry data, presents unique challenges for data visualization, processing, and quantitative analysis. Medical imaging provides rich information, from anatomical to deformation, but extracting this to a coherent picture across image modalities with preserved quality is not trivial. Addressing these challenges and integrating visualization with image and quantitative analysis results in Eidolon, a platform which can adapt to rapidly changing research workflows. In this paper we outline Eidolon, a software environment aimed at addressing these challenges, and discuss the novel integration of visualization and analysis components. These capabilities are demonstrated through the example of cardiac strain analysis, showing the Eidolon supports and enhances the workflow.

Ongoing developments in cardiac modelling have resulted, in particular, in the development of advanced and increasingly complex computational frameworks for simulating cardiac tissue electrophysiology. The goal of these simulations is often to represent the detailed physiology and pathologies of the heart using codes that exploit the computational potential of high-performance computing architectures. These developments have rapidly progressed the simulation capacity of cardiac virtual physiological human style models; however, they have also made it increasingly challenging to verify that a given code provides a faithful representation of the purported governing equations and corresponding solution techniques. This study provides the first cardiac tissue electrophysiology simulation benchmark to allow these codes to be verified. The benchmark was successfully evaluated on 11 simulation platforms to generate a consensus gold-standard converged solution. The benchmark definition in combination with the gold-standard solution can now be used to verify new simulation codes and numerical methods in the future.

The applicability of aspects as a means of implementing runtime contract checking has been demonstrated in prior work, where contracts are identified as cross-cutting concerns [12, 13]. Checking contracts at runtime encounters a set of challenges within concurrent environments, such as the risk that evaluation will introduce deadlock to code which is otherwise deadlock-free. This paper presents a simple methodology for generating runtime contract checking aspects targeted at concurrent programs. The novel features of this approach allow contracts to depend on active objects without race conditions or deadlock, and addresses issues relating to timing and blame assignment. The CoJava language is discussed whose tool-supported aspect generation methodology allows the correct checking of contracts predicated on active objects. © 2010 ACM.

Active objects are an attractive method of introducing concurrency into Java-like languages by decoupling method execution from invocation. In this paper, we show how ownership is used in the Java [14] subset language CoJava [17] to prevent deadlock associated with active object method calls. This approach builds on existing type-based approaches that eliminates data races and data-based deadlock in concurrent systems. The novel addition is the use of ownership to organize active objects, thus preventing deadlock from arising when objects are allowed to block awaiting responses from others.Typechecking is used to prevent threads from sharing mutable data, thus CoJava is free of data races and data-based deadlock. Behavioural deadlock is prevented by the use of promise objects which prevent clients from blocking indefinitely while awaiting responses. Ownership imposes a hierarchy on active objects; this allows owners to safely block while waiting for responses from owned objects. The paper also discusses the implications of this approach to specification with JML, formal reasoning about programs, and the consequences to runtime assertion checking.