Search

Three-dimensional electroanatomical mapping (EAM) has the potential to identify the pathological substrate underlying ventricular arrhythmias (VAs) in different clinical settings by detecting myocardial areas with abnormally low voltages, which reflect the presence of different cardiomyopathic substrates. In athletes, the added value of EAM may be to enhance the efficacy of third-level diagnostic tests and cardiac magnetic resonance (CMR) in detecting concealed arrhythmogenic cardiomyopathies. Additional benefits of EAM in the athlete include the potential impact on disease risk stratification and the consequent implications for eligibility to competitive sports. This opinion paper of the Italian Society of Sports Cardiology aims to guide general sports medicine physicians and cardiologists on the clinical decision when to eventually perform an EAM study in the athlete, highlighting strengths and weaknesses for each cardiovascular disease at risk of sudden cardiac death during sport. The importance of early (preclinical) diagnosis to prevent the negative effects of exercise on phenotypic expression, disease progression, and worsening of the arrhythmogenic substrate is also addressed. • Three-dimensional electroanatomical mapping (EAM) has the potential to identify the pathological substrate underlying ventricular arrhythmias (VAs). • In athletes, EAM may enhance the efficacy of third-level diagnostic tests and cardiac magnetic resonance (CMR) in detecting concealed arrhythmogenic cardiomyopathies. • An electroanatomical mapping-guided endomyocardial biopsy may be considered as additional diagnostic tool among athletes presenting with complex ventricular arrhythmias and unclear findings after comprehensive clinical-imaging assessments and genetic testing. • The role of electroanatomical mapping is particularly relevant in the differentiation between myocarditis and forms of arrhythmogenic cardiomyopathy, especially if integrated with the biopsy and histological examination that allows sampling in an extremely precise way the areas of altered voltage, expression of myocardial fibrosis. [ABSTRACT FROM AUTHOR]

Data regarding the diagnosis, management, and follow-up of carcinoid syndrome (CS) and carcinoid heart disease (CHD) were identified by searches of the MEDLINE database using specific terms in human studies: CS; CHD; screening; epidemiology; diagnosis; treatment; prognosis. CS, carcinoid syndrome; CHD, carcinoid heart disease; MDT, multidisciplinary team; PRRT, peptide receptor radioligand, therapy; SSA, somatostatin analogues; u5-HIAA, urinary 5-hydroxiindolic acid gl Ultimately, all patients develop symptomatic progression of CS when on an SSA. 2 TABLELevel of evidence and grade of recommendation as specified in the GRADE criteria HT

Cardiac magnetic resonance (CMR) has become an essential tool for the evaluation of patients affected or at risk of developing cardiomyopathies (CMPs). In fact, CMR not only provides precise data on cardiac volumes, wall thickness, mass and systolic function but it also a non-invasive characterization of myocardial tissue, thus helping the early diagnosis and the precise phenotyping of the different CMPs, which is essential for early and individualized treatment of patients. Furthermore, several CMR characteristics, such as the presence of extensive LGE or abnormal mapping values, are emerging as prognostic markers, therefore helping to define patients' risk. Lastly new experimental CMR techniques are under investigation and might contribute to widen our knowledge in the field of CMPs. In this perspective, CMR appears an essential tool to be systematically applied in the diagnostic and prognostic work-up of CMPs in clinical practice. This review provides a deep overview of clinical applicability of standard and emerging CMR techniques in the management of CMPs. [ABSTRACT FROM AUTHOR]

Valvular regurgitation represents an important cause of cardiovascular morbidity and mortality. Imaging is pivotal in the evaluation of native valve regurgitation and echocardiography is the primary imaging modality for this purpose. The imaging assessment of valvular regurgitation should integrate quantification of the regurgitation, assessment of the valve anatomy and function, and the consequences of valvular disease on cardiac chambers. In clinical practice, the management of patients with valvular regurgitation largely relies on the results of imaging. It is crucial to provide standards that aim at establishing a baseline list of measurements to be performed when assessing native valve regurgitation. The present document aims to present clinical guidance for the multi-modality imaging assessment of native valvular regurgitation. [ABSTRACT FROM AUTHOR]

Cardiac magnetic resonance imaging (MRI) usually requires a long acquisition time. The movement of the patients during MRI acquisition will produce image artifacts. Previous studies have shown that clear MR image texture edges are of great significance for pathological diagnosis. In this paper, a motion artifact reduction method for cardiac MRI based on edge enhancement network is proposed. Firstly, the four-plane normal vector adaptive fractional differential mask is applied to extract the edge features of blurred images. The four-plane normal vector method can reduce the noise information in the edge feature maps. The adaptive fractional order is selected according to the normal mean gradient and the local Gaussian curvature entropy of the images. Secondly, the extracted edge feature maps and blurred images are input into the de-artifact network. In this network, the edge fusion feature extraction network and the edge fusion transformer network are specially designed. The former combines the edge feature maps with the fuzzy feature maps to extract the edge feature information. The latter combines the edge attention network and the fuzzy attention network, which can focus on the blurred image edges. Finally, extensive experiments show that the proposed method can obtain higher peak signal-to-noise ratio and structural similarity index measure compared to state-of-art methods. The de-artifact images have clear texture edges. [ABSTRACT FROM AUTHOR]

Cardiovascular diseases (CVDs) are the leading cause of premature death and disability globally, leading to significant increases in healthcare costs and economic strains. Artificial intelligence (AI) is emerging as a crucial technology in this context, promising to have a significant impact on the management of CVDs. A wide range of methods can be used to develop effective models for medical applications, encompassing everything from predicting and diagnosing diseases to determining the most suitable treatment for individual patients. This literature review synthesizes findings from multiple studies that apply AI technologies such as machine learning algorithms and neural networks to electrocardiograms, echocardiography, coronary angiography, computed tomography, and cardiac magnetic resonance imaging. A narrative review of 127 articles identified 31 papers that were directly relevant to the research, encompassing a broad spectrum of AI applications in cardiology. These applications included AI models for ECG, echocardiography, coronary angiography, computed tomography, and cardiac MRI aimed at diagnosing various cardiovascular diseases such as coronary artery disease, hypertrophic cardiomyopathy, arrhythmias, pulmonary embolism, and valvulopathies. The papers also explored new methods for cardiovascular risk assessment, automated measurements, and optimizing treatment strategies, demonstrating the benefits of AI technologies in cardiology. In conclusion, the integration of artificial intelligence (AI) in cardiology promises substantial advancements in diagnosing and treating cardiovascular diseases. [ABSTRACT FROM AUTHOR]

Deep learning-based segmentation models often struggle to achieve optimal performance when encountering new, unseen semantic classes. Their effectiveness hinges on vast amounts of annotated data and high computational resources for training. However, a promising solution to mitigate these challenges is the adoption of few-shot segmentation (FSS) networks, which can train models with reduced annotated data. The inherent complexity of medical images limits the applicability of FSS in medical imaging, despite its potential. Recent advancements in self-supervised label-efficient FSS models have demonstrated remarkable efficacy in medical image segmentation tasks. This paper presents a novel FSS architecture that enhances segmentation accuracy by utilising fewer features than existing methodologies. Additionally, this paper proposes a novel self-supervised learning approach that utilises supervoxel and augmented superpixel images to further enhance segmentation accuracy. This paper assesses the efficacy of the proposed model on two different datasets: abdominal magnetic resonance imaging (MRI) and cardiac MRI. The proposed model achieves a mean dice score and mean intersection over union of 81.62% and 70.38% for abdominal images, and 79.38% and 65.23% for cardiac images. [ABSTRACT FROM AUTHOR]

Background: Magnetic Resonance Imaging (MRI) is a highly demanded medical imaging system due to high resolution, large volumetric coverage, and ability to capture the dynamic and functional information of body organs e.g. cardiac MRI is employed to assess cardiac structure and evaluate blood flow dynamics through the cardiac valves. Long scan time is the main drawback of MRI, which makes it difficult for the patients to remain still during the scanning process. Objective: By collecting fewer measurements, MRI scan time can be shortened, but this undersampling causes aliasing artifacts in the reconstructed images. Advanced image reconstruction algorithms have been used in literature to overcome these undersampling artifacts. These algorithms are computationally expensive and require a long time for reconstruction which makes them infeasible for real-time clinical applications e.g. cardiac MRI. However, exploiting the inherent parallelism in these algorithms can help to reduce their computation time. Methods: Low-rank plus sparse (L+S) matrix decomposition model is a technique used in literature to reconstruct the highly undersampled dynamic MRI (dMRI) data at the expense of long reconstruction time. In this paper, Compressed Singular Value Decomposition (cSVD) model is used in L+S decomposition model (instead of conventional SVD) to reduce the reconstruction time. The results provide improved quality of the reconstructed images. Furthermore, it has been observed that cSVD and other parts of the L+S model possess highly parallel operations; therefore, a customized GPU based parallel architecture of the modified L+S model has been presented to further reduce the reconstruction time. Results: Four cardiac MRI datasets (three different cardiac perfusion acquired from different patients and one cardiac cine data), each with different acceleration factors of 2, 6 and 8 are used for experiments in this paper. Experimental results demonstrate that using the proposed parallel architecture for the reconstruction of cardiac perfusion data provides a speed-up factor up to 19.15× (with memory latency) and 70.55× (without memory latency) in comparison to the conventional CPU reconstruction with no compromise on image quality. Conclusion: The proposed method is well-suited for real-time clinical applications, offering a substantial reduction in reconstruction time. [ABSTRACT FROM AUTHOR]

Premature ventricular contractions (PVCs) are a common finding in clinical practice, requiring a full diagnostic work-up in order to exclude an underlying cardiomyopathy. Still, in a substantial proportion of patients, these investigations do not identify any substrate, and the PVCs are labelled as idiopathic. Cardiac magnetic resonance (CMR) has proven in the last decades as the method of choice for the exploration of patients with cardiomyopathies, since it can identify subtle changes in the myocardial tissue and help with risk stratification. In patients with idiopathic PVCs and a high PVC burden, several studies report the presence of late gadolinium enhancement (LGE) at CMR, which can offer additional diagnostic and prognostic benefits, as well as assistance in catheter ablation procedures, as the risk for adverse cardiac and risk for arrhythmic events events is higher compared to patients without scar. This paper focuses on the impact of the presence of LGE in patients with idiopathic PVCs, reviewing all the relevant studies published so far, including randomized controlled clinical trials, prospective or retrospective cohort studies, case series and case reports as well as systematic reviews. [ABSTRACT FROM AUTHOR]

Aims: Acute myocarditis, although a rare disease, can be associated with sudden cardiac death or the need for transplantation in both children and young adults. To date, there is no definitive evidence to support the routine use of immunosuppressive therapy or treatment targeting inflammation in patients with myocarditis. Animal models of cardiovascular (CV), as well as neurological diseases, have demonstrated that cannabidiol has significant anti‐inflammatory properties and may represent a promising therapy in acute myocarditis. This efficacy has been shown in a murine model of autoimmune myocarditis as well as in in vitro and in vivo models of heart failure (HF). Methods and results: We present the rationale and design of the ARCHER Trial, an international multicentre, double‐blind, randomized, placebo‐controlled, phase II study examining the safety and efficacy of a pharmaceutically produced cannabidiol formulation, in patients with mild to moderate acute myocarditis. Eligible patients are those with acute myocarditis, randomized within 10 days of the diagnostic cardiac MRI (CMR), which has met defined diagnostic criteria for myocarditis. Oral treatment (cannabidiol or placebo) is titrated from 2.5 mg/kg of body weight up to 10 mg/kg of body weight b.i.d. (or highest tolerated dose) and taken for 12 weeks in addition to standard of care therapy for HF. The primary endpoints are defined as changes in global longitudinal strain (GLS) and extra cellular volume (ECV), measured by CMR at 12 weeks. Assuming 80% power, a 5% alpha risk and 25% missing CMR follow‐up data at Week 12, 100 patients are required to demonstrate the desired treatment effect of 18%. The change in left ventricular ejection fraction (LVEF) from baseline to Week 12 was selected as the secondary endpoint. Additional exploratory endpoints include changes in hs‐troponin, NT‐proBNP, markers of inflammation and endothelial function during the 12‐week treatment period. The trial is ongoing but is now more than 50% recruited. As enrolment in the trial continues, no interim data are available for inclusion in this Design paper. Conclusions: The ongoing ARCHER Trial is an international, multicentre, double‐blind, randomized, placebo‐controlled phase II study, designed to determine the effect of a pharmaceutically produced cannabidiol formulation on CMR parameters in patients presenting with acute myocarditis. Enrolment of 100 patients is expected to conclude in Q3 2024. Study results will be available in early 2025. [ABSTRACT FROM AUTHOR]

Congenital absence of the pericardium (CAP) is an unusual condition discovered, in most cases, incidentally but can potentially lead to fatal complications, including severe arrhythmias and sudden death. Recently, the use of modern imaging technologies has increased the diagnosis of CAP, providing important findings for risk stratification. Nevertheless, there is not yet consensus regarding therapeutic decisions, and the management of patients with CAP remains challenging. In this paper, we discuss the pathophysiological implication of CAP, review the current literature and explain the role of multimodality imaging tools for its diagnosis, management and treatment. [ABSTRACT FROM AUTHOR]

Background: Congenital absence of pericardium (CAP), also known as pericardial agenesis, represents an uncommon cardiac abnormality and mostly incidental finding. It can be subdivided into complete and partial (left or right-sided) forms. Because of its infrequency, just case reports and a few case series have been released so far. This paper represents the largest systematic review in the field. Nine features (age at diagnosis, type, gender, clinical presentation, electrocardiography, imaging (ultrasounds, CT/MRI), concomitant cardiac defects, and outcome) were analysed. Methods: The electronic database PubMed was investigated from its establishment up to July 15th, 2023. Just case reports and case series were included. Animal studies, papers that were not in English, Spanish, and Italian, and those manuscripts not reporting at least seven of the nine analysed features. were ruled out. The analysed data were reported mostly in terms of percentage. Results: One hundred eighty studies were included encompassing 247 patients. More than half of reviewed CAP cases were in males (63.2%). The mean age at diagnosis was 31.8 ± 19.3 years; a range of 32 weeks of gestation-81 years). 23.5% of the patients did not report any symptoms. The most common clinical presentations were chest pain (35.2%) and dyspnoea (29.2%). The most commonly seen ECG changes were right axis deviation (28.7%) and right bundle branch block (23.9%). CAP was suspected or diagnosed by echocardiography in 20.1% of cases. The diagnosis was made by CT and/or MRI in 61.9% of cases. CAP was left-sided in 71.2%, complete in 23.1%, and right-sided in 5.7%. A concomitant congenital heart defect was found in 22.7%, especially in the form of atrial septal defect (6.5%) and patency of ductus arteriosus (2.8%). The pericardial repair was required in 12.9% of the incomplete forms of the disease. Never did the complete form require surgical correction. The outcome appeared favourable in the vast majority of cases, with just 18 deaths (7.3%). Discussion: The main limitation of this systematic review is that it is based just on case reports and case series, due to the lack of large studies on CAP. However, it represents the largest analysis in the field. Due to the rarity of CAP establishing an International Registry is recommended. [ABSTRACT FROM AUTHOR]

Background Myocarditis is challenging to diagnose due to its varied presentations. Endomyocardial biopsy is the gold standard for diagnosis, but its invasive nature has led to alternative non-invasive modalities, notably cardiovascular magnetic resonance (CMR). Identifying the precise aetiology of myocarditis is crucial for effective treatment, yet extra-cardiac causes are often overlooked. In this paper, we spotlight the underexplored role of CMR in diagnosing extra-cardiac aetiologies, utilizing three insightful cases for illustration. Case summary The first case is a 31-year-old patient with myocarditis secondary to a pyogenic liver abscess, identified through CMR, who improved after abscess drainage. The second case involves a 54-year-old patient with myocarditis attributed to adult T-cell leukaemia–lymphoma, with the loco-regional thickening process identified thanks to CMR. This patient had an unfavourable disease progression due to the underlying malignancy. The third case concerns a 23-year-old patient suffering from myocarditis associated with pneumonia, again illustrated effectively through CMR imaging, who recovered after antibiotic treatment. Discussion These cases underline the overlooked potential of CMR in diagnosing extra-cardiac aetiologies of myocarditis, even though such causes are rare. Despite current guidelines recognizing the importance of identifying the aetiology of myocarditis, they do not explicitly address the role of CMR in diagnosing extra-cardiac aetiologies. This article, therefore, proposes that future guidelines could emphasize the utility of CMR in exploring these causes, potentially leading to more accurate diagnoses and improved patient outcomes. It also advocates for a comprehensive, multidisciplinary approach to myocarditis diagnosis, encouraging vigilance for potential loco-regional causes, and calls for further research in this area. [ABSTRACT FROM AUTHOR]

Background: Cardiac magnetic resonance (CMR) provides excellent temporal and spatial resolution, tissue characterization, and flow measurements. This enables major advantages when guiding cardiac invasive procedures compared with X-ray fluoroscopy or ultrasound guidance. However, clinical implementation is limited due to limited availability of technological advancements in magnetic resonance imaging (MRI) compatible equipment. A systematic review of the available literature on past and present applications of interventional MR and its technology readiness level (TRL) was performed, also suggesting future applications. Methods: A structured literature search was performed using PubMed. Search terms were focused on interventional CMR, cardiac catheterization, and other cardiac invasive procedures. All search results were screened for relevance by language, title, and abstract. TRL was adjusted for use in this article, level 1 being in a hypothetical stage and level 9 being widespread clinical translation. The papers were categorized by the type of procedure and the TRL was estimated. Results: Of 466 papers, 117 papers met the inclusion criteria. TRL was most frequently estimated at level 5 meaning only applicable to in vivo animal studies. Diagnostic right heart catheterization and cavotricuspid isthmus ablation had the highest TRL of 8, meaning proven feasibility and efficacy in a series of humans. Conclusion: This article shows that interventional CMR has a potential widespread application although clinical translation is at a modest level with TRL usually at 5. Future development should be directed toward availability of MR-compatible equipment and further improvement of the CMR techniques. This could lead to increased TRL of interventional CMR providing better treatment. [ABSTRACT FROM AUTHOR]

Automatic and accurate segmentation of medical images plays an essential role in disease diagnosis and treatment planning. Convolution neural networks have achieved remarkable results in medical image segmentation in the past decade. Meanwhile, deep learning models based on Transformer architecture also succeeded tremendously in this domain. However, due to the ambiguity of the medical image boundary and the high complexity of physical organization structures, implementing effective structure extraction and accurate segmentation remains a problem requiring a solution. In this paper, we propose a novel Dual Encoder Network named DECTNet to alleviate this problem. Specifically, the DECTNet embraces four components, which are a convolution-based encoder, a Transformer-based encoder, a feature fusion decoder, and a deep supervision module. The convolutional structure encoder can extract fine spatial contextual details in images. Meanwhile, the Transformer structure encoder is designed using a hierarchical Swin Transformer architecture to model global contextual information. The novel feature fusion decoder integrates the multi-scale representation from two encoders and selects features that focus on segmentation tasks by channel attention mechanism. Further, a deep supervision module is used to accelerate the convergence of the proposed method. Extensive experiments demonstrate that, compared to the other seven models, the proposed method achieves state-of-the-art results on four segmentation tasks: skin lesion segmentation, polyp segmentation, Covid-19 lesion segmentation, and MRI cardiac segmentation. [ABSTRACT FROM AUTHOR]

Background: IgG4-related disease is a fibro-inflammatory disorder with an unknown etiology, which can affect multiple organ systems, including the cardiovascular system. While most reported cases of cardiovascular involvement are primarily associated with the aorta, there have been sporadic reports of isolated cardiac involvement. Case presentation: This paper presents a documented case of IgG4-related systemic disease with symptoms indicative of restrictive cardiomyopathy. Subsequent Cardiac Magnetic Resonance imaging revealed diffuse myopericardial involvement, characterized by pericardial thickening and enhancement, accompanied by subepicardial and myocardial infiltration. Considering the rarity of cardiac involvement in our case, we conducted a thorough review of the existing literature pertaining to various patterns of cardiac involvement in IgG4-related disease, as well as the diagnostic modalities that can be employed for accurate identification and assessment. Conclusions: This case report sheds light on the importance of recognizing and evaluating cardiac manifestations in IgG4-related systemic disease to facilitate timely diagnosis and appropriate management. [ABSTRACT FROM AUTHOR]

There is currently no clear consensus on screening techniques to evaluate the presence or severity of Fontan-associated liver disease (FALD). Cardiac MRI (CMR) is used routinely for post-Fontan surveillance, but CMR-derived measures that relate to the severity of FALD are not yet defined. This was a cross-sectional single-center study of post-Fontan patients who underwent a CMR. CMR exams were re-analyzed by a single pediatric cardiologist. Surrogates of FALD included Gamma-Glutamyl Transferase (GGT), Fibrosis-4 laboratory score (FIB-4), and imaging findings. Findings consistent with cirrhosis on liver ultrasound included increased liver echogenicity and/or nodularity. Statistical analyses were performed to investigate potential relationships between CMR parameters and markers of FALD. Sixty-one patients were included. A larger inferior vena cava cross-sectional area (IVC-CSA) indexed to height was significantly associated with a higher FIB-4 score (Spearman's ρ = 0.28, p = 0.04), a higher GGT level (Spearman's ρ = 0.40, p = 0.02), and findings consistent with cirrhosis on liver ultrasound (OR 1.17, 95% CI: (1.01, 1.35), p = 0.04). None of the other CMR parameters were associated with markers of FALD. A larger indexed IVC-CSA was associated with higher systemic ventricle end-diastolic pressure (EDP) on cardiac catheterization (Spearman's ρ = 0.39, p = 0.018) as well as older age (Spearman's ρ = 0.46, p = < 0.001). Indexed IVC-CSA was the only CMR parameter that was associated with markers of FALD. This measure has the potential to serve as an additional non-invasive tool to improve screening strategies for FALD. Visual abstract summarizing the primary findings of this paper [ABSTRACT FROM AUTHOR]

Lipomatous hypertrophy of the interatrial septum (LHIAS) represents a benign proliferation of lipoid cells at the level of the interatrial septum (IAS) inducing an important thickening of this structure. It respects the fossa ovalis (FO) region, having a typical "hourglass" echocardiographic appearance. There are certain cases though, with unusual appearances and/or with associated pathologies that may induce similar lesions in the heart, in which the differential diagnosis cannot be guaranteed using only the standard methods. The final diagnosis has important implications in these patients' treatment plan. In this paper, we present an unusual case of a female patient undergoing chemotherapy for lung carcinoma, suspected of right atrial thrombosis/metastasis. As the diagnosis was unclear after transthoracic echocardiography (TTE), inducing the suspicion of an IAS mass with atrial wall infiltration, bi- and tridimensional transesophageal echocardiography (TOE) was performed, revealing a severely and homogenously hypertrophied IAS respecting the FO, but lacking a clear visualization of the atrial wall. The diagnosis of LHIAS was established by cardiac magnetic resonance (CMR) that certified the adipose nature of the structure, excluding the need for invasive investigations and/or treatment options. Multimodality imaging is very important for the clinician in adopting the best management plan for each individual patient. [ABSTRACT FROM AUTHOR]

Cardiovascular diseases (CVDs) are considered one of the leading causes of death worldwide. Myocardial infarction (MI) is one of the deadliest cardiac diseases that require more consideration. Recently, cardiac magnetic resonance imaging (MRI) has been applied as a standard technique for assessing such diseases. The segmentation of the left ventricle (LV) and myocardium from MRI images is vital in detecting MI disease at its early stages. The automatic segmentation of LV is still challenging due to the complex structures of MRI images, inhomogeneous LV shape and moving organs around the LV, such as the lungs and diaphragm. Thus, this study proposed a convolutional neural network (CNN) model for LV and myocardium segmentation to detect MI. The layers selection and hyper-parameters fine-tuning were applied before the training phase. The model showed robust performance based on the evaluation metrics such as accuracy, sensitivity, specificity, dice score coefficient (DSC), Jaccard index and intersection over union (IOU) with values of 0.86, 0.91, 0.84, 0.81, 0.69 and 0.83, respectively. [ABSTRACT FROM AUTHOR]

As a regular tool for assessing and diagnosing cardiovascular disease (CVD), medical professionals and health care centers, are highly dependent on cardiac imaging. The purpose of dividing the cardiac images is to paint the inner and outer walls of the heart to divide all or part of the limb's boundaries. In order to enhance cardiologist in the process of cardiac segmentation, new and accurate methods are needed to divide the selected object, which is the left ventricle (LV). Segmentation techniques aim to provide a fast segmentation process and improve the reliability of the process. In this paper, a comparative study is made on basic random walk (BRW), extended random walk with priors (ERW), and high-speed random walk (HSRW) techniques. In the presented paper, we have applied three different types of medical image segmentation techniques to many Cardiovascular Magnetic Resonance images (CMRIs) in our experimental evaluation to lead statistically significant conclusion and confirm that our results are generalized. We have used 125 sets of CMRIs generated from five groups of patients with different types of cardiovascular disease to get the precise capacity of the productivity of the introduced method. In this paper, several performance metrics are used for instance correspondence coefficient D, distance, and PSNR. In the presented paper, a short-axis 3D multilayer CMRIs database has been taken and applied on many case studies to decide the outcomes of several segmentation methods. Throughout the experiments, the performance time for three segmentation methods are also calculated and utilized in the comparison process as another important performance factor. The experimental results show that ERW technique is the furthermost accurate segmentation technique among all the approaches. [ABSTRACT FROM AUTHOR]

A method of determining the optimal kernel size for filtering noise in vortex dominated flow-fields, as found in the cardiac chambers is presented in this paper. Using synthetic flow fields generated using harmonic functions and perturbed using Gaussian noises of different amplitudes and spreads, the effect of kernel size on noise removal using the Median filter is tested systematically. It is shown that there exists an optimal kernel size at which the Median filter works best. The size of the optimal kernel is shown to be related to the vortex size. When applied to MRI generated cardiac flow-fields, the approach is seen to reveal underlying vortex patterns thereby aiding as an effective tool in the diagnosis and prognosis of cardiac diseases based on vortices as clinical biomarkers. The behavior of the restored cardiac flow fields which are filtered with the optimal kernel size and also with some values preceding and succeeding it are similar to that observed in studies with synthetic flow fields. This confirms that the optimal size of the kernel is related to the cardiac vortex size as is observed in the case of synthetic flow fields. [ABSTRACT FROM AUTHOR]

Advanced heart failure (AHF) presents a complex landscape with challenges spanning diagnosis, management, and patient outcomes. In response, the integration of multimodality imaging techniques has emerged as a pivotal approach. This comprehensive review delves into the profound significance of these imaging strategies within AHF scenarios. Multimodality imaging, encompassing echocardiography, cardiac magnetic resonance imaging (CMR), nuclear imaging and cardiac computed tomography (CCT), stands as a cornerstone in the care of patients with both short- and long-term mechanical support devices. These techniques facilitate precise device selection, placement, and vigilant monitoring, ensuring patient safety and optimal device functionality. In the context of orthotopic cardiac transplant (OTC), the role of multimodality imaging remains indispensable. Echocardiography offers invaluable insights into allograft function and potential complications. Advanced methods, like speckle tracking echocardiography (STE), empower the detection of acute cell rejection. Nuclear imaging, CMR and CCT further enhance diagnostic precision, especially concerning allograft rejection and cardiac allograft vasculopathy. This comprehensive imaging approach goes beyond diagnosis, shaping treatment strategies and risk assessment. By harmonizing diverse imaging modalities, clinicians gain a panoramic understanding of each patient's unique condition, facilitating well-informed decisions. The aim is to highlight the novelty and unique aspects of recently published papers in the field. Thus, this review underscores the irreplaceable role of multimodality imaging in elevating patient outcomes, refining treatment precision, and propelling advancements in the evolving landscape of advanced heart failure management. [ABSTRACT FROM AUTHOR]

The field of prenatal cardiac imaging has revolutionized the way we understand and manage congenital heart diseases (CHD) in the developing fetus. In the prenatal period, cardiac imaging plays a pivotal role in the diagnostic pathway, from screening to classification and follow-up of CHD. The ability to visualize the fetal heart in utero allows healthcare professionals to detect abnormalities early, thus enabling timely interventions and informed decision-making processes for both the mother and the medical team. Early CHD detection improves preparation for delivery, postnatal care, and postnatal outcomes. Advancements in medical technology and imaging techniques have provided clinicians with insights into the fascinating workings of the fetal heart. Several imaging modalities have proven to be helpful in this field, with echocardiography undoubtedly representing the primary modality for evaluating the fetus. By providing detailed anatomical and functional information, fetal cardiac magnetic resonance (CMR) imaging contributes to better prenatal counseling and enhances the coordination of care between obstetricians, maternal–fetal medicine specialists, and pediatric cardiologists. Shortcomings of fetal CMR are due to technical concerns related to the intrauterine position of the fetus and subsequent challenges to following a standard scan protocol. The aim of this paper was to revise the current state-of-the-art in the field of fetal CMR and its clinical applications and to delve into methods, challenges, and future directions of fetal CMR in prenatal imaging. [ABSTRACT FROM AUTHOR]

Although implantable cardioverter defibrillators offer the best protection against sudden cardiac death, catheter ablation for ventricular arrhythmias (VAs) can modify or prevent this event from occurring. In order to achieve a successful ablation, the correct identification of the underlying arrhythmogenic substrate is mandatory to tailor the pre-procedural planning of an ablative procedure as appropriately as possible. We propose that several of the imaging modalities currently used could be merged, including echocardiography (also intracardiac), cardiac magnetic resonance, cardiac computed tomography, nuclear techniques, and electroanatomic mapping. The aim of this state-of-the-art review is to present the value of each modality, that is, its benefits and limitations, in the assessment of arrhythmogenic substrate. Moreover, VAs can be also idiopathic, and in this paper we will underline the role of these techniques in facilitating the ablative procedure. Finally, a hands-on workflow for approaching such a VA and future perspectives will be presented. [ABSTRACT FROM AUTHOR]

Copyright of Revista Foco (Interdisciplinary Studies Journal) is the property of Revista Foco and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Background: Golden angle (GA) radial trajectory is advantageous for dynamic magnetic resonance imaging (MRI). Recently, several advanced algorithms have been developed based on navigator‐interleaved GA trajectory to realize free‐running cardiac MRI. However, navigator‐interleaved GA trajectory suffers from the eddy‐current effect, which reduces the image quality. Purpose: This work aims to integrate the navigator‐interleaved GA trajectory with clinical cardiac MRI acquisition, with the minimum eddy‐current artifacts. The ultimate goal is to realize a high‐quality free‐running cardiac imaging technique. Methods: In this paper, we propose a new "swing golden angle" (swingGA) radial profile order. SwingGA samples the k‐space by rotating back and forth at the generalized golden ratio interval, with smoothly interleaved navigator readouts. The sampling efficiency and angle increment distributions were investigated by numerical simulations. Static phantom imaging experiments were conducted to evaluate the eddy current effect, compared with cartesian, golden angle radial (GA), and tiny golden angle (tGA) trajectories. Furthermore, 12 heart‐healthy subjects (aged 21–25 years) were recruited for free‐running cardiac imaging with different sampling trajectories. Dynamic images were reconstructed by a low‐rank subspace‐constrained algorithm. The image quality was evaluated by signal‐to‐noise‐ratio and spectrum analysis in the heart region, and compared with traditional clinical cardiac MRI images. Results: SwingGA pattern achieves the highest sampling efficiency (mSE > 0.925) and the minimum azimuthal angle increment (mAD < 1.05). SwingGA can effectively suppress eddy currents in static phantom images, with the lowest normalized root mean square error (nRMSE) values among radial trajectories. For the in‐vivo cardiac images, swingGA enjoys the highest SNR both in the blood pool and myocardium, and contains the minimum level of high‐frequency artifacts. The free‐running cardiac images have good consistency with traditional clinical cardiac MRI, and the swingGA sampling pattern achieves the best image quality among all sampling patterns. Conclusions: The proposed swingGA sampling pattern can effectively improve the sampling efficiency and reduce the eddy currents for the navigator‐interleaved GA sequence. SwingGA is a promising sampling pattern for free‐running cardiac MRI. [ABSTRACT FROM AUTHOR]

Cancer therapies have revolutionized patient survival rates, yet they come with the risk of cardiotoxicity, necessitating effective monitoring and management. The existing guidelines offer a limited empirical basis for practical approaches in various clinical scenarios. This article explores the intricate relationship between cancer therapy and the cardiovascular system, highlighting the role of advanced multimodality imaging in monitoring patients before, during, and after cancer treatment. This review outlines the cardiovascular effects of different cancer therapy classes, offering a comprehensive understanding of their dose- and time-dependent impacts. This paper delves into diverse imaging modalities such as echocardiography, cardiac magnetic resonance imaging, cardiac computed tomography, and nuclear imaging, detailing their strengths and limitations in various conditions due to cancer treatment, such as cardiac dysfunction, myocarditis, coronary artery disease, Takotsubo cardiomyopathy, pulmonary hypertension, arterial hypertension, valvular heart diseases, and heart failure with preserved ejection fraction. Moreover, it underscores the significance of long-term follow-up for cancer survivors and discusses future directions. [ABSTRACT FROM AUTHOR]

An increasing and aging patient population poses a growing burden on healthcare professionals. Automation of medical imaging diagnostics holds promise for enhancing patient care and reducing manpower required to accommodate an increasing patient-population. Deep learning, a subset of machine learning, has the potential to facilitate automated diagnostics, but commonly requires large-scaled labeled datasets. In medical domains, data is often abundant but labeling is a laborious and costly task. Active learning provides a method to optimize the selection of unlabeled samples that are most suitable for improvement of the model and incorporate them into the model training process. This approach proves beneficial when only a small number of labeled samples are available. Various selection methods currently exist, but most of them employ fixed querying schedules. There is limited research on how the timing of a query can impact performance in relation to the number of queried samples. This paper proposes a novel approach called dynamic querying, which aims to optimize the timing of queries to enhance model development while utilizing as few labeled images as possible. The performance of the proposed model is compared to a model trained utilizing a fully-supervised training method, and its effectiveness is assessed based on dataset size requirements and loss rates. Dynamic querying demonstrates a considerably faster learning curve in relation to the number of labeled samples used, achieving an accuracy of 70% using only 24 samples, compared to 82% for a fully-supervised model trained on the complete training dataset of 1017 images. [ABSTRACT FROM AUTHOR]

Many variables obtained during cardiopulmonary exercise test (CPET), including O2 uptake (VO2) versus heart rate (HR, O2-pulse) and work rate (VO2/Watt), provide quantitative patterns of responses to exercise when left ventricular dysfunction is an effect of myocardial ischemia (MI). Therefore, CPET offers a unique approach to evaluate exercise-induced MI in the presence of fixed or dynamic coronary arteries stenosis. In this paper, we examined the case of a 74-year-old patient presenting with an ischemic CPET and a normal stress cardiac magnetic resonance (CMR) with dipyridamole. A coronary angiography demonstrated the presence of myocardial bridging (MB), a well-known congenital coronary anomaly that is able to generate MI during exercise (but not in provocative testing using coronary artery vasodilators, such as dipyridamole). Despite the good diagnostic accuracy of the imaging methods (i.e., stress CMR) in MI detection, this case shows that exercise should be the method of choice in elicit ischemia in specific cases, like MB. [ABSTRACT FROM AUTHOR]

This paper presents a novel hybrid approach for the computational modeling of cardiac perfusion, combining a discrete model of the coronary arterial tree with a continuous porous-media flow model of the myocardium. The constructive constrained optimization (CCO) algorithm captures the detailed topology and geometry of the coronary arterial tree network, while Poiseuille's law governs blood flow within this network. Contrast agent dynamics, crucial for cardiac MRI perfusion assessment, are modeled using reaction–advection–diffusion equations within the porous-media framework. The model incorporates fibrosis–contrast agent interactions and considers contrast agent recirculation to simulate myocardial infarction and Gadolinium-based late-enhancement MRI findings. Numerical experiments simulate various scenarios, including normal perfusion, endocardial ischemia resulting from stenosis, and myocardial infarction. The results demonstrate the model's efficacy in establishing the relationship between blood flow and stenosis in the coronary arterial tree and contrast agent dynamics and perfusion in the myocardial tissue. The hybrid model enables the integration of information from two different exams: computational fractional flow reserve (cFFR) measurements of the heart coronaries obtained from CT scans and heart perfusion and anatomy derived from MRI scans. The cFFR data can be integrated with the discrete arterial tree, while cardiac perfusion MRI data can be incorporated into the continuum part of the model. This integration enhances clinical understanding and treatment strategies for managing cardiovascular disease. [ABSTRACT FROM AUTHOR]

Background: Recent advances in hardware and software permit the use of cardiac MRI of late gestation fetuses, however there is a paucity of MRI‐based reference values. Purpose: To provide initial data on fetal cardiac MRI‐derived cardiac dimensions, volumes, ventricular function, and left ventricular longitudinal strain in healthy developing fetuses >30 weeks gestational age. Study Type: Prospective. Population: Twenty‐five third trimester (34 ± 1 weeks, range of 32–37 weeks gestation) women with healthy developing fetuses. Field Strength/Sequence: Studies were performed at 1.5 T and 3 T. Cardiac synchronization was achieved with a Doppler ultrasound device. The protocol included T2 single shot turbo spin echo stacks for fetal weight and ultrasound probe positioning, and multiplanar multi‐slice cine balanced steady state free precession gradient echo sequences. Assessment: Primary analyses were performed by a single observer. Weight indexed right ventricular (RV) and left ventricular (LV) volumes and function were calculated from short axis (SAX) stacks. Cardiac dimensions were calculated from the four‐chamber and SAX stacks. Single plane LV longitudinal strain was calculated from the four‐chamber stack. Interobserver variability was assessed in 10 participants. Cardiac MRI values were compared against available published normative fetal echocardiogram data using z‐scores. Statistical Tests: Mean and SDs were calculated for baseline maternal/fetal demographics, cardiac dimensions, volumes, ventricular function, and left ventricular longitudinal strain. Bland–Altman and intraclass correlation coefficient analysis was performed to test interobserver variability. Results: The mean gestational age was 34 ± 1.4 weeks. The mean RV and LV end diastolic volumes were 3.1 ± 0.6 mL/kg and 2.4 ± 0.5 mL/kg respectively. The mean RV cardiac output was 198 ± 49 mL/min/kg while the mean LV cardiac output was 173 ± 43 mL/min/kg. Data Conclusion: This paper reports initial reference values obtained by cardiac MRI in healthy developing third trimester fetuses. MRI generally resulted in slightly larger indexed values (by z‐score) compared to reports in literature using fetal echocardiography. Evidence level: 1 Technical Efficacy: Stage 2 [ABSTRACT FROM AUTHOR]

Vortical blood flow structures inside the heart's left ventricle (LV) play a crucial role in an efficient blood supply from the heart to organs. Recent medical imaging and computational technology progress have brought us blood flow visualization tools in echocardiography and cardiac MRI. However, there are still few tools to precisely capture the vortical flow structures since the flow is highly unsteady and turbulent. Because of the importance of vortex flow power force on the prognosis of cardiac functions in heart diseases, identifying the vortex flow structure without ambiguity is essential in medical science. In this paper, we propose a mathematical method to describe the topological features of two-dimensional (2D) flows with symbolic graph expressions, called COT representations. Since the heart contracts and relaxes repeatedly in a short time range, the instantaneous blood flow pattern along this moving boundary would appear as a source/sink structure. This means that the flow does not satisfy the slip-boundary condition that is assumed in the preceding topological classification theory for 2D flows [T. Sakajo and T. Yokoyama, IMA J. Appl. Math., 83 (2018), pp. 380--411], [T. Sakajo and Y. Yokoyama, Discrete Math. Algorithms Appl., 15 (2023), 2250143]. We thus establish a new topological classification theory and an algorithm suitable for blood flow with the moving boundary condition by introducing a degenerate singular point named n-bundled ss-saddle. Applying the theory to 2D blood flow patterns obtained by the visualization tools, we successfully identify vortical flow structures as topological vortex structures. This realizes a new image processing characterizing healthy blood flow patterns as well as inefficient patterns in diseased hearts. [ABSTRACT FROM AUTHOR]

Diabetes mellitus (DM) is a new epidemic which has presented an immense increase in recent decades, due to the rapid increase in obesity. Cardiovascular disease (CVD) significantly reduces life expectancy and is the main cause of death in type 2 diabetes mellitus (T2DM). Strict glycemic control is a well-established method to combat microvascular CVD of type 1 diabetes mellitus (T1DM); its role against CVD of the T2DM risk has not been well documented. Therefore, the most efficient prevention is multifactorial risk factor reduction. Recently, the European Society of Cardiology published its 2019 recommendations on CVD in DM. Although all clinical points were discussed in this document, only a few comments were presented about when and how we should recommend cardiovascular (CV) imaging. Currently, CV imaging is the "must" in CV noninvasive evaluation. Alterations in CV imaging parameters can lead to early recognition of various types of CVD. In this paper, we briefly discuss the role of noninvasive imaging modalities, emphasizing the benefits of including cardiovascular magnetic resonance (CMR) in the evaluation of DM. CMR, in the same examination, can provide an assessment of tissue characterization, perfusion and function, with excellent reproducibility and without radiation or limitations, due to the body habitus. Therefore, it can play a dominant role in the prevention and risk stratification of DM. The suggested protocol for DM evaluation should include routine annual echocardiographic evaluation of all DM patients and CMR assessment of those with poorly controlled DM, microalbuminuria, heart failure, arrhythmia and recent alterations in clinical or echocardiographic evaluation. [ABSTRACT FROM AUTHOR]

Simple Summary: Brugada syndrome (BrS) has always been considered a purely electrical disease and imaging techniques do not currently play a specific role in the diagnosis of this arrhythmic syndrome. The aim of this review is to identify possible structural abnormalities of BrS and their potential association with symptoms, risk stratification, and prognosis. The aim of this review is to identify possible structural abnormalities of BrS and their potential association with symptoms, risk stratification, and prognosis. (1) Background: BrS has always been considered a purely electrical disease and imaging techniques do not currently play a specific role in the diagnosis of this arrhythmic syndrome. Some authors have recently hypothesized the presence of structural and functional abnormalities. Therefore, several studies investigated the presence of pathological features in echocardiography and cardiac magnetic resonance imaging (MRI) in patients with BrS, but results were controversial. (2) Methods: We performed a systematic review of the literature on the spectrum of features detected by echocardiography and cardiac MRI. Articles were searched in Pubmed, Cochrane Library, and Biomed Central. Only papers published in English and in peer-reviewed journals up to November 2021 were selected. After an initial evaluation, 596 records were screened; the literature search identified 19 relevant articles. (3) Results: The imaging findings associated with BrS were as follows: right ventricular dilation, right ventricular wall motion abnormalities, delayed right ventricular contraction, speckle and feature tracking abnormalities, late gadolinium enhancement, and fat infiltration in the right ventricle. Furthermore, these features emerged more frequently in patients carrying the genetic mutation on the sodium voltage-gated channel α-subunit 5 (SCN5A) gene. (4) Conclusions: Specific imaging features detected by echocardiography and cardiac magnetic resonance are associated with BrS. However, this population appears to be heterogeneous and imaging anomalies emerged to be more frequent in patients carrying genetic mutations of SCN5A. Future studies with an evaluation of BrS patients are needed to identify the specific association linking the Brugada pattern, imaging abnormalities and their possible correlation with prognosis. [ABSTRACT FROM AUTHOR]

Left Ventricle (LV) detection from Cardiac Magnetic Resonance (CMR) imaging is a fundamental step, preliminary to myocardium segmentation and characterization. This paper focuses on the application of a Visual Transformer (ViT), a novel neural network architecture, to automatically detect LV from CMR relaxometry sequences. We implemented an object detector based on the ViT model to identify LV from CMR multi-echo T2* sequences. We evaluated performances differentiated by slice location according to the American Heart Association model using 5-fold cross-validation and on an independent dataset of CMR T2*, T2, and T1 acquisitions. To the best of our knowledge, this is the first attempt to localize LV from relaxometry sequences and the first application of ViT for LV detection. We collected an Intersection over Union ( I o U ) index of 0.68 and a Correct Identification Rate ( C I R ) of blood pool centroid of 0.99, comparable with other state-of-the-art methods.  I o U  and  C I R  values were significantly lower in apical slices. No significant differences in performances were assessed on independent T2* dataset ( I o U  = 0.68, p = 0.405;  C I R  = 0.94, p = 0.066). Performances were significantly worse on the T2 and T1 independent datasets (T2:  I o U  = 0.62,  C I R  = 0.95; T1:  I o U  = 0.67,  C I R  = 0.98), but still encouraging considering the different types of acquisition. This study confirms the feasibility of the application of ViT architectures in LV detection and defines a benchmark for relaxometry imaging. [ABSTRACT FROM AUTHOR]

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

In sub-Saharan Africa, idiopathic dilated cardiomyopathy (IDCM) is a common yet poorly investigated cause of heart failure. Cardiovascular magnetic resonance (CMR) imaging is the gold standard for tissue characterisation and volumetric quantification. In this paper, we present CMR findings obtained from a cohort of patients with IDCM in Southern Africa suspected of having a genetic cause of cardiomyopathy. A total of 78 IDCM study participants were referred for CMR imaging. The participants had a median left ventricular ejection fraction of 24% [interquartile range, (IQR): 18–34]. Late gadolinium enhancement (LGE) was visualised in 43 (55.1%) participants and localised in the midwall in 28 (65.0%) participants. At the time of enrolment into the study, non-survivors had a higher median left ventricular end diastolic wall mass index of 89.4 g/m2 (IQR: 74.5–100.6) vs. 73.6 g/m2 (IQR: 51.9–84.7), p = 0.025 and a higher median right ventricular end-systolic volume index of 86 mL/m2 (IQR:74–105) vs. 41 mL/m2 (IQR: 30–71), p < 0.001. After one year, 14 participants (17.9%) died. The hazard ratio for the risk of death in patients with evidence of LGE from CMR imaging was 0.435 (95% CI: 0.259–0.731; p = 0.002). Midwall enhancement was the most common pattern, visualised in 65% of participants. Prospective, adequately powered, and multi-centre studies across sub-Saharan Africa are required to determine the prognostic significance of CMR imaging parameters such as late gadolinium enhancement, extracellular volume fraction, and strain patterns in an African IDCM cohort. [ABSTRACT FROM AUTHOR]

Background: Cushing's Syndrome (CS) is associated with increased cardiovascular morbidity and mortality. In endogenous CS, cardiovascular mortality remains increased for up to 15 years post remission of hypercortisolism. Similarly, patients with exogenous CS have 4-fold increased incidence of cardiovascular events, regardless of pre-existing cardiovascular disease (CVD). Objective: To present the pathophysiology, prognosis, clinical and imaging phenotype of cardiac disease in CS. Methods: A Pubmed search for cardiac disease in CS over the last 20 years was conducted using combinations of relevant terms. Preclinical and clinical studies, as well as review papers reporting on subclinical heart failure (HF), cardiomyopathy, coronary heart disease (CHD), and cardiovascular imaging were selected. Results: Cardiac disease in CS is associated with direct mineralocorticoid and glucocorticoid receptor activation, increased responsiveness to angiotensin II, ectopic epicardial adiposity, arterial stiffness and endothelial dysfunction, as well as with diabetes mellitus, hypertension, hyperlipidemia, obesity and prothrombotic diathesis. Subclinical HF and cardiomyopathy are principally related to direct glucocorticoid (GC) effects and markedly improve or regress post hypercortisolism remission. In contrast, CHD is related to both direct GC effects and CS comorbidities and persists post cure. In patients without clinical evidence of CVD, echocardiography and cardiac magnetic resonance (CMR) imaging reveal left ventricular hypertrophy, fibrosis, diastolic and systolic dysfunction, with the latter being underestimated by echocardiography. Finally, coronary microvascular disease is encountered in one third of cases. Conclusion: Cardiovascular imaging is crucial in evaluation of cardiac involvement in CS. CMR superiority in terms of reproducibility, operator independency, unrestricted field of view and capability of tissue characterisation makes this modality ideal for future studies. [ABSTRACT FROM AUTHOR]

Cardiac magnetic resonance imaging (MRI) segmentation task refers to the accurate segmentation of ventricle and myocardium, which is a prerequisite for evaluating the soundness of cardiac function. With the development of deep learning in medical imaging, more and more heart segmentation methods based on deep learning have been proposed. Due to the fuzzy boundary and uneven intensity distribution of cardiac MRI, some existing methods do not make full use of multi-scale characteristic information and have the problem of ambiguity between classes. In this paper, we propose a dilated convolution network with edge fusion block and directional feature maps for cardiac MRI segmentation. The network uses feature fusion module to preserve boundary information, and adopts the direction field module to obtain the feature maps to improve the original segmentation features. Firstly, multi-scale feature information is obtained and fused through dilated convolutional layers of different scales while downsampling. Secondly, in the decoding stage, the edge fusion block integrates the edge features into the side output of the encoder and concatenates them with the upsampled features. Finally, the concatenated features utilize the direction field to improve the original segmentation features and generate the final result. Our propose method conducts comprehensive comparative experiments on the automated cardiac diagnosis challenge (ACDC) and myocardial pathological segmentation (MyoPS) datasets. The results show that the proposed cardiac MRI segmentation method has better performance compared to other existing methods. [ABSTRACT FROM AUTHOR]

Learning good data representations for medical imaging tasks ensures the preservation of relevant information and the removal of irrelevant information from the data to improve the interpretability of the learned features. In this paper, we propose a semi-supervised model—namely, combine-all in semi-supervised learning (CqSL)—to demonstrate the power of a simple combination of a disentanglement block, variational autoencoder (VAE), generative adversarial network (GAN), and a conditioning layer-based reconstructor for performing two important tasks in medical imaging: segmentation and reconstruction. Our work is motivated by the recent progress in image segmentation using semi-supervised learning (SSL), which has shown good results with limited labeled data and large amounts of unlabeled data. A disentanglement block decomposes an input image into a domain-invariant spatial factor and a domain-specific non-spatial factor. We assume that medical images acquired using multiple scanners (different domain information) share a common spatial space but differ in non-spatial space (intensities, contrast, etc.). Hence, we utilize our spatial information to generate segmentation masks from unlabeled datasets using a generative adversarial network (GAN). Finally, to reconstruct the original image, our conditioning layer-based reconstruction block recombines spatial information with random non-spatial information sampled from the generative models. Our ablation study demonstrates the benefits of disentanglement in holding domain-invariant (spatial) as well as domain-specific (non-spatial) information with high accuracy. We further apply a structured L 2 similarity (S L 2 SIM) loss along with a mutual information minimizer (MIM) to improve the adversarially trained generative models for better reconstruction. Experimental results achieved on the STACOM 2017 ACDC cine cardiac magnetic resonance (MR) dataset suggest that our proposed (CqSL) model outperforms fully supervised and semi-supervised models, achieving an 83.2% performance accuracy even when using only 1% labeled data. We hypothesize that our proposed model has the potential to become an efficient semantic segmentation tool that may be used for domain adaptation in data-limited medical imaging scenarios, where annotations are expensive. Code, and experimental configurations will be made available publicly. [ABSTRACT FROM AUTHOR]

Introduction: Utilization of cardiac magnetic resonance imaging (CMRI) has been increasing year by year for the most cardiovascular diseases. In this paper, we documented a real-life experience of our center as a high-volume CMRI performing center. Methods: We have retrospectively analyzed the 100 patients who have undergone CMRI at our center during the last 1 year. All the preliminary diagnoses, specialty or subspecialty of referring physicians, patient characteristics and CMRI findings were analyzed. Results: In 87 of 100 scans, a gadolinium-based contrast agent was used and in none of these procedures neither complications nor adverse events related to the contrast agent has occurred. Among these 100 consecutive CMRIs were referred to by a clinical cardiologist, invasive cardiologists, heart failure specialist, cardiovascular imaging specialists, electrophysiologists, and other specialists. On referral from a clinical cardiologist, the CMRI findings were high consistency. In these patients, the biggest number of preliminary diagnoses belongs to hypertrophic cardiomyopathy. The most common MRI finding was reduced left ventricular ejection fraction. In 25 patients we observed extracardiac findings. Conclusion: CMRI is increasingly occurring in cardiovascular imaging and diagnosis of various cardiovascular diseases. CMRI not only produces high-resolution morphological images but also provides quantitative information on the severity of regurgitant or stenotic lesions in valvular diseases or cardiac shunts with the velocity and flow measurements. [ABSTRACT FROM AUTHOR]

Copyright of Die Radiologie is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Die Radiologie is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Cardiac Magnetic Resonance (CMR) is widely used in diagnosing cardiac diseases for its excellent contrast of cardiovascular features. However, due to the long imaging time of CMR scanning, the patient's respiration, limb shaking, and heart beating will lead to a certain degree of motion artifacts in the image, seriously degrade the image quality and affect the doctor's clinical judgment. This paper proposes a superpixel conditional Generative Adversarial Network (spcGAN) based on a conditional Generative Adversarial Network (cGAN) by applying superpixel to both generator and discriminator parts. In the generator section, a generator network based on superpixel segmentation and pooling is proposed for feature extraction at the superpixel level to enhance the reconstruction of image edge texture and structural details. In the discriminator part, superpixel pooling is used to construct a superpixel discriminator. It is fused with the traditional convolutional discriminator to produce a superpixel-based dual discriminator, which makes the discriminator consider the image's local structure and details. Based on the generator and discriminator structure proposed in this paper, superpixel pooling and edge texturing loss functions are designed for optimization. Adequate ablation experiments and comparison experiments are conducted in terms of experimental results. Three types of objective metrics, Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM), and Focus Measurement (Tenengrad), were selected as references. The experimental results show that the effect of removing motion artifacts from authentic CMR images on the three datasets is most significant in the dataset produced in this paper. The results obtained from the fusion between the designed generator, discriminator, and loss function are the most obvious. Compared with the existing methods, the spcGAN proposed in this paper performs better. • Applying superpixels to CMR artifact removal networks. • Proposing Generator Networks Based on Superpixel Segmentation and Pooling. • Constructing Superpixel Discriminator and combine them with Regular Discriminator. • Designing loss functions for superpixel pooling and edge texture optimization. [ABSTRACT FROM AUTHOR]

The automatic segmentation of cardiac magnetic resonance (MR) images is the basis for the diagnosis of cardiac-related diseases. However, the segmentation of cardiac MR images is a challenging task due to the inhomogeneity of MR images intensity distribution and the unclear boundaries between adjacent tissues. In this paper, we propose a novel multiresolution mutual assistance network (MMA-Net) for cardiac MR images segmentation. It is mainly composed of multibranch input module, multiresolution mutual assistance module, and multilabel deep supervision. First, the multibranch input module helps the network to extract local and global features more pertinently. Then, the multiresolution mutual assistance module implements multiresolution feature interaction and progressively improves semantic features to more completely express the information of the tissue. Finally, the multilabel deep supervision is proposed to generate the final segmentation map. We compare with state-of-the-art medical image segmentation methods on the medical image computing and computer-assisted intervention (MICCAI) automated cardiac diagnosis challenge datasets and the MICCAI atrial segmentation challenge datasets. The mean dice scores of our method in the left atrium, right ventricle, myocardium, and left ventricle are 0.919, 0.920, 0.881, and 0.960, respectively. The analysis of evaluation indicators and segmentation results shows that our method achieves the best performance in cardiac magnetic resonance images segmentation. [ABSTRACT FROM AUTHOR]