Search

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]

Introduction: Assessment of left ventricular ejection fraction (LVEF) is one of the primary objectives of echocardiography. The gold standard assessment technique in emergency medicine is eyeballing. A new tool is now available on pocket ultrasound devices (PUD): automatic LVEF. The primary aim of this study was to evaluate the concordance between LVEF values estimated by automatic LVEF with PUD and by cardiac magnetic resonance imaging (MRI). Materials: This was a prospective, monocentric, and observational study. All adult patients with an indication for cardiac MRI underwent a point-of-care ultrasound. Blinded to the MRI results, the emergency physician assessed LVEF using the automatic PUD tool and by visual evaluation. Results: Sixty patients were included and analyzed. Visual estimation of LVEF was feasible for all patients and automatic evaluation for 52 (87%) patients. Lin's concordance correlation coefficient between automatic ejection fraction with PUD and by cardiac MRI was 0.23 (95% CI, 0.03–0.40). Conclusion: Concordance between LVEF estimated by the automatic ejection fraction with PUD and LVEF estimated by MRI was non-existent. [ABSTRACT FROM AUTHOR]

Computational fluid dynamics (CFD) can be used for non-invasive evaluation of hemodynamics. However, its routine use is limited by labor-intensive manual segmentation, CFD mesh creation, and time-consuming simulation. This study aims to train a deep learning model to both generate patient-specific volume-meshes of the pulmonary artery from 3D cardiac MRI data and directly estimate CFD flow fields. This proof-of-concept study used 135 3D cardiac MRIs from both a public and private dataset. The pulmonary arteries in the MRIs were manually segmented and converted into volume-meshes. CFD simulations were performed on ground truth meshes and interpolated onto point-point correspondent meshes to create the ground truth dataset. The dataset was split 110/10/15 for training, validation, and testing. Image2Flow, a hybrid image and graph convolutional neural network, was trained to transform a pulmonary artery template to patient-specific anatomy and CFD values, taking a specific inlet velocity as an additional input. Image2Flow was evaluated in terms of segmentation, and the accuracy of predicted CFD was assessed using node-wise comparisons. In addition, the ability of Image2Flow to respond to increasing inlet velocities was also evaluated. Image2Flow achieved excellent segmentation accuracy with a median Dice score of 0.91 (IQR: 0.86–0.92). The median node-wise normalized absolute error for pressure and velocity magnitude was 11.75% (IQR: 9.60–15.30%) and 9.90% (IQR: 8.47–11.90), respectively. Image2Flow also showed an expected response to increased inlet velocities with increasing pressure and velocity values. This proof-of-concept study has shown that it is possible to simultaneously perform patient-specific volume-mesh based segmentation and pressure and flow field estimation using Image2Flow. Image2Flow completes segmentation and CFD in ~330ms, which is ~5000 times faster than manual methods, making it more feasible in a clinical environment. Author summary: Computational fluid dynamics is an engineering tool that can be used in a clinical setting to non-invasively model blood flow through blood vessels, such as the pulmonary artery. This information can be used to inform treatment planning for patients, especially those with cardiovascular conditions. However, its routine use is limited by a labor-intensive process, requiring substantial expertise and computational resources. Recently, machine learning has offered solutions to automate parts of this process, but no single model has addressed the entire workflow. Therefore, we created Image2Flow, a machine learning model capable of generating a patient-specific representation of a pulmonary artery while predicting blood flow through the vessel. Image2Flow can generate highly accurate pulmonary artery representations and reasonably accurate blood flow predictions. Notably, it performs this whole process in 330ms, which is ~5000x faster than the manual methods. With its speed and accuracy, Image2Flow holds substantial promise for facilitating computational fluid dynamics in clinical settings. [ABSTRACT FROM AUTHOR]

A similarity-driven multi-dimensional binning algorithm (SIMBA) reconstruction of free-running cardiac magnetic resonance imaging data was previously proposed. While very efficient and fast, the original SIMBA focused only on the reconstruction of a single motion-consistent cluster, discarding the remaining data acquired. However, the redundant data clustered by similarity may be exploited to further improve image quality. In this work, we propose a novel compressed sensing (CS) reconstruction that performs an effective regularization over the clustering dimension, thanks to the integration of inter-cluster motion compensation (XD-MC-SIMBA). This reconstruction was applied to free-running ferumoxytol-enhanced datasets from 24 patients with congenital heart disease, and compared to the original SIMBA, the same XD-MC-SIMBA reconstruction but without motion compensation (XD-SIMBA), and a 5D motion-resolved CS reconstruction using the free-running framework (FRF). The resulting images were compared in terms of lung-liver and blood-myocardium sharpness, blood-myocardium contrast ratio, and visible length and sharpness of the coronary arteries. Moreover, an automated image quality score (IQS) was assigned using a pretrained deep neural network. The lung-liver sharpness and blood-myocardium sharpness were significantly higher in XD-MC-SIMBA and FRF. Consistent with these findings, the IQS analysis revealed that image quality for XD-MC-SIMBA was improved in 18 of 24 cases, compared to SIMBA. We successfully tested the hypothesis that multiple motion-consistent SIMBA clusters can be exploited to improve the quality of ferumoxytol-enhanced cardiac MRI when inter-cluster motion-compensation is integrated as part of a CS reconstruction. [ABSTRACT FROM AUTHOR]

Prediction of major arrhythmic events (MAEs) in dilated cardiomyopathy represents an unmet clinical goal. Computational models and artificial intelligence (AI) are new technological tools that could offer a significant improvement in our ability to predict MAEs. In this proof-of-concept study, we propose a deep learning (DL)-based model, which we termed Deep ARrhythmic Prevention in dilated cardiomyopathy (DARP-D), built using multidimensional cardiac magnetic resonance data (cine videos and hypervideos and LGE images and hyperimages) and clinical covariates, aimed at predicting and tracking an individual patient's risk curve of MAEs (including sudden cardiac death, cardiac arrest due to ventricular fibrillation, sustained ventricular tachycardia lasting ≥30 s or causing haemodynamic collapse in <30 s, appropriate implantable cardiac defibrillator intervention) over time. The model was trained and validated in 70% of a sample of 154 patients with dilated cardiomyopathy and tested in the remaining 30%. DARP-D achieved a 95% CI in Harrell's C concordance indices of 0.12–0.68 on the test set. We demonstrate that our DL approach is feasible and represents a novelty in the field of arrhythmic risk prediction in dilated cardiomyopathy, able to analyze cardiac motion, tissue characteristics, and baseline covariates to predict an individual patient's risk curve of major arrhythmic events. However, the low number of patients, MAEs and epoch of training make the model a promising prototype but not ready for clinical usage. Further research is needed to improve, stabilize and validate the performance of the DARP-D to convert it from an AI experiment to a daily used tool. [ABSTRACT FROM AUTHOR]

Presence of left atrial (LA) fibrosis reflects underlying atrial cardiomyopathy. Interatrial block (IAB) is associated with LA fibrosis in patients with atrial fibrillation (AF). The association of IAB and LA fibrosis in the patients without history of AF is unknown. We examined association of IAB and LA fibrosis in the patients without AF history. This is a retrospective analysis of 229 patients undergoing cardiac magnetic resonance imaging (CMR). LA fibrosis was reported from spatial extent of late gadolinium enhancement of CMR. IAB was measured from 12-lead electrocardiography using digital caliper. Of 229 patients undergoing CMR, prevalence of IAB was 50.2%. Patients with IAB were older (56.9±13.9 years vs. 45.9±19.2 years, p<0.001) and had higher prevalence of co-morbidities. Left ventricular ejection fraction was lower in IAB group. LA volume index (LAVI) was greater in IAB group (54.6±24.9 ml/m2 vs. 43.0±21.1 ml/m2, p<0.001). Patients with IAB had higher prevalence of LA fibrosis than those without IAB (70.4% vs. 21.2%; p<0.001). After multivariable analysis, only IAB and LAVI were independent factors that predict LA fibrosis. Prevalence of IAB in patients undergoing CMR was high. IAB was highly associated with LA fibrosis and larger LA size in patients without AF history. [ABSTRACT FROM AUTHOR]

Background: Limited data exist regarding cardiac manifestations of Chagas disease in migrants living in non-endemic regions. Methods: A retrospective cohort analysis of 109 patients with Chagas disease seen at Boston Medical Center (BMC) between January 2016 and January 2023 was performed. Patients were identified by screening and testing migrants from endemic regions at a community health center and BMC. Demographic, laboratory, and cardiac evaluation data were collected. Results: Mean age of the 109 patients was 43 years (range 19–76); 61% were female. 79% (86/109) were diagnosed with Chagas disease via screening and 21% (23/109) were tested given symptoms or electrocardiogram abnormalities. Common symptoms included palpitations (25%, 27/109) and chest pain (17%, 18/109); 52% (57/109) were asymptomatic. Right bundle branch block (19%, 19/102), T-wave changes (18%, 18/102), and left anterior fascicular block (11%, 11/102) were the most common electrocardiogram abnormalities; 51% (52/102) had normal electrocardiograms. Cardiomyopathy stage was ascertained in 94 of 109 patients: 51% (48/94) were indeterminate stage A and 49% (46/94) had cardiac structural disease (stages B1-D). Clinical findings that required clinical intervention or change in management were found in 23% (25/109), and included cardiomyopathy, apical hypokinesis/aneurysm, stroke, atrial or ventricular arrhythmias, and apical thrombus. Conclusions: These data show high rates of cardiac complications in a cohort of migrants living with Chagas disease in a non-endemic setting. We demonstrate that Chagas disease diagnosis prompts cardiac evaluation which often identifies actionable cardiac disease and provides opportunities for prevention and treatment. Author summary: Chagas cardiomyopathy is a manifestation of end-organ damage from Trypanosoma cruzi parasitic infection. Most infections occur in Mexico, Central and South America but disease is present globally due to migration. Approximately 30% of those with Chagas disease develop cardiomyopathy years after infection from persistent heart muscle and conduction system inflammation, which can be life-threatening. Unfortunately, Chagas disease remains underdiagnosed and identifying those at risk for severe disease remains challenging. The 2018 American Heart Association guidelines recommend ECG and cardiac rhythm strip, but there is no consensus on the approach to further cardiac evaluation in the US or management of Chagas cardiomyopathy. This study retrospectively analyzed symptoms and cardiac examination of migrants predominantly from endemic Central American countries who were diagnosed with Chagas disease and received care at Boston Medical Center. Most patients were asymptomatic and nearly half had evidence of cardiomyopathy. Echocardiogram abnormalities were present in approximately one-third of asymptomatic individuals with normal ECGs. Some individuals had significant abnormalities found on heart rhythm monitors or cardiac magnetic resonance imaging which led to management changes. These findings underscore the importance of routine echocardiograms, consideration of cardiac rhythm monitoring, and thorough cardiac assessment in people with Chagas disease regardless of symptoms. [ABSTRACT FROM AUTHOR]

The acute myocardial infarction (AMI) present high mortality rate that may be reduced with cardiac rehabilitation. Despite its good establishment in outpatient care, few studies analyzed cardiac rehabilitation during hospitalization. Thus, this study aims to clarify the safety and efficacy of early cardiac rehabilitation after AMI. This will be a clinical, controlled, randomized trial with blind outcome evaluation and a superiority hypothesis. Twenty-four patients with AMI will be divided into two groups (1:1 allocation ratio). The intervention group will receive an individualized exercise-based cardiac rehabilitation protocol during hospitalization and a semi-supervised protocol after hospital discharge; the control group will receive conventional care. The primary outcomes will be the cardiac remodeling assessed by cardiac magnetic resonance imaging, functional capacity assessed by maximal oxygen consumption, and cardiac autonomic balance examined via heart rate variability. Secondary outcomes will include safety and the total exercise dose provided during the protocol. Statistical analysis will consider the intent-to-treat analysis. Trial registration. Trial registration number: Brazilian Registry of Clinical Trials (ReBEC) (RBR- 9nyx8hb). [ABSTRACT FROM AUTHOR]