Cardiovascular magnetic resonance images with susceptibility artifacts: artificial intelligence with spatial-attention for ventricular volumes and mass assessment.

BACKGROUND: Segmentation of cardiovascular magnetic resonance (CMR) images is an essential step for evaluating dimensional and functional ventricular parameters as ejection fraction (EF) but may be limited by artifacts, which represent the major challenge to automatically derive clinical information. The aim of this study is to investigate the accuracy of a deep learning (DL) approach for automatic segmentation of cardiac structures from CMR images characterized by magnetic susceptibility artifact in patient with cardiac implanted electronic devices (CIED). METHODS: In this retrospective study, 230 patients (100 with CIED) who underwent clinically indicated CMR were used to developed and test a DL model. A novel convolutional neural network was proposed to extract the left ventricle (LV) and right (RV) ventricle endocardium and LV epicardium. In order to perform a successful segmentation, it is important the network learns to identify salient image regions even during local magnetic field inhomogeneities. The proposed network takes advantage from a spatial attention module to selectively process the most relevant information and focus on the structures of interest. To improve segmentation, especially for images with artifacts, multiple loss functions were minimized in unison. Segmentation results were assessed against manual tracings and commercial CMR analysis software cvi42(Circle Cardiovascular Imaging, Calgary, Alberta, Canada). An external dataset of 56 patients with CIED was used to assess model generalizability. RESULTS: In the internal datasets, on image with artifacts, the median Dice coefficients for end-diastolic LV cavity, LV myocardium and RV cavity, were 0.93, 0.77 and 0.87 and 0.91, 0.82, and 0.83 in end-systole, respectively. The proposed method reached higher segmentation accuracy than commercial software, with performance comparable to expert inter-observer variability (bias ± 95%LoA): LVEF 1 ± 8% vs 3 ± 9%, RVEF - 2 ± 15% vs 3 ± 21%. In the external cohort, EF well correlated with manual tracing (intraclass correlation coefficient: LVEF 0.98, RVEF 0.93). The automatic approach was significant faster than manual segmentation in providing cardiac parameters (approximately 1.5 s vs 450 s). CONCLUSIONS: Experimental results show that the proposed method reached promising performance in cardiac segmentation from CMR images with susceptibility artifacts and alleviates time consuming expert physician contour segmentation.

A Comprehensive Assessment of Cardiomyopathies through Cardiovascular Magnetic Resonance: Focus on the Pediatric Population.

Cardiomyopathies (CMPs) are a heterogeneous group of diseases that involve the myocardium and result in systolic or diastolic impairment of the cardiac muscle, potentially leading to heart failure, malignant arrhythmias, or sudden cardiac death. Occurrence in pediatric age is rare but has been associated with worse outcomes. Non-invasive cardiac imaging techniques, integrated with clinical, genetic, and electrocardiographic data, have shown a pivotal role in the clinical work-up of such diseases by defining structural alterations and assessing potential complications. Above all modalities, cardiovascular magnetic resonance (CMR) has emerged as a powerful tool complementary to echocardiography to confirm diagnosis, provide prognostic information and guide therapeutic strategies secondary to its high spatial and temporal resolution, lack of ionizing radiation, and good reproducibility. Moreover, CMR can provide in vivo tissue characterization of the myocardial tissue aiding the identification of structural pathologic changes such as replacement or diffuse fibrosis, which are predictors of worse outcomes. Large prospective randomized studies are needed for further validation of CMR in the context of childhood CMPs. This review aims to highlight the role of advanced imaging with CMR in CMPs with particular reference to the dilated, hypertrophic and non-compacted phenotypes, which are more commonly seen in children.

The direct costs of coronary CT angiography relative to contrast-enhanced thoracic CT: Time-driven activity-based costing.

BACKGROUND: Coronary CT angiography (CCTA) and contrast-enhanced thoracic CT (CECT) are distinctly different diagnostic procedures that involve intravenous contrast-enhanced CT of the chest. The technical component of these procedures is reimbursed at the same rate by the Centers for Medicare and Medicaid Services (CMS). This study tests the hypothesis that the direct costs of performing these exams are significantly different. METHODS: Direct costs for both procedures were measured using a time-driven activity-based costing (TDABC) model. The exams were segmented into four phases: preparation, scanning, post-scan monitoring, and image processing. Room occupancy and direct labor times were collected for scans of 54 patients (28 CCTA and 26 CECT studies), in seven medical facilities within the USA and used to impute labor and equipment cost. Contrast material costs were measured directly. Cost differences between the exams were analyzed for significance and variability. RESULTS: Mean CCTA duration was 3.2 times longer than CECT (121 and 37 â€‹min, respectively. p â€‹< â€‹0.01). Mean CCTA direct costs were 3.4 times those of CECT ($189.52 and $55.28, respectively, p â€‹< â€‹0.01). Both labor and capital equipment costs for CCTA were significantly more expensive (6.5 and 1.8-fold greater, respectively, p â€‹< â€‹0.001). Segmented by procedural phase, CCTA was both longer and more expensive for each (p â€‹< â€‹0.01). Mean direct costs for CCTA exceeded the standard CMS technical reimbursement of $182.25 without accounting for indirect or overhead costs. CONCLUSION: The direct cost of performing CCTA is significantly higher than CECT, and thus reimbursement schedules that treat these procedures similarly undervalue the resources required to perform CCTA and possibly decrease access to the procedure.

Reliability of single breath hold three-dimensional cine kat-ARC for the assessment of biventricular dimensions and function.

PURPOSE: To assess the accuracy and reproducibility of 3D-cine k-adaptative-t-autocalibrating reconstruction for cartesian sampling (3D cine kat-ARC) for quantification of biventricular volumes, ejection fraction and LV mass in clinical practice. METHOD: 74 patients underwent cardiac magnetic resonance for clinical indications. In the whole population 3D cine kat-ARC and 2D cine bSSFP images were acquired on short axis view. Subsequently, the population was divided in three subgroups (dilated, hypetrophic, other phenotypes). Two experienced observers performed analysis of volumes, biventricular function and left ventricular mass in the overall population and subgroups using an off-line workstation. Statistical analysis was performed using Student's t-test, linear regression and Bland-Altman plot, correlation coefficient η2 and the intraclass correlation coefficient (ICC). A cut-off value of p < 0.05 was considered statistically significant. RESULTS: Biventricular volumes, function and left ventricular mass evaluated with 3D cine kat-ARC sequences did not show any significant difference compared to 2D bSSFP sequences in the overall population (p > 0.05). Bland-Altman analysis showed limited bias and narrow limits of the agreement for all measurements in overall population. Subgroup analysis showed a statistically significant difference (p = 0.04) for left ventricular ejection fraction (LVEF) in patients with a dilated phenotype; showing a minimum overestimation tendency for 3D cine kat ARC (2D cine bSSFP LVEF = 46.44 ± 15.83% vs 3D cine kat-ARC LVEF = 48.36 ± 16.50 %). CONCLUSIONS: 3D cine kat-ARC 3D sequences allow an accurate evaluation of biventricular volumes and function in a single breath hold.

Healthcare Policy Statement on the Utility of Coronary Computed Tomography for Evaluation of Cardiovascular Conditions and Preventive Healthcare: From the Health Policy Working Group of the Society of Cardiovascular Computed Tomography.

The rising cost of healthcare is prompting numerous policy and advocacy discussions regarding strategies for constraining growth and creating a more efficient and effective healthcare system. Cardiovascular imaging is central to the care of patients at risk of, and living with, heart disease. Estimates are that utilization of cardiovascular imaging exceeds 20 million studies per year. The Society of Cardiovascular CT (SCCT), alongside Rush University Medical Center, and in collaboration with government agencies, regional payers, and industry healthcare experts met in November 2016 in Chicago, IL to evaluate obstacles and hurdles facing the cardiovascular imaging community and how they can contribute to efficacy while maintaining or even improving outcomes and quality. The summit incorporated inputs from payers, providers, and patients' perspectives, providing a platform for all voices to be heard, allowing for a constructive dialogue with potential solutions moving forward. This article outlines the proceedings from the summit, with a detailed review of past hurdles, current status, and potential solutions as we move forward in an ever-changing healthcare landscape.

Left atrial volume assessment in atrial fibrillation using multimodality imaging: a comparison of echocardiography, invasive three-dimensional CARTO and cardiac magnetic resonance imaging.

Left atrial size in atrial fibrillation is a strong predictor of successful ablation and cardiovascular events. Cardiac magnetic resonance multislice method (CMR-MSM) is the current gold standard for left atrial volume (LAV) assessment but is time consuming. We investigated whether LAV with more rapid area-length method by echocardiography (Echo-AL) or cardiac magnetic resonance (CMR-AL) and invasive measurement by 3D-CARTO mapping during ablation correlate with the CMR-MSM. We studied 250 consecutive patients prior to atrial fibrillation ablation. CMR images were acquired on 3T scanner to measure LAV by MSM and biplane area-length method. Standard echocardiography views were used to calculate LAV by biplane area-length method. LAV during ablation was measured by 3D-CARTO mapping. LAV was compared using intra-class correlation (ICC), Pearson's correlation and Bland-Altman plots. CMR-MSM was used as the reference standard. Mean LAV using CMR-MSM was 112.7 ± 36.7 ml. CMR-AL method overestimated LAV by 13.3 ± 21.8 ml (11.2%, p < 0.005) whereas 3D-CARTO and Echo-AL underestimated LAV by 8.3 ± 22.6 and 24.0 ± 27.6 ml respectively (8.7% and 20.0% respectively, p < 0.005). There was no significant difference between paroxysmal and persistent atrial fibrillation. CMR-AL and 3D-CARTO correlated and agreed well with CMR-MSM (r = 0.87 and 0.74, ICC = 0.80 and 0.77 respectively). However, Echo-AL had poor correlation and agreement with CMR-MSM (r = 0.66 and ICC = 0.48). Bland-Altman plots confirmed these findings. CMR-AL method may be used as an alternative to CMR-MSM, as it is non-invasive, rapid, and correlates well with CMR-MSM. LAV by different modalities should not be used interchangeably.