Advances in Cardiovascular Imaging

Left ventricular ejection fraction (LVEF) plays as an essential role in the assessment of cardiac function, providing quantitative data support for the medical diagnosis of heart disease. Robust evaluation of the ejection fraction relies on accurate left ventricular (LV) segmentation of echocardiograms. Because human bias and expensive labor cost exist in manual echocardiographic analysis, computer algorithms of deep-learning have been developed to help human experts in segmentation tasks. Most of the previous work is based on the convolutional neural networks (CNN) structure and has achieved good results. However, the region occupied by the left ventricle is large for echocardiography. Therefore, the limited receptive field of CNN leaves much room for improvement in the effectiveness of LV segmentation. In recent years, Vision Transformer models have demonstrated their effectiveness and universality in traditional semantic segmentation tasks. Inspired by this, we propose two models that use two different pure Transformers as the basic framework for LV segmentation in echocardiography: one combines Swin Transformer and K-Net, and the other uses Segformer. We evaluate these two models on the EchoNet-Dynamic dataset of LV segmentation and compare the quantitative metrics with other models for LV segmentation. The experimental results show that the mean Dice similarity of the two models scores are 92.92% and 92.79%, respectively, which outperform most of the previous mainstream CNN models. In addition, we found that for some samples that were not easily segmented, whereas both our models successfully recognized the valve region and separated left ventricle and left atrium, the CNN model segmented them together as a single part. Therefore, it becomes possible for us to obtain accurate segmentation results through simple post-processing, by filtering out the parts with the largest circumference or pixel square. These promising results prove the effectiveness of the two models and reveal the potential of Transformer structure in echocardiographic segmentation. Full article

Background and Aims. Dobutamine stress echocardiography (DSE) is a well-established non-invasive investigation for the detection of ischemic myocardial dysfunction. The aim of this study was to evaluate the accuracy of myocardial deformation parameters measured by speckle tracking echocardiography (STE) in predicting culprit coronary artery lesions in patients with prior revascularization and acute coronary syndrome (ACS). Methods. We prospectively studied 33 patients with ischemic heart disease, a history of at least one episode of ACS and prior revascularization. All patients underwent a complete stress Doppler echocardiographic examination, including the myocardial deformation parameters of peak systolic strain (PSS), peak systolic strain rate (SR) and wall motion score index (WMSI). The regional PSS and SR were analyzed for different culprit lesions. Results. The mean age of patients was 59 ± 11 years and 72.7% were males. At peak dobutamine stress, the change in regional PSS and SR in territories supplied by the LAD showed smaller increases compared to those in patients without culprit LAD lesions (p < 0.05 for all). Likewise, the regional parameters of myocardial deformation were reduced in patients with culprit LCx lesions compared to those with non-culprit LCx lesions and in patients with culprit RCA legions compared to those with non-culprit RCA lesions (p < 0.05 for all). In the multivariate analysis, the △ regional PSS (1.134 (CI = 1.059–3.315, p = 0.02)) and the △ regional SR (1.566 (CI = 1.191–9.013, p = 0.001)) for LAD territories predicted the presence of LAD lesions. Similarly, in a multivariable analysis, the △ regional PSS and the △SR predicted LCx culprit lesions and RCA culprit lesions (p < 0.05 for all). In an ROC analysis, the PSS and SR had higher accuracies compared to the regional WMSI in predicting culprit lesions. A △ regional SR of −0.24 for the LAD territories was 88% sensitive and 76% specific (AUC = 0.75; p < 0.001), a △ regional PSS of −1.20 was 78% sensitive and 71% specific (AUC = 0.76, p < 0.001) and a △ WMSI of −0.35 was 67% sensitive and 68% specific (AUC = 0.68, p = 0.02) in predicting LAD culprit lesions. Similarly, the △ SR for LCx and RCA territories had higher accuracies in predicting LCx and RCA culprit lesions. Conclusions. The myocardial deformation parameters, particularly the change in regional strain rate, are the most powerful predictors of culprit lesions. These findings strengthen the role of myocardial deformation in increasing the accuracy of DSE analyses in patients with prior cardiac events and revascularization. Full article

Background: While lifestyle changes, management of coronary artery disease (CAD) risk factors, myocardial revascularization procedures, and medication can improve a patient’s prognosis, de novo native coronary lesions and in-stent restenosis (ISR) remain significant clinical concerns. ISR is more frequent with a bare-metal stent than with a drug-eluting stent and has been documented in around 12% of DES patients. Acute coronary syndrome (ACS) manifests as unstable angina in about 30% to 60% of ISR patients. Myocardial work imaging is a modern, non-invasive technique able to identify individuals with critical coronary artery lesions with high sensitivity and specificity. Case report: We present the case of a 72-year-old Caucasian gentleman with multiple cardiovascular risk factors, admitted to the Cardiology Clinic of Timișoara Municipal Hospital with unstable angina. From 1999 to 2021, the patient experienced two myocardial infarctions, a double aortocoronary bypass graft, and multiple percutaneous coronary interventions with 11 stent implantations, including 6 for ISR. Using two-dimensional speckle-tracking echocardiography and myocardial work assessment, we detected that the lateral wall of the left ventricle had a severely impaired deformation pattern. Angio-coronarography was performed, and sub-occlusion of the posterolateral branch of the right coronary artery was found. Angioplasty was performed and a DES was inserted, with a good final angiographic result and complete release of symptoms. Conclusion: In patients with a history of multiple myocardial revascularization interventions and ISR, it is challenging to identify the critical ischemia region by non-invasive methods. Myocardial work imaging was beneficial in the detection of the altered deformation patterns indicating significant ischemia, its accuracy being superior to that of LV strain, as proven by coronary angiography. Urgent coronary angiography followed by angioplasty and stent implantation resolved the issue. Full article

Infective endocarditis (IE) is common in patients with corrected congenital heart disease (CHD) with a residual lesion, but is rarely found on surgical patches used to close atrial septal defects (ASDs). This is also reflected in the current guidelines that do not recommend antibiotic therapy for patients with a repaired ASD with no residual shunt six months after closure (percutaneous or surgical). However, the situation could be different in the case of mitral valve endocarditis, which causes leaflet disruption with severe mitral insufficiency and could seed the surgical patch. We present herein a 40-year-old male patient with a past medical history of a complete surgically corrected atrioventricular canal defect performed in childhood who presented with fever, dyspnea and severe abdominal pain. Transthoracic and transesophageal echocardiography (TTE and TEE) revealed vegetation at the level of the mitral valve and the interatrial septum. The CT scan confirmed ASD patch endocarditis and multiple septic emboli, guiding the therapeutic management. An accurate evaluation of cardiac structures should be mandatory when a systemic infection is detected in CHD patients, even if the defects were surgically corrected, because the detection and eradication of such infectious foci as well as a surgical reintervention are particularly difficult to achieve in this subpopulation. Full article