4-chamber View Research Articles

Deep learning for transesophageal echocardiography view classification

Transesophageal echocardiography (TEE) imaging is a vital tool used in the evaluation of complex cardiac pathology and the management of cardiac surgery patients. A key limitation to the application of deep learning strategies to intraoperative and intraprocedural TEE data is the complexity and unstructured nature of these images. In the present study, we developed a deep learning-based, multi-category TEE view classification model that can be used to add structure to intraoperative and intraprocedural TEE imaging data. More specifically, we trained a convolutional neural network (CNN) to predict standardized TEE views using labeled intraoperative and intraprocedural TEE videos from Cedars-Sinai Medical Center (CSMC). We externally validated our model on intraoperative TEE videos from Stanford University Medical Center (SUMC). Accuracy of our model was high across all labeled views. The highest performance was achieved for the Trans-Gastric Left Ventricular Short Axis View (area under the receiver operating curve [AUC] = 0.971 at CSMC, 0.957 at SUMC), the Mid-Esophageal Long Axis View (AUC = 0.954 at CSMC, 0.905 at SUMC), the Mid-Esophageal Aortic Valve Short Axis View (AUC = 0.946 at CSMC, 0.898 at SUMC), and the Mid-Esophageal 4-Chamber View (AUC = 0.939 at CSMC, 0.902 at SUMC). Ultimately, we demonstrate that our deep learning model can accurately classify standardized TEE views, which will facilitate further downstream deep learning analyses for intraoperative and intraprocedural TEE imaging.

Diagnostic confidence with quantitative cardiovascular magnetic resonance perfusion mapping increases with increased coverage of the left ventricle

BackgroundQuantitative cardiovascular magnetic resonance (CMR) first pass perfusion maps are conventionally acquired with 3 short-axis (SAX) views (basal, mid, and apical) in every heartbeat (3SAX/1RR). Thus, a significant part of the left ventricle (LV) myocardium, including the apex, is not covered. The aims of this study were 1) to investigate if perfusion maps acquired with 3 short-axis views sampled every other RR-interval (2RR) yield comparable quantitative measures of myocardial perfusion (MP) as 1RR and 2) to assess if acquiring 3 additional perfusion views (i.e., total of 6) every other RR-interval (2RR) increases diagnostic confidence. MethodsIn 287 patients with suspected ischemic heart disease stress and rest MP were performed on clinical indication on a 1.5T MR scanner. Eighty-three patients were examined by acquiring 3 short-axis perfusion maps with 1RR sampling (3SAX/1RR); for which also 2RR maps were reconstructed. Additionally, in 103 patients 3 short-axis and 3 long-axis (LAX; 2-, 3, and 4-chamber view) perfusion maps were acquired using 2RR sampling (3SAX + 3LAX/2RR) and in 101 patients 6 short-axis perfusion maps using 2RR sampling (6SAX/2RR) were acquired. The diagnostic confidence for ruling in or out stress-induced ischemia was scored according to a Likert scale (certain ischemia [2 points], probably ischemia [1 point], uncertain [0 points], probably no ischemia [1 point], certain no ischemia [2 points]). ResultsThere was a strong correlation (R = 0.99) between 3SAX/1RR and 3SAX/2RR for global MP (mL/min/g). The diagnostic confidence score increased significantly when the number of perfusion views was increased from 3 to 6 (1.24 ± 0.68 vs 1.54 ± 0.64, p < 0.001 with similar increase for 3SAX+3LAX/2RR (1.29 ± 0.68 vs 1.55 ± 0.65, p < 0.001) and for 6SAX/2RR (1.19 ± 0.69 vs 1.53 ± 0.63, p < 0.001). ConclusionQuantitative perfusion mapping with 2RR sampling of data yields comparable perfusion values as 1RR sampling, allowing for the acquisition of additional views within the same perfusion scan. The diagnostic confidence for stress-induced ischemia increases when adding 3 additional views, short- or long axes, to the conventional 3 short-axis views. Thus, future development and clinical implementation of quantitative CMR perfusion should aim at increasing the LV coverage from the current standard using 3 short-axis views.

Automatic segmentation of 2D echocardiography ultrasound images by means of generative adversarial network.

Automated cardiac segmentation from two-dimensional (2D) echocardiographic images is a crucial step toward improving clinical diagnosis. Anatomical heterogeneity and inherent noise, however, present technical challenges and lower segmentation accuracy. The objective of this study is to propose a method for the automatic segmentation of the ventricular endocardium, the myocardium, and the left atrium, in order to accurately determine clinical indices. Specifically, we suggest using the recently introduced pixel-to-pixel Generative Adversarial Network (Pix2Pix GAN) model for accurate segmentation. To accomplish this, we integrate the backbone PatchGAN model for the discriminator and the UNET for the generator, for building the Pix2Pix GAN. The resulting model produces precisely segmented images, thanks to UNET's capability for precise segmentation and PatchGAN's capability for fine-grained discrimination. For the experimental validation, we use the Cardiac Acquisitions for Multi-structure Ultrasound Segmentation (CAMUS) dataset, which consists of echocardiographic images from 500 patients in 2-chamber (2CH) and 4-chamber (4CH) views at the end-diastolic (ED) and end-systolic (ES) phases. Similarly to state-of-the-art studies on the same dataset, we followed the same train-test splits. Our results demonstrate that the proposed GAN-based technique improves segmentation performance for clinical and geometrical parameters compared to the state-of-the-art methods. More precisely, throughout the ED and ES phases, the mean Dice values for the left ventricular endocardium reached 0.961 and 0.930 for 2CH, and 0.959 and 0.950 for 4CH, respectively. Furthermore, the average ejection fraction correlation and Mean Absolute Error obtained were 0.95 and 3.2ml for 2CH, and 0.98 and 2.1ml for 4CH, outperforming the state-of-the-art results.

Determination of Values of the Tricuspid Annular Plane Systolic Excursion (TAPSE) In Bangladeshi Adult Patient With or Without LV Dysfunction

Background: Tricuspid annular plane systolic excursion (TAPSE) is an Echocardiographic measure that allows us to assess right ventricular systolic function and it correlates well with reference techniques like Cardiac Magnetic Resonance Imaging. TAPSE measurement is common in adults. Objective: Our objective was to determine values of TAPSE in Bangladeshi adults with or without LV systolic dysfunction and to determine the relationship of these values with age, sex, RVIDd, LVEF &amp; EPSS. Method: This was an prospective observational study in patients undergoing comprehensive transthoracic echocardiography for any indication. From April 2022 to April 2023 we prospectively enrolled 100 adult (from 30 to age 80 years) of both sexes who presented to the Cardiology Clinic of LABAID Cardiac Hospital. We performed a complete transthoracic echocardiography study. We measured TAPSE in 2-dimensional M-mode echocardiograms from the apical 4- chamber view, positioning the cursor on the lateral tricuspid annulus near the free RV wall and aligning it as close as possible to the apex of the heart . The mean values were taken by at least 2 measurements for reducing interobserver and intraobserver variability’s. Patients with confirmed congenital &amp; valvular heart disease were excluded. Results: Mean TAPSE values were 19.15±3.87cm irrespective of LVEF, with no significant differences between sexes, 18.45±3.801 in male , 19.94±3.853 in female (P=.056). TAPSE value was 22.00±1.581 in person with normal LVEF &amp; 16.77±2.455 in person with reduced LVEF ( P&lt;.001) A statistically significant positive correlation of LVEF (r=.813) and significant negative correlation of EPSS (r=-.639) were observed with TAPSE (p&lt;0.001). But no significant correlation of TAPSE was found between age (r=-.185)). ), gender (r=.192) &amp; RVIDd (r= -.063) (p &gt;0.05). Multivariate analysis confirmed these correlations and the interactions between variables (LVEF &amp; EPSS). Graphs of estimated population-based TAPSE values adjusted by age and LV function are provided. Conclusion: We determined values of TAPSE in Bangladeshi adult population with or without LV systolic dysfunction and assessed relationship of these values with age, sex, RVIDd, LVEF &amp; EPSS. The TAPSE measurement was reproducible and associated directly with LV systolic function. These reference values could guide decision making in daily clinical practice. Bangladesh Heart Journal 2023; 38(2): 92-101

Evaluation of subclinical left ventricular systolic dysfunction in obese patients by global myocardial work

ObjectiveTo evaluate subclinical LV systolic dysfunction in obese patients by global myocardial work (MW).MethodsA total of 589 obese patients and 100 normal controls were enrolled in the study. The global longitudinal strain (GLS), global work index (GWI), global constructive work (GCW), global wasted work (GWW) and global work efficiency (GWE) were generated by a noninvasive pressure-strain loop (PSL) in apical 3-, 4- and 2-chamber views acquired by two-dimensional echocardiography. All obese patients were divided into three groups: class I obesity (mild) 30–35 kg/m2, class II obesity (moderate) 35–40 kg/m2 and class III obesity (severe) > 40 kg/m2. These values were compared among the three groups. The independent influencing factors of subclinical LV systolic dysfunction in obese patients were explored by constructing a multiple regression model. ROC analysis was performed to determine the performance of MW to detect subclinical LV systolic dysfunction in obese patients.ResultsThe absolute value of GLS in obese patients was significantly lower than that in normal controls (P < 0.001). The values of GWI, GCW, GWE and GCW/GWW in obese patients were significantly lower than those in normal controls (P < 0.05), while GWW was significantly larger than that in normal controls (P < 0.001). Subgroup analysis and trend analysis showed that the values of GWI, GCW, GWE and GCW/GWW in severe obese patients were lower than those in moderate obese patients and lower than those in mild obese patients (P < 0.01), while GWW in severe obese patients was larger than that in moderate obese patients and larger than that in mild obese patients (P < 0.05). Female sex, BMI and SBP were independent influencing factors of impaired GWI (β = 0.15, P < 0.001) (β=-0.18, P < 0.001) (β = 0.50, P < 0.001) and GCW (β = 0.17, P < 0.001) (β=-0.19, P < 0.001) (β = 0.57, P < 0.001). ROC analysis showed that the AUC of the combined global MW was significantly higher than the AUCs of the individual indices (P < 0.05).ConclusionIn this study, we conclude that subclinical LV systolic dysfunction was detected by the novel global MW technique in obese patients. Elevated BMI in obese patients results in an increased risk of subclinical LV systolic dysfunction, although the LVEF is normal. Controlling BMI in obese patients may reduce the impairment to the LV myocardial systolic function. Global MW is a novel and reproducible technique that can be well applied in the clinical evaluation of subclinical LV systolic dysfunction.

Echocardiography, apical 4-chamber view showing sustained normal LV function (ejection fraction 55%) at 4-year follow up.

Echocardiography, apical 4-chamber view showing sustained normal LV function (ejection fraction 55%) at 4-year follow up.

Echocardiography, apical 4-chamber view at 6-month follow-up showing normal systolic function (ejection fraction 60%).

Echocardiography, apical 4-chamber view at 6-month follow-up showing normal systolic function (ejection fraction 60%).

Echocardiography, apical 4-chamber view at presentation showing a dilated left ventricle with severely reduced systolic function and ejection fraction of 15%.

Echocardiography, apical 4-chamber view at presentation showing a dilated left ventricle with severely reduced systolic function and ejection fraction of 15%.

Echocardiography, apical 2-chamber views showing sustained normal LV function (ejection fraction 55%) at 4-year follow up.

Echocardiography, apical 2-chamber views showing sustained normal LV function (ejection fraction 55%) at 4-year follow up.

Clinical service evaluation of the feasibility and reproducibility of novel artificial intelligence based-echocardiographic quantification of global longitudinal strain and left ventricular ejection fraction in trastuzumab-treated patients.

Cardiotoxicity is a potential prognostically important complication of certain chemotherapeutic agents that may result in preclinical or overt clinical heart failure. In some cases, chemotherapy must be withheld when left ventricular (LV) systolic function becomes significantly impaired, to protect cardiac function at the expense of a change in the oncological treatment plan, leading to associated changes in oncological prognosis. Accordingly, patients receiving potentially cardiotoxic chemotherapy undergo routine surveillance before, during and following completion of therapy, usually with transthoracic echocardiography (TTE). Recent advancements in AI-based cardiac imaging reveal areas of promise but key challenges remain. There are ongoing questions as to whether the ability of AI to detect subtle changes in individual patients is at a level equivalent to manual analysis. This raises the question as to whether AI-based left ventricular strain analysis could provide a potential solution to left ventricular systolic function analysis in a manner equivocal to or superior to conventional assessment, in a real-world clinical service. AI based automated analyses may represent a potential solution for addressing the pressure of increasing echocardiographic demands within limited service-capacity healthcare systems, in addition to facilitating more accurate diagnoses. This clinical service evaluation aims to establish whether AI-automated analysis compared to conventional methods (1) is a feasible method for assessing LV-GLS and LVEF, (2) yields moderate to good correlation between the two approaches, and (3) would lead to different clinical recommendations with serial surveillance in a real-world clinical population. We observed a moderate correlation (r = 0.541) in GLS between AI automated assessment compared to conventional methods. The LVEF quantification between methods demonstrated a strong correlation (r = 0.895). AI-generated GLS and LVEF values compared reasonably well with conventional methods, demonstrating a similar temporal pattern throughout echocardiographic surveillance. The apical-three chamber view demonstrated the lowest correlation (r = 0.423) and revealed to be least successful for acquisition of GLS and LVEF. Compared to conventional methodology, AI-automated analysis has a significantly lower feasibility rate, demonstrating a success rate of 14% (GLS) and 51% (LVEF).

The effect of atrial morphology on atrial function in hypertrophic cardiomyopathy

Abstract Background Atrial dysfunction is a relevant marker of disease progression in hypertrophic cardiomyopathy (HCM). Left atrial (LA) longitudinal functional parameters and volumes derived from cardiac magnetic resonance (CMR) are associated with new-onset atrial fibrillation (AF) and its complications. The asymmetrical shape of the LA and its morphological alterations may influence LA function and could provide new mechanistic insights into HCM. Objective To assess the association between CMR derived functional and morphological LA characteristics in HCM patients. Methods Patients with an established diagnosis of HCM were included. HCM patients with a history of AF or without available CMR were excluded. CMR acquisitions used for clinical indication of heart failure diagnosis and etiology were retrospectively analyzed to obtain LA reservoir (LAres), booster (LAboost), and conduit (LAcond) strain on 2-chamber views (Medis Suite v3.2). Strain measurements of the other cardiac chambers were also performed. Manual tracing of LA endocardial border at the LA orthogonal longitudinal and transverse diameters on 2-, 3-, and 4-chamber views was performed (Philips Portal v10.1). Univariable and multivariable forward linear regression was employed to assess associations between functional and morphological LA measures. Results A total of 81 HCM patients were included, mean age 52±16 years, 59 (73%) male, and left ventricular ejection fraction 72.0±8.3%. Mean LAres was 27.2±11.0%, LAboost -14.9%±6.4%, and LAcond -12.5%±7.5%. LA morphological parameters are summarized in Table 1. The strongest correlates in multivariable regression for LAres were longitudinal LA diameter on 2-chamber view (Figure 1) and transverse LA diameter ratio between 4- and 2-chamber view (R2 0.30, p&amp;lt;0.001). The strongest correlates in multivariable regression for LAboost were longitudinal LA diameter on 2- and 4-chamber view, antero-posterior LA diameter on 3-chamber view, and LA area on 4-chamber view (R2 0.29, p&amp;lt;0.001). Longitudinal 2-chamber LA diameter also correlated with LAcond, but the strongest correlates of LAcond in multivariable regression were longitudinal-transversal LA diameter ratio on 2-chamber view, LA area on 3-chamber view, and LA sphericity (R2 0.25, p&amp;lt;0.001). Conclusions CMR-derived LA functions in HCM patients differently correlated with LA morphology. LA longitudinal 2-chamber diameter had a strong influence on all LA functions.Left atrial measures in HCMLA function and diameter correlations

Contribution of the left atrial speckle tracking in the evaluation of left ventricule filling pressure in acute coronary syndromes

Abstract Introduction A non invasive estimation of diastolic function with echocardiography according to consensual methods, ie American society of Echocardiography (ASE) / European association of cardiovascular imaging (EACVI) algorithm 2018, is considered an integral essential part of the clinical evaluation of patients presenting with symptoms of acute coronary syndrome (ACS). Left atrial (LA) longitudinal strain in the frame of speckle tracking echocardiography (STE) was reported recently to have additive diagnostic value to assess left ventricle (LV) filling pressures (LVFP) in a large spectrum of cardiovascular diseases. Our study aim is to assess the accuracy of LA strain in evaluating LVFP in patients with ACS, as a single parameter. Methods Our study was monocentric in our cardiology department led prospectively between April 20, 2022, and June 30, 2022. We included all patients admitted to our department for evolving ST elevation (STEMI) or non-ST elevation (NSTEMI) myocardial infarction (&amp;lt;48 hours from onset of symptoms). Echocardiographic measurements were performed according to ASE/EACVI in less than 24 hours. They were divided into two groups according to the elevation of LVFP group 1 with non-elevated LVFP vs group with elevated LVF. LA-GS was assessed using images obtained in apical 4- and 2-chamber views , with attention to optimal visualization of the LA. The endocardial border of the LA was traced manually. Left atrial reservoir strain (LARS) was calculated from LV-end diastole, and pump strain (LAPS) after the onset of the p-wave in the electrocardiogram. Results Fifty patients were included in our study. The mean age was 59 ± 12 years. 72%(36) of our population was men. 34%(17) of the population had elevated LVFP (Group2) with a male predominance of 82% (14). They were active smokers in 64% (11), 52%(9) had hypertension, 70% (12) had diabetes mellitus, 47%(8) had dyslipidemia and 35% (6) were hospitalized for NSTEMI. The mean LARS and LAPS were 26.9%, and 15.2% in group 1 vs 15.1%, and 7.1% respectively in group 2 with a difference statically significative p = 0.001, and p = 0.002 respectively. The area under the curve was 0.910 (LARS) and 0.850 (LAPS). The best cut-off for the LAPS was 11.5% with 100% of sensibility and 63% of specificity, for the LARS the best cut-off was 18% with 95% of sensibility and 66% of specificity. Conclusion LA-GS includes a reproducible and simple method for LVFP assessment in ACS. it provides an additional variable that can contribute when one of the other parameters is missing.

Prognostic value of left atrial strain in heart failure with reduced ejection fraction

Abstract Background The prognostic value of left atrial (LA) strain in patients with heart failure with reduced ejection fraction (HFrEF) has not been fully elucidated. Therefore, this study investigated the prognostic value of left atrial strain in HFrEF patients in relation to allcause mortality. Methods A total of 822 echocardiograms from HFrEF patients admitted to a heart failure clinic were analyzed offline. To calculate left atrial resevoir strain (LA RS) and left atrial contractile strain (LA CS), left atrial two-dimensional speckle tracking was performed in the 4-chamber, 2-chamber and 3-chamber view. The end-point was all-cause mortality. The association between left atrial strain parameters and outcome was examined using Cox regression. Results The median follow-up time was 40 months and follow-up was 100% complete. During follow-up, a total of 137 patients (16.7%) died of all causes. In a final multivariable model adjusted for clinical and echocardiographic parameters including global longitudinal strain, LA RS and LA CS were significantly associated with all-cause death during follow-up (LA RS, HR 0.96, 95% CI 0.92-0.99 p = 0.014, pr. 1% increase) (LACS, HR 0.95, 95% CI 0.92-0.98 p = 0.002, pr. 1% increase) (Table 1). When added to the final multivariable model, both LA RS and LA CS contributed with incremental prognostic value as determined by C-statistic (LA RS: C-stat difference 0.007, 95% CI 0.000-0.020, p = 0.050) (LA CS: C-stat difference 0.009, 95% CI 0.000-0.023, p = 0.030). Conclusion In HFrEF patients, LA RS and LA CS were associated with all-cause mortality and contributed with incremental prognostic value in addition to established prognostic measures.Table 1

Echocardiographic predictors of occult atrial fibrillation in patients with cryptogenic stroke

Abstract Background Left atrial (LA) strain has been proposed as an echocardiographic predictor of subsequent atrial fibrillation (AF) in patients presenting with cryptogenic stroke (CS). The purpose of this study was to compare the predictive value of LA strain parameters with traditional echocardiographic measurements for predicting occult AF in patients with CS. Methods We conducted a single-center retrospective cohort study of patients with cryptogenic stroke who underwent implantable cardiac monitor (ICM) placement. Transthoracic echocardiogram (TTE) parameters collected included mitral e and e’ velocities, and LA volume index (LAVI). LA strain was calculated offline using speckle-tracking in apical 4 and 2 chamber views, during the reservoir, conduit, and contractile phases of the cardiac cycle. Strain measurements obtained in each view were averaged (Figure 1). AF episodes had to last at least 2 minutes to qualify as an AF event. Results The cohort consisted of 269 patients with cryptogenic stroke who underwent ICM placement between April 2015 to December 2020, of them 45 patients had AF detected by ICM during follow-up. Echocardiographic evidence of dilated LA measured using LAVI (p=0.043) as well as lower filling pressures measured using e/e’ (p=0.033) were significantly associated with AF. (Table 1). LA function using strain in reservoir, conduit, and contractile phases was not significantly associated with AF (Table 1). Conclusion Increased LA size, but not abnormal LA function was significantly associated with incident AF in patients with CS.

Mechanisms of adaptation to high intensity exercise in hypertrophic cardiomyopathy

Abstract Background Many individuals with hypertrophic cardiomyopathy (HCM) demonstrate exercise limitation. For a proportion this may be related to their overall cardiorespiratory fitness influenced by physical activity habits, body mechanics, or habitus. In others there is evidence of central and/or peripheral pathophysiology. However, some individuals with HCM demonstrate favourable adaptation to exercise. In the SAFE-HCM study, participants who underwent 12 weeks of high intensity exercise showed significant improvement in exercise indices including peak VO2, VO2/kg at anaerobic threshold (AT), time to AT, and overall exercise time compared to a usual care group. Purpose There have been no studies investigating the mechanistic adaptation(s) to exercise in HCM. This sub-study aimed to identify whether the observed improvements in exercise indices were attributable to central or peripheral adaptation. Methods Eighty patients with HCM (45.7±8.6 years) underwent baseline clinical, quality of life and psychological assessment. Individuals were randomised to a 12-week high intensity exercise programme (n=40) or usual care (n=40). Baseline evaluation was repeated at 12 weeks. The Fick equation (oxygen uptake (VO2) = cardiac output (CO) X (arterial-venous oxygen content (a-vO2 difference)) was used to assess whether central and/or peripheral adaptation was responsible for observed improvements. 2D speckle tracking imaging was utilised to calculate left ventricular longitudinal strain from the apical 2-, 3- and 4 chamber views (EchoPAC, V202, GE Healthcare). Results 12-weeks of high intensity exercise training produced a statistically significant increase in CO (1.1±0.4 L/min, CI (0.2,2.0), p=0.016) compared with the usual care group. There was no difference in the change in a-vO2 difference between groups (p=0.682) suggesting central adaptation to high intensity exercise. This was driven by an increase in stroke volume (SV) (6.1±3.0ml, CI (0.1,12.2), p=0.047) rather than an increase in heart rate (0.6±3.6 bpm, CI (-6.6,7.7), p=0.874). However, there was no change in resting myocardial deformation to account for the observed improvement in CO. Analysis of strain data demonstrated no difference in resting regional 4Ch (-0.7±0.6, CI (-1.9, 0.5), p=0.270) 3Ch (-1.1±0.9, CI (-2.8, 0.6), p=0.201), 2Ch (-1.3±0.9, CI (-3.1, 0.5), p=0.162) or average global longitudinal strain (0.9±0.6, CI (-2.2,0.3), p=0.144) between groups at 12 weeks. Conclusion Favourable central adaptations, predominantly driven by an increase in SV, enable improvements in exercise capacity following a high intensity exercise programme. Further studies are required to understand the physiological processes underlying this adaptation including assessment of myocardial deformation at peak exercise

Identification of abnormal ventricular asymmetry in 2nd trimester fetal ultrasound using artificial intelligence

Abstract Introduction Prenatal ultrasound screening for congenital heart disease (CHD) suffers from poor detection yield (10%-56%)[1, 2], with a strong impact on neonatal morbidity and mortality. The need for expertise in fetal cardiology and the high volume of screening cases limit the current detection rates. Computer-assisted prenatal screening could support clinicians in improving diagnostic yield, including for abnormal ventricular asymmetry, which is often hard to discriminate from physiological asymmetry. Here we aim at evaluating a deep neural network (DNN) for detection of abnormal ventricular asymmetry, which can be linked to multiple types of CHD, including coarctation of the aorta, pulmonary or aortic valve stenosis, ventricular hypoplasia or univentricular heart. Purpose To determine if a novel DNN can identify cases of abnormal ventricular asymmetry in 2nd trimester fetal ultrasound videos. Methods We used as an endpoint the presence of any abnormality causing a significantly abnormal asymmetry of the ventricles as seen in the fetal ultrasound. Consecutive patients who had an echocardiography performed at one center were included retrospectively starting from 2022, January 1st. Inclusion criteria were single pregnancy between 18 and 25 weeks of gestation. To have a high number of positive patients, patients were included separately if they were expected to be positive (n=35) or negative (n=75) to the endpoint, based on their medical record. Each case was reviewed by one of two physicians expert in fetal echocardiography interpretation to confirm the presence or absence of the endpoint. For each patient, a single video showing an interpretable four chamber view was selected. Patients with no such video were excluded. The DNN takes as input fetal ultrasound videos, and predicts the absence or presence of the endpoint for each video. If its confidence is low, the DNN predicts an "inconclusive" output instead. The DNN has a ResNet-50 architecture[3] adapted to videos and was trained on data from patients not included in the evaluation. The detection performance of the DNN and the proportion of conclusive outputs were assessed. Results Overall, 37 positive and 66 negative ultrasound videos were included. The DNN achieved an AUC of 75.5%, a sensitivity of 71.4% (54.9-83.7, 95%CI) and a specificity of 64.4% (51.7-75.4, 95%CI) in identifying cases of abnormal ventricular asymmetry, after excluding inconclusive diagnosis. The DNN predicted a conclusive diagnosis in 91.3% of cases. Conclusion A DNN could accurately identify cases of abnormal ventricular asymmetry in fetal heart ultrasound videos. Importantly, this evaluation was performed in a population of patients who had an echocardiogram, and which therefore contains more abnormal cases compared to patients undergoing standard screening. This work lays the ground for diagnostic support to enable a more efficient, accurate, and scalable analysis of fetal heart ultrasounds.

Left ventricular strain-volume loops in bicuspid aortic valve: new insights in hemodynamics and prognostic value

Abstract Background Bicuspid aortic valve (BAV) is a common congenital cardiac disease with a high risk of adverse outcomes. By combining left ventricular (LV) global longitudinal strain (GLS) with LV volume during the cardiac cycle, LV strain-volume loops (SV-loops) can be generated. This may be a valuable biomarker in early detection of LV deterioration. The aim of this study is to describe SV-loop characteristics in BAV patients and investigate its prognostic value. Methods BAV patients were compared with healthy controls, matched for age and sex on a group level. Apical 2, 3 and 4 chamber views were used to measure LV GLS and volume to construct SV-loops. The parameters measured from these SV-loops are depicted in Figure 1A. Associations with the composite endpoint of all-cause mortality, heart failure and supraventricular and ventricular arrhythmias were assessed by univariable Cox regression. Results 113 BAV patients were included (median age 32 years, 40% female). The median aortic jet velocity was 2.3 m/s [IQR 1.6-3.3] and 21 patients (19%) had moderate aortic regurgitation. A clear rightward shift in average SV-loops was seen between BAV patients and healthy controls (figure 1B). Sslope was significantly lower in BAV patients (0.21%/mL, [IQR 0.17-0.28] vs. 0.27%/mL [0.24-0.34], p&amp;lt;0.001), as was ESslope (0.19%/mL [0.12-0.25] vs. 0.29%/mL [0.21-0.43], p&amp;lt;0.001). Moreover, greater uncoupling was seen in BAV patients, both early (0.48±1.29 vs. 0.05±1.21, p=0.018) and late diastolic (0.66±1.02 vs -0.07±1.07, p&amp;lt;0.001). During a median follow-up period of 9.9 years [9.3-10.4], 17 patients experienced a primary endpoint. Echocardiographic parameters associated with the primary endpoint were early diastolic uncoupling (HR 1.82, p=0.009), E/e’ ratio (HR 1.29, p&amp;lt;0.001), ESslope (HR 0.55, p=0.03) and LV end-systolic volume (HR 1.05, p=0.03). Conclusion Significant differences in SV-loop characteristics were observed between BAV patients and healthy controls, suggesting its capability to provide new insights in cardiac hemodynamics and detect LV remodelling at an early stage. Moreover, SV-loops can be promising new prognostic markers.

The prevalence of congenital cardiac tumours in unselected newborns

Abstract Background Primary cardiac tumours in children are rare. The most common cardiac tumour in newborns is rhabdomyomas, associated with tuberous sclerosis in &amp;gt;50% of cases. The estimated prevalence is 0.14‰ in fetuses, whereas in the paediatric population, a 20-fold difference in autopsy prevalence has been reported (0.017‰ to 0.27‰). Purpose To determine the pre- and postnatal prevalence of congenital cardiac tumours in a large, population-based cohort of prenatally enrolled newborns. Methods Systematic transthoracic echocardiography (TTE), including sub-xiphoid, apical, parasternal, and suprasternal views, was performed in unselected newborns included in a population study. Participants were included at time of the routine malformation scan (weeks 18-21), which included 4-chamber view, aortic and pulmonary outflow tracts, and three-vessel view. Cardiac tumours were defined as solid, echogenic masses, and the echocardiographic description included location, size, and number (one/multiple) of the tumour. Information on subsequent diagnosis of tuberous sclerosis was collected from review of medical charts. Results A total of 25,588 newborns (age 12±8 days, 51.6% male) were enrolled and underwent TTE. Prenatally, no cardiac tumours were reported in any of the participants. Postnatally, cardiac tumours were detected in 7 newborns (4 males), corresponding to a prevalence of 0.3 [0.1; 0.6] per 1,000 live-births. Through retrospective review of the prenatal scans, a possible tumour in the ventricle was suspected in 1 of the 7 cases; the remaining 6 cases showed no signs of tumours prenatally. Sex, gestational age at birth, birth length and weight, APGAR 5-score, age and weight at TTE, and maternal age and pre-pregnancy BMI, did not significantly differ between newborns with (n=7) and without (n=25,581) cardiac tumours (all p&amp;gt;0.05). Smoking during pregnancy was significantly more frequent among mothers to newborns with cardiac tumours compared to the remaining cohort (29% vs 4%, p=0.023). In all 7 newborns, the cardiac tumours were located in the ventricles (5 (71%) newborns with tumours in both ventricles, 2 (29%) with tumours in the right ventricle), with multiple tumours seen in 6 (86%), and with size ranging from 2.0x1.9 mm to 10.0x5.1 mm. All 7 newborns had otherwise structurally normal hearts and no flow obstruction. Three newborns with cardiac tumours in the ventricles (43%) were diagnosed with tuberous sclerosis within 4 months after birth. Conclusions Systematic TTE in unselected newborns revealed a prevalence of congenital cardiac tumours of 0.3‰. Prenatal screening in week 18-21 did not seem efficient for identification of cardiac tumours. Cardiac tumours were located in the ventricles and were most often multiple. Cardiac tumours in the ventricles were associated with tuberous sclerosis in almost half the cases. For newborns with cardiac tumours, maternal smoking during pregnancy was common (29%).Figure 1

E-wave propagation index as a marker for left ventricular thrombi post-ST elevation myocardial infarction

Abstract Background The E-wave propagation index (EPI) is a novel echocardiographic measure for quantifying apical washout in the left ventricle (LV) and thus a promising marker of an elevated risk for LV thrombus. The association between EPI and LV thrombus has not been investigated in patients after ST-segment elevation myocardial infarction (STEMI). Purpose Aim was to determine, whether there is an association between EPI and LV thrombus development in STEMI patients treated with primary percutaneous coronary intervention (pPCI). Methods 665 STEMI patients treated with pPCI included in the prospective MARINA-STEMI cohort study (NCT04113356) were investigated. LV thrombus presence was diagnosed via contrast enhanced CMR a median of 4 (interquartile range [IQR] 3–5) days post-STEMI. EPI and left ventricular ejection fraction (LVEF) were measured using transthoracic echocardiography (TTE) a median of 2 ([IQR] 2–3) days post-STEMI. The longitudinal length of the LV was measured in the apical 4-chamber view at end-diastole. Velocity time integral (VTI) of the E-wave was measured using pulsed wave doppler. Results 5% (n=32) of the study population had a LV thrombus. Patients with LV thrombus had lower EPI values compared to patients without LV thrombus (0.92 vs 1.29, p&amp;lt;0.001). EPI (OR 0.21, 95% CI: 0.06-0.73, p&amp;lt;0.014), anterior infarct location (OR 17.18, 95 % CI: 2.25-131.05, p&amp;lt;0.006) and LVEF (OR 0.91, 95 % CI 0.86-0.95, p&amp;lt;0.001) were independently associated with LV thrombus. The optimal cut-off value for the prediction of LV thrombus prediction was an EPI &amp;lt;1 (sensitivity 56.3% and specificity 80.4%). 13% (n=18) of patients with an EPI &amp;lt;1 developed a LV thrombus compared to 3% (n=14) with an EPI≥1. Conclusion In STEMI patients treated with pPCI, a decreased EPI is a novel independent predictor for CMR verified LV thrombus. The optimal cut off for LV thrombus prediction is EPI &amp;lt;1.Center Image EPI

Left atrial strain measurement to predict new-onset atrial fibrillation in ST-elevation myocardial infarction patients

Abstract Background/Introduction ST-elevation myocardial infarction (STEMI) remains a healthcare burden not only through increased mortality risk, but also development of chronic cardiac pathologies like atrial fibrillation (AF). Left atrial (LA) reservoir strain is a known predictor of incident AF in the general population. Purpose Our aim was to explore the additional prognostic value of LA reservoir strain measured by transthoracic echocardiography (TTE) in STEMI patients for new-onset atrial fibrillation (NOAF). Methods Data were analyzed retrospectively from an ongoing STEMI registry. Patients with previous myocardial infarction, AF, known history of heart failure, severe valvular pathology, suboptimal image quality, AF during TTE or missing follow-up were excluded. TTE was performed within 48 hours of hospitalization. LA reservoir strain was measured in apical 4-chamber view. LA strain &amp;lt;23% was used as cut-off value for impaired LA function as previously established. The endpoint was NOAF. Follow-up was censored at last patient visit or at 5 years. Results In total 1238 patients (mean age 60±12 years; 930 (75%) men) were included. After median follow-up of 22 months (IQR 12; 60) 106 (8.6%) patients developed NOAF, most events (71 (67%)) taking place within the first year after STEMI. Mean LA reservoir strain was more impaired in patients who developed NOAF as compared to those who did not (19.3 ± 8.1% versus 24.3 ± 8.8% respectively (p&amp;lt;0.001). Clinical and echocardiographical characteristics are shown in the table. Cumulative event-free survival rates at 1, 3 and 5 years in patients with preserved versus decreased LA strain were 97%, 95% and 93% versus 91%, 89% and 83% respectively (Log-rank X2 = 21.1; p&amp;lt;0.001; Figure). Factors significant on univariable Cox regression analysis (age, presence of chronic obstructive pulmonary disease, troponin levels, left ventricular end-diastolic diameter, interventricular septum diameter, left ventricular global longitudinal strain, LA volume index, LA reservoir strain, E/E’ ratio and right ventricular fractional area change) were included in multivariable model, where LA reservoir strain remained significantly associated with NOAF (HR 0.96 (0.93 – 0.99); p=0.015). Addition of LA strain provided incremental prognostic value over baseline clinical risk factors, traditional TTE parameters and left ventricular global longitudinal strain (X2 84.5 vs 88.8; p=0.013). Conclusion LA reservoir strain was associated with new-onset atrial fibrillation in STEMI patients after adjusting for relevant clinical and echocardiographic risk factors.TableFigure