Transthoracic 3D Echocardiographic Left Heart Chamber Quantification Using an Automated Adaptive Analytics Algorithm

Contemporary clinical role of echocardiography in patients with advanced heart failure

Echocardiography represents an essential tool for imagers and clinical cardiologists in the management of patients with heart failure. Advanced heart failure (AdHF) is a more severe and, typically, later stage of HF that exposes patients to a high risk of adverse outcomes, with a 1-year mortality rate of around 50%. Currently, several therapies are available to improve the outcomes of these patients, reduce their mortality rate, and, possibly, delay the need for advanced therapies such as heart transplant and long-term mechanical circulatory support. When accurately performed and interpreted, echocardiography provides crucial information to properly tailor medical and device therapy of patients with AdHF and to identify those at even higher risk. In this review, we present the state of the art of echocardiography applications in the clinical management of patients with AdHF. We will discuss the role of echocardiography chronologically, beginning with the prediction of AdHF, proceeding through diagnosis, and detailing how echocardiography informs clinical decision-making, before concluding with indications for advanced therapies.

New ultrasound techniques. Present and future

The present study highlights the advances in ultrasound, especially regarding its clinical applications to critically ill patients. Artificial intelligence (AI) is crucial in automating image interpretation, improving accuracy and efficiency. Software has been developed to make it easier to perform accurate bedside ultrasound examinations, even by professionals lacking prior experience, with automatic image optimization. In addition, some applications identify cardiac structures, perform planimetry of the Doppler wave, and measure the size of vessels, which is especially useful in hemodynamic monitoring and continuous recording. The "strain" and "strain rate" parameters evaluate ventricular function, while "auto strain" automates its calculation from bedside images. These advances, and the automatic determination of ventricular volume, make ultrasound monitoring more precise and faster. The next step is continuous monitoring using gel devices attached to the skin.

Training Intensity Distribution of a 7-Day HIIT Shock Microcycle: Is Time in the "Red Zone" Crucial for Maximizing Endurance Performance? A Randomized Controlled Trial

BACKGROUND

Various studies have shown that the type of intensity measure affects training intensity distribution (TID) computation. These conclusions arise from studies presenting data from meso- and macrocycles, while microcycles, e.g., high-intensity interval training shock microcycles (HIIT-SM) have been neglected so far. Previous literature has suggested that the time spent in the high-intensity zone, i.e., zone 3 (Z3) or the "red zone", during HIIT may be important to achieve improvements in endurance performance parameters. Therefore, this randomized controlled trial aimed to compare the TID based on running velocity (TIDV), running power (TIDP) and heart rate (TIDHR) during a 7-day HIIT-SM. Twenty-nine endurance-trained participant were allocated to a HIIT-SM consisting of 10 HIIT sessions without (HSM, n = 9) or with (HSM + LIT, n = 9) additional low-intensity training or a control group (n = 11). Moreover, we explored relationships between time spent in Z3 determined by running velocity (Z3V), running power (Z3P), heart rate (Z3HR), oxygen uptake ( Z 3 V ˙ O 2 ) and changes in endurance performance.

RESULTS

Both intervention groups revealed a polarized pattern for TIDV (HSM: Z1: 38 ± 17, Z2: 16 ± 17, Z3: 46 ± 2%; HSM + LIT: Z1: 59 ± 18, Z2: 14 ± 18, Z3: 27 ± 2%) and TIDP (Z1: 50 ± 8, Z2: 14 ± 11, Z3: 36 ± 7%; Z1: 62 ± 15, Z2: 12 ± 16, Z3: 26 ± 2%), while TIDHR (Z1: 48 ± 13, Z2: 26 ± 11, Z3: 26 ± 7%; Z1: 65 ± 17, Z2: 22 ± 18, Z3: 13 ± 4%) showed a pyramidal pattern. Time in Z3HR was significantly less compared to Z3V and Z3P in both intervention groups (all p < 0.01). There was a time x intensity measure interaction for time in Z3 across the 10 HIIT sessions for HSM + LIT (p < 0.001, pη2 = 0.30). Time in Z3V and Z3P within each single HIIT session remained stable over the training period for both intervention groups. Time in Z3HR declined in HSM from the first (47%) to the last (28%) session, which was more pronounced in HSM + LIT (45% to 16%). A moderate dose-response relationship was found for time in Z3V and changes in peak power output (rs = 0.52, p = 0.028) as well as time trial performance (rs = - 0.47, p = 0.049) with no such associations regarding time in Z3P, Z3HR, and Z 3 V ˙ O 2 .

CONCLUSION

The present study reveals that the type of intensity measure strongly affects TID computation during a HIIT-SM. As heart rate tends to underestimate the intensity during HIIT-SM, heart rate-based training decisions should be made cautiously. In addition, time in Z3V was most closely associated with changes in endurance performance. Thus, for evaluating a HIIT-SM, we suggest integrating a comprehensive set of intensity measures. Trial Registration Trial register: Clinicaltrials.gov, registration number: NCT05067426.

Increasing region of interest width reduces neonatal circumferential strain

OBJECTIVE

There is growing interest in speckle tracking echocardiography-derived strain as a measure of left ventricular function in neonates. However, knowledge gaps remain regarding the effect of image acquisition and processing parameters on circumferential strain measurements. The aim of this study was to evaluate the effect of using different region of interest (ROI) widths on speckle tracking derived circumferential strain in healthy neonates.

METHODS

Thirty healthy-term-born neonates were examined with speckle-tracking echocardiography in the short-axis view. Circumferential strain values were acquired and compared using two different ROI widths. Furthermore, strain values in the different vendor-defined wall layers were also compared.

RESULTS

Increasing ROI width led to a decrease in global circumferential strain (GCS) in the midwall and epicardial layers, the respective decreases in strain being -23.4 ± .6% to -22.0 ± 1.1%, p < .0001 and 18.5 ± 1.7% to -15.6 ± 2.0%, p < .0001. Segmental analyses were consistent with these results, apart from two segments in the midwall. There was no statistically significant effect on strain for the endocardial layer. A gradient was seen where strain increased from the epicardial to endocardial layers.

CONCLUSION

Increasing ROI width led to a decrease in GCS in the midwall and epicardium. There is an increase in circumferential strain when moving from the epicardial toward the endocardial layer. Clinicians wishing to implement circumferential strain into their practice should consider ROI width variation as a potential confounder in their measurements.

A comprehensive review of applications of artificial intelligence in echocardiography

Echocardiography plays a crucial role in diagnosis of cardiovascular diseases. Artificial intelligence has emerged as a high-precision tool to automate echocardiographic analysis. This review discusses AI algorithms that have been utilized at various steps of echocardiographic analysis such as image acquisition, standard view classification, cardiac chamber segmentation, quantification of cardiac structure and function and aid diagnosis. The under-discussion AI models demonstrated high accuracy comparable to experts in view classification, measurement of cardiac structure and function and diagnosis of conditions such as cardiomyopathies. This review also discusses potential benefits and the value of AI in revolutionizing healthcare. It also explores the limitations such as the lack of large annotated datasets to train AI models and potential algorithm biases making it challenging to translate the benefits of AI into wider clinical practice.

Automatic classification of heart failure based on Cine-CMR images

PURPOSE

Heart failure (HF) is a serious and complex syndrome with a high mortality rate. In clinical diagnosis, the correct classification of HF is helpful. In our previous work, we proposed a self-supervised learning framework of HF classification (SSLHF) on cine cardiac magnetic resonance images (Cine-CMR). However, this method lacks the integration of three dimensions of spatial information and temporal information. Thus, this study aims at proposing an automatic 4D HF classification algorithm.

METHODS

To construct a 4D classification model, we proposed an extensional framework called 4D-SSLHF. It mainly consists of self-supervised image restoration and HF classification. The image restoration proxy task utilizes three image transformation methods to enhance the exploration of spatial and temporal information in the Cine-CMR. In the classification task, we proposed a Siamese Conv-LSTM network by combining the Siamese network and bi-directional Conv-LSTM to integrate the features of the four dimensions simultaneously.

RESULTS

Experimental results on 184 patients from Shanghai Chest Hospital achieved an AUC of 0.8794 and an ACC of 0.8402 in the five-fold cross-validation. Compared with our previous work, the improvements in AUC and ACC were 2.89 % and 1.94 %, respectively.

CONCLUSIONS

In this study, we proposed a novel self-supervised learning framework named 4D-SSLHF for HF classification based on Cine-CMR. The proposed 4D-SSLHF can mine 3D spatial information and temporal information in Cine-CMR images well and accurately classify different categories of HF. The good classification results show our method's potential to assist physicians in choosing personalized treatment.

Factors associated with reporting left ventricular ejection fraction with 3D echocardiography in real-world practice

BACKGROUND

Guidelines recommend 3D echocardiography (3DE) to assess left ventricular ejection fraction (LVEF) on transthoracic echocardiogram (TTE) when possible, but it is unclear which factors are most strongly associated with reporting 3DE LVEF in real-world practice.

METHODS

We evaluated 3DE LVEF reporting by age, sex, BMI, TTE location and variation in reporting by sonographer and reader. All TTEs were performed without contrast enhancement agent at a large medical center from 9/2015 to 12/2020 using ultrasound machines capable of 3DE. We used multivariable logistic regression to assess which factors were most associated with reporting 3DE LVEF.

RESULTS

Among 35 641 TTEs included in this study, 57.4% were performed on women. 3DE LVEF was reported on 18 391 TTEs (51.6% of cohort; 50.5% for women and 52.4% for men). Portable inpatient TTEs (n = 5569) had the lowest rates of 3DE LVEF reporting (30.9%), while general outpatient TTEs (n = 15 933) had greater reporting (56.9%). Outpatient TTEs with an indication for chemotherapy (n = 3244) had the highest rates of 3DE LVEF (87.2%). The median (IQR) percentage of TTEs reporting 3D LVEF was 52.7% (43.1%-68.1%) among sonographers and 51.6% (46.5%-59.6%) among readers. Among 20082 (56.3%) TTEs with 3DE LVEF measured by sonographers, 91.6% were included by readers in the final report. After adjustment, performing sonographer in the highest reporting quartile was most strongly associated with reporting 3DE LVEF (OR 7.04, 95% CI 6.55-7.56), while an inpatient portable study had the strongest negative association for reporting (OR .38, 95% CI .35-.40).

CONCLUSIONS

Use of 3DE LVEF in real-world practice varies substantially based on performing sonographer and is low for hospitalized patients, but can be frequently used for chemotherapy. Initiatives are needed to increase sonographer 3DE acquisition in most clinical settings.

Using Artificial Intelligence for Rheumatic Heart Disease Detection by Echocardiography: Focus on Mitral Regurgitation

BACKGROUND

Identification of children with latent rheumatic heart disease (RHD) by echocardiography, before onset of symptoms, provides an opportunity to initiate secondary prophylaxis and prevent disease progression. There have been limited artificial intelligence studies published assessing the potential of machine learning to detect and analyze mitral regurgitation or to detect the presence of RHD on standard portable echocardiograms.

METHODS AND RESULTS

We used 511 echocardiograms in children, focusing on color Doppler images of the mitral valve. Echocardiograms were independently reviewed by an expert adjudication panel. Among 511 cases, 229 were normal, and 282 had RHD. Our automated method included harmonization of echocardiograms to localize the left atrium during systole using convolutional neural networks and RHD detection using mitral regurgitation jet analysis and deep learning models with an attention mechanism. We identified the correct view with an average accuracy of 0.99 and the correct systolic frame with an average accuracy of 0.94 (apical) and 0.93 (parasternal long axis). It localized the left atrium with an average Dice coefficient of 0.88 (apical) and 0.9 (parasternal long axis). Maximum mitral regurgitation jet measurements were similar to expert manual measurements (P value=0.83) and a 9-feature mitral regurgitation analysis showed an area under the receiver operating characteristics curve of 0.93, precision of 0.83, recall of 0.92, and F1 score of 0.87. Our deep learning model showed an area under the receiver operating characteristics curve of 0.84, precision of 0.78, recall of 0.98, and F1 score of 0.87.

CONCLUSIONS

Artificial intelligence has the potential to detect RHD as accurately as expert cardiologists and to improve with more data. These innovative approaches hold promise to scale echocardiography screening for RHD.

Left Atrial Strain Predicts Stroke Recurrence and Death in Patients With Cryptogenic Stroke

Left atrial strain (LAS) has been widely studied as a predictor of atrial fibrillation (AF) after cryptogenic stroke (CS). However, the evidence about its prognostic role in terms of stroke recurrence and death in this setting remains scarce. A total of 92 consecutive patients with ischemic stroke or transient ischemic attack with ABCD2 scale ≥4 of unknown etiology were prospectively recruited. Echocardiography, including LAS was performed during admission. The primary outcome measure was the composite of stroke recurrence or death. The mean age was 77.5 ± 7.7, and 58% of patients were female. After a median follow up of 28 months, the primary outcome measure occurred in 15 patients (16%). The primary outcome was more frequent in patients with diabetes (53% vs 21%, p = 0.02), chronic kidney disease (33% vs 10%, p = 0.034), and a history of heart failure (13% vs 0%, p = 0.025). LAS reservoir (LASr) and LAS conduit (LAScd) were lower in patients developing the primary outcome (21% ± 7% vs 28.8% ± 11%, p = 0.017 and 7.7% ± 3.9% vs 13.7% ± 7%, p = 0.007, respectively). On multivariate analysis, LASr (hazard ratio 0.9, 95% confidence interval 0.85 to 0.99, p = 0.048) and diabetes (hazard ratio 3.3, 95% confidence interval 1.03 to 10.4, p = 0.045) were associated with stroke recurrence or all-cause death after CS. On the log-rank test (using the discriminatory cut-off value of LASr <23%), LASr (p = 0.009) was associated with higher risk of the primary outcome. In conclusion, lower values of the LAS reservoir were associated with a higher risk of stroke recurrence or death after CS. LAS may identify patients at higher risk of thromboembolism and stress conditions.

Embracing AI: The Imperative Tool for Echo Labs to Stay Ahead of the Curve

Advancements in artificial intelligence (AI) have rapidly transformed various sectors, and the field of echocardiography is no exception. AI-driven technologies hold immense potential to revolutionize echo labs' diagnostic capabilities and improve patient care. This paper explores the importance for echo labs to embrace AI and stay ahead of the curve in harnessing its power. Our manuscript provides an overview of the growing impact of AI on medical imaging, specifically echocardiography. It highlights how AI-driven algorithms can enhance image quality, automate measurements, and accurately diagnose cardiovascular diseases. Additionally, we emphasize the importance of training echo lab professionals in AI implementation to optimize its integration into routine clinical practice. By embracing AI, echo labs can overcome challenges such as workload burden and diagnostic accuracy variability, improving efficiency and patient outcomes. This paper highlights the need for collaboration between echocardiography laboratory experts, AI researchers, and industry stakeholders to drive innovation and establish standardized protocols for implementing AI in echocardiography. In conclusion, this article emphasizes the importance of AI adoption in echocardiography labs, urging practitioners to proactively integrate AI technologies into their workflow and take advantage of their present opportunities. Embracing AI is not just a choice but an imperative for echo labs to maintain their leadership and excel in delivering state-of-the-art cardiac care in the era of advanced medical technologies.

Quantification of Myocardial Contraction Fraction with Three-Dimensional Automated, Machine-Learning-Based Left-Heart-Chamber Metrics: Diagnostic Utility in Hypertrophic Phenotypes and Normal Ejection Fraction

Aims: The differentiation of left ventricular (LV) hypertrophic phenotypes is challenging in patients with normal ejection fraction (EF). The myocardial contraction fraction (MCF) is a simple dimensionless index useful for specifically identifying cardiac amyloidosis (CA) and hypertrophic cardiomyopathy (HCM) when calculated by cardiac magnetic resonance. The purpose of this study was to evaluate the value of MCF measured by three-dimensional automated, machine-learning-based LV chamber metrics (dynamic heart model [DHM]) for the discrimination of different forms of hypertrophic phenotypes. Methods and Results: We analyzed the DHM LV metrics of patients with CA (n = 10), hypertrophic cardiomyopathy (HCM, n = 36), isolated hypertension (IH, n = 87), and 54 healthy controls. MCF was calculated by dividing LV stroke volume by LV myocardial volume. Compared with controls (median 61.95%, interquartile range 55.43-67.79%), mean values for MCF were significantly reduced in HCM-48.55% (43.46-54.86% p < 0.001)-and CA-40.92% (36.68-46.84% p < 0.002)-but not in IH-59.35% (53.22-64.93% p < 0.7). MCF showed a weak correlation with EF in the overall cohort (R2 = 0.136) and the four study subgroups (healthy adults, R2 = 0.039 IH, R2 = 0.089; HCM, R2 = 0.225; CA, R2 = 0.102). ROC analyses showed that MCF could differentiate between healthy adults and HCM (sensitivity 75.9%, specificity 77.8%, AUC 0.814) and between healthy adults and CA (sensitivity 87.0%, specificity 100%, AUC 0.959). The best cut-off values were 55.3% and 52.8%. Conclusions: The easily derived quantification of MCF by DHM can refine our echocardiographic discrimination capacity in patients with hypertrophic phenotype and normal EF. It should be added to the diagnostic workup of these patients.

Heart failure diagnosis in the general community - Who, how and when? A clinical consensus statement of the Heart Failure Association (HFA) of the European Society of Cardiology (ESC)

A significant proportion of patients experience delays in the diagnosis of heart failure due to the non-specific signs and symptoms of the syndrome. Diagnostic tools such as measurement of natriuretic peptide concentrations are fundamentally important when screening for heart failure, yet are frequently under-utilized. This clinical consensus statement provides a diagnostic framework for general practitioners and non-cardiology community-based physicians to recognize, investigate and risk-stratify patients presenting in the community with possible heart failure.

The Use of Artificial Intelligence Guidance for Rheumatic Heart Disease Screening by Novices

INTRODUCTION

A novel technology utilizing artificial intelligence (AI) to provide real-time image-acquisition guidance, enabling novices to obtain diagnostic echocardiographic images, holds promise to expand the reach of echo screening for rheumatic heart disease (RHD). We evaluated the ability of nonexperts to obtain diagnostic-quality images in patients with RHD using AI guidance with color Doppler.

METHODS

Novice providers without prior ultrasound experience underwent a 1-day training curriculum to complete a 7-view screening protocol using AI guidance in Kampala, Uganda. All trainees then scanned 8 to 10 volunteer patients using AI guidance, half RHD and half normal. The same patients were scanned by 2 expert sonographers without the use of AI guidance. Images were evaluated by expert blinded cardiologists to assess (1) diagnostic quality to determine presence/absence of RHD and (2) valvular function and (3) to assign an American College of Emergency Physicians score of 1 to 5 for each view.

RESULTS

Thirty-six novice participants scanned a total of 50 patients, resulting in a total of 462 echocardiogram studies, 362 obtained by nonexperts using AI guidance and 100 obtained by expert sonographers without AI guidance. Novice images enabled diagnostic interpretation in >90% of studies for presence/absence of RHD, abnormal MV morphology, and mitral regurgitation (vs 99% by experts, P ≤ .001). Images were less diagnostic for aortic valve disease (79% for aortic regurgitation, 50% for aortic stenosis, vs 99% and 91% by experts, P < .001). The American College of Emergency Physicians scores of nonexpert images were highest in the parasternal long-axis images (mean, 3.45; 81% ≥ 3) compared with lower scores for apical 4-chamber (mean, 3.20; 74% ≥ 3) and apical 5-chamber images (mean, 2.43; 38% ≥ 3).

CONCLUSIONS

Artificial intelligence guidance with color Doppler is feasible to enable RHD screening by nonexperts, performing significantly better for assessment of the mitral than aortic valve. Further refinement is needed to optimize acquisition of color Doppler apical views.

Echocardiographic evaluation of left ventricular function using an automated analysis algorithm is feasible for beginners and experts: comparison with invasive and non-invasive methods

AIMS

Echocardiographic measurement of left ventricular function using a user-friendly automated three-dimensional algorithm is highly attractive as it promises quick and accurate diagnosis, circumventing limitations associated with visual estimation or manual biplane measurements. We sought to assess the feasibility and correlation of such automated analysis with clinically established methods.

METHODS

A total of 198 patients undergoing transthoracic echocardiography (TTE) with assessment of left ventricular parameters by automated software algorithm (Philips 3D-Heartmodel; 3D-HM) which additionally had either left ventricular angiography (LVA) or cardiac magnetic resonance (CMR) within 24 h of the TTE examination were analyzed. Left ventricular parameters (left ventricular end-diastolic volume, LVEDV, left ventricular end-systolic volume, LVESV as well as left ventricular ejection fraction, LVEF) were compared between 3D-HM, CMR and LVA.

RESULTS

Correlation of left ventricular measurements was overall good to excellent and stronger for CMR (EF r = 0.824) than for LVA (EF r = 0.746). Unexperienced and expert clinicians yielded comparable good results. For CMR, highest correlation was detected in patients with BMI < 25 and excellent image quality. High agreement was seen between 3D-HM and CMR or LVA when stratifying patients according to heart failure categories.

CONCLUSIONS

Echocardiographic quantification of left ventricular parameters using a software-based algorithm correlated well with established invasive and non-invasive modalities in the clinical setting, even for unexperienced clinicians. Such automated approaches are promising as they allow a reliable, more observer-independent as well as reproducible assessment of left ventricular function.

Artificial intelligence in cardiovascular imaging: enhancing image analysis and risk stratification

In this review, we summarize state-of-the-art artificial intelligence applications for non-invasive cardiovascular imaging modalities including CT, MRI, echocardiography, and nuclear myocardial perfusion imaging.

Interchangeability in Left Ventricular Ejection Fraction Measured by Echocardiography and cardiovascular Magnetic Resonance: Not a Perfect Match in the Real World

Comparisons of transthoracic echocardiography (TTE) and cardiovascular magnetic resonance (CMR) derived left ventricular ejection fraction (LVEF) have been reported in core-lab settings but are limited in the real-world setting. We retrospectively identified outpatients from 4 hospital sites who had clinically indicated quantitative assessment of LVEF_TTE and LVEF_CMR and evaluated their concordance. In 767 patients (mean age 47.6 years; 67.9% males) the median inter-modality interval was 35 days. There was significant positive correlation between the 2 modalities (r = 0.75; P < 0.001). Median LVEF was 54% (IQR 47%, 60%) for TTE and 59% (IQR 51%, 64%) for CMR, (P < 0.001). Normal LVEF_TTE was confirmed by CMR in 90.6% of cases. Of patients with severely impaired LVEF_TTE, 42.3% were upwardly reclassified by CMR as less severely impaired. The overall proportion of patients that had their LVEF category confirmed by both imaging modalities was 64.4%; Cohen's Kappa 0.41, indicating fair-to-moderate agreement. Overall, CMR upwardly reclassified 28% of patients using the British Society of Echocardiography LVEF grading, 18.6% using the European Society of Cardiology heart failure classification, and 29.6% using specific reference ranges for each modality. In a multi-site "real-worldˮ clinical setting, there was significant discrepancy between LVEF_TTE and LVEF_CMR measurement. Only 64.4% had their LVEF category confirmed by both imaging modalities. LVEF_TTE was generally lower than LVEF_CMR. LVEF_CMR upwardly reclassified almost half of patients with severe LV dysfunction by LVEF_TTE. Clinicians should consider the inter-modality variation before making therapeutic recommendations, particularly as clinical trial LVEF thresholds have historically been guided by echocardiography.

Risk of recurrent stroke and mortality after cryptogenic stroke in diabetic patients

BACKGROUND

Diabetes mellitus is a highly prevalent and growing chronic disease that is associated with increased risk of recurrence among several stroke subtypes. However, evidence on the prognostic role of diabetes in the setting of cryptogenic stroke (CS) remains scarce.

METHODS

From April 2019 to November 2021, we recruited prospectively 78 consecutive patients with CS. Patients were classified according to the presence of diabetes. Main outcome was the composite of stroke recurrence and death. Secondary outcome was stroke recurrence.

RESULTS

Mean age of the cohort was 78 ± 7.7 years and 18 patients (23%) had diabetes. After a median clinical follow-up of 23 months the incidence of stroke recurrence and mortality [HR 5.8 (95% CI 1.9-19), p = 0.002] and the incidence of stroke recurrence [HR 16.6 (95% CI 1.8-149), p = 0.012], were higher in patients with diabetes. After adjusting for potential confounders diabetes was identified as an independent predictor of stroke recurrence and death in patients with CS [HR 33.8 (95% CI 2.1-551), p = 0.013]. Other independent predictors of stroke recurrence and mortality were hypertension [HR 31.4 (95% CI 1.8-550), p = 0.018], NTproBNP [HR 1.002 (95% CI 1.001-1.004), p = 0.013] and chronic kidney disease (CKD) [HR 27.4 (95% CI 1.4-549) p = 0.03]. Furthermore, diabetes was an independent predictor of stroke recurrence [HR 103 (95% CI 1.3-8261), p = 0.038].

CONCLUSION

Diabetic patients with CS are at higher risk of stroke recurrence and death. Hypertension CKD and NTproBNP are also independent predictors of stroke recurrence and death after CS.

Left ventricular volume and ejection fraction measurements by fully automated 3D echocardiography left chamber quantification software versus CMR: A systematic review and meta-analysis

BACKGROUND

Although transthoracic three-dimensional echocardiography (3DE) is now recommended by guidelines for left ventricular (LV) volumetric measurements, widespread implementation has been limited due to time constraints and required expertise. We hypothesized that fully automated 3DE left chamber quantification software might provide accurate measurements, and that its application could eliminate these obstacles.

METHODS

To address this hypothesis, we conducted a systematic review and meta-analysis following a search for studies that compared LV volumes and ejection fraction (EF) using fully automated 3DE software (HeartModel or Dynamic HeartModel, Philips Healthcare, Andover, MA, USA) with cardiac magnetic resonance (CMR), from 2015 to 2021. A random effects model was used to determine biases, correlations, and 95 % confidence intervals (CI) of LV end-diastolic volume (EDV), end-systolic volume (ESV), and EF. Subgroup and meta-regression analyses were performed to determine effects of moderators on the outcome.

RESULTS

Of 12 studies (616 subjects), mean differences and 95 % CIs in EDV, ESV, and EF between fully automated 3DE software and CMR were -19.6 mL (95 % CI; -27.6 to -11.5 mL), -11.4 mL (-16.7 to -6.2 mL), and 0.4 % (-1.1 to 2.0 %), respectively. Corresponding correlation values between the two methods were 0.91 (0.86-0.94), 0.89 (0.82-0.93), and 0.85 (0.81-0.88), respectively. Meta-regression analysis revealed that there were no effects of either publication year, type of software, or type of analysis on the outcome of LV volumetric and functional parameters except for publication year on LVESV correlation values.

CONCLUSIONS

Although 3DE still underestimates LV volumes, the observed differences were no >20 mL. EF showed similar values to CMR. Excellent correlations between the two techniques make fully automated 3DE left chamber quantification software useful for routine clinical practice in adult population.

MAEF-Net: Multi-attention efficient feature fusion network for left ventricular segmentation and quantitative analysis in two-dimensional echocardiography

The segmentation of cardiac chambers and the quantification of clinical functional metrics in dynamic echocardiography are the keys to the clinical diagnosis of heart disease. Identifying the end-diastolic frames (EDFs) and end-systolic frames (ESFs) and manually segmenting the left ventricle in the echocardiographic cardiac cycle before obtaining the left ventricular ejection fraction (LVEF) is a time-consuming and tedious task for clinicians. In this work, we proposed a deep learning-based fully automated echocardiographic analysis method. We proposed a multi-attention efficient feature fusion network (MAEF-Net) to automatically segment the left ventricle. Then, EDFs and ESFs in all cardiac cycles were automatically detected to compute LVEF. The MAEF-Net method used a multi-attention mechanism to guide the network to capture heartbeat features effectively, while suppressing noise, and incorporated deep supervision mechanism and spatial pyramid feature fusion to enhance feature extraction capabilities. The proposed method was validated on the public EchoNet-Dynamic dataset (n = 1226). The Dice similarity coefficient (DSC) of the left ventricular segmentation reached (93.10 ± 2.22)%, and the mean absolute error (MAE) of cardiac phase detection was (2.36 ± 2.23) frames. The MAE for predicting LVEF was 6.29 %. The proposed method was also validated on a private clinical dataset (n = 22). The DSC of the left ventricular segmentation reached (92.81 ± 2.85)%, and the MAE of cardiac phase detection was (2.25 ± 2.27) frames. The MAE for predicting LVEF was 5.91 %, and the Pearson correlation coefficient r reached 0.96. The proposed method may be used as a new method for automatic left ventricular segmentation and quantitative analysis in two-dimensional echocardiography. Our code and trained models will be made available publicly at https://github.com/xiaojinmao-code/MAEF-Net.

Advancing cardiovascular medicine with machine learning: Progress, potential, and perspective

Recent advances in machine learning (ML) have made it possible to analyze high-dimensional and complex data-such as free text, images, waveforms, videos, and sound-in an automated manner by successfully learning complex associations within these data. Cardiovascular medicine is particularly well poised to take advantage of these ML advances, due to the widespread digitization of medical data and the large number of diagnostic tests used to evaluate cardiovascular disease. Various ML approaches have successfully been applied to cardiovascular tests and diseases to automate interpretation, accurately perform measurements, and, in some cases, predict novel diagnoses from less invasive tests, effectively expanding the utility of more widely accessible diagnostic tests. Here, we present examples of some impactful advances in cardiovascular medicine using ML across a variety of modalities, with a focus on deep learning applications.

Three-Dimensional Automated, Machine-Learning-Based Left Heart Chamber Metrics: Associations with Prevalent Vascular Risk Factors and Cardiovascular Diseases

Background. Three-dimensional transthoracic echocardiography (3DE) powered by artificial intelligence provides accurate left chamber quantification in good accordance with cardiac magnetic resonance and has the potential to revolutionize our clinical practice. Aims. To evaluate the association and the independent value of dynamic heart model (DHM)-derived left atrial (LA) and left ventricular (LV) metrics with prevalent vascular risk factors (VRFs) and cardiovascular diseases (CVDs) in a large, unselected population. Materials and Methods. We estimated the association of DHM metrics with VRFs (hypertension, diabetes) and CVDs (atrial fibrillation, stroke, ischemic heart disease, cardiomyopathies, >moderate valvular heart disease/prosthesis), stratified by prevalent disease status: participants without VRFs or CVDs (healthy), with at least one VRFs but without CVDs, and with at least one CVDs. Results. We retrospectively included 1069 subjects (median age 62 [IQR 49−74]; 50.6% women). When comparing VRFs with the healthy, significant difference in maximum and minimum indexed atrial volume (LAVi max and LAVi min), left atrial ejection fraction (LAEF), left ventricular mass/left ventricular end-diastolic volume ratio, and left ventricular global function index (LVGFI) were recorded (p < 0.05). In the adjusted logistic regression, LAVi min, LAEF, LV ejection fraction, and LVGFI showed the most robust association (OR 3.03 [95% CI 2.48−3.70], 0.45 [95% CI 0.39−0.51], 0.28 [95% CI 0.22−0.35], and 0.22 [95% CI 0.16−0.28], respectively, with CVDs. Conclusions. The present data suggested that novel 3DE left heart chamber metrics by DHM such as LAEF, LAVi min, and LVGFI can refine our echocardiographic disease discrimination capacity.

Echocardiographic Evidence of Cardiac Atrophy in the Critically Ill

The purpose of this explorative study is to determine if critically ill patients experience cardiac atrophy that can be quantified as a loss of left ventricular mass (LVM) and thus detected by echocardiography.

DESIGN

Retrospective single-center cohort study.

SETTING

Patients admitted to a tertiary medical center in Boston, MA.

PATIENTS

Adult critically ill patients with ICU length of stay greater than or equal to 5 days.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

We conducted a retrospective cohort study of 68 patients, of which 42 were included in the final analysis (mean age 60.9 ± 19.2 yr; 47.6% male). The median length of ICU stay was 11.3 days (interquartile range, 6.8-20.1 d). A decrease in mean LVM over the course of admission for critical illness was observed (median 189.11 g [162.82-240.20 g] vs 176.69 g [142.37-226.26 g]; p = 0.01). After adjusting for sex, age, fluid balance, ICU type, dietary orders, time between echocardiograms, and vasopressor use, this decrease in LVM remained consistent (mean difference, -21.30 g; 95% CI, -41.85 to -0.74; p = 0.04). Relative wall thickness (RWT) did not change during admission.

CONCLUSIONS

These data reveal that a loss of LVM is present in patients over their ICU stay without a corresponding change in RWT, consistent with cardiac atrophy. Future prospective studies are needed to confirm these findings and identify possible sequelae of this finding.

Big Data in cardiac surgery: real world and perspectives

Big Data, and the derived analysis techniques, such as artificial intelligence and machine learning, have been considered a revolution in the modern practice of medicine. Big Data comes from multiple sources, encompassing electronic health records, clinical studies, imaging data, registries, administrative databases, patient-reported outcomes and OMICS profiles. The main objective of such analyses is to unveil hidden associations and patterns. In cardiac surgery, the main targets for the use of Big Data are the construction of predictive models to recognize patterns or associations better representing the individual risk or prognosis compared to classical surgical risk scores. The results of these studies contributed to kindle the interest for personalized medicine and contributed to recognize the limitations of randomized controlled trials in representing the real world. However, the main sources of evidence for guidelines and recommendations remain RCTs and meta-analysis. The extent of the revolution of Big Data and new analytical models in cardiac surgery is yet to be determined.

The variability of 2D and 3D transthoracic echocardiography applied in a general population : Intermodality, inter- and intraobserver variability

Assessment of the left ventricular (LV) function by three-dimensional echocardiography (3DE) is potentially superior to 2D echo echocardiography (2DE) for LV performance assessment. However, intra- and interobserver variation needs further investigation. We examined the intra- and interobserver variability between 2 and 3DE in a general population. In total, 150 participants from the Copenhagen City Heart Study were randomly chosen. Two observers assessed left ventricular ejection fraction (LVEF), end-diastolic (EDV) and end-systolic volumes (ESV) by 2DE and 3DE. Inter-, intraobserver and intermodality variabilities are presented as means of difference (MD), limits of agreement (LoA), coefficient of correlation (r), intraclass correlation coefficients (ICC). The lowest MD and LoA and highest r- and ICC-values was generally seen among the 3D acquisitions, with the 3D EDV interobserver as the best performing estimate (r = 0.95, ICC = 0.94). The largest MD, LoA and lowest r- and ICC-values was found in the interobserver 2D LVEF (r = 0.76, ICC = 0.63. For the intraobserver analysis, there were statistically significant differences between observations for all but 3DE EDV (p = 0.06). For interobserver analysis, there were statistically significant differences between observers for all estimates but 2DE EDV (p = 0.11), 3D ejection fraction (p = 0.9), 3DE EDV (p = 0.11) and 3D ESV (p = 0.15). Three-dimensional echocardiography is more robust and reproducible than 2DE and should be preferred for assessment of LV function.

Three-Dimensional Echocardiographic Deconstruction: Feasibility of Clinical Evaluation from Two-Dimensional Views Derived from a Three-Dimensional Data Set

BACKGROUND

Three-dimensional echocardiography (3DE) makes it possible to capture the entire heart in a single data set that theoretically could be used to extract any two-dimensional (2D) views and potentially replace the standard practice of serial 2D acquisitions. The aim of this study was to test the hypothesis that the quality of 3DE-derived 2D images is sufficient to allow the visualization of the left ventricular (LV), right ventricular (RV), and left atrial (LA) endocardium, on par with images from conventional two-dimensional echocardiography (2DE), and potentially more accurate quantification of chamber size and function.

METHODS

First, the investigators prospectively studied 36 patients who underwent 2DE in 14 standard views, and full-volume data sets from 3DE, from which the same views were extracted offline. The ability to visualize the LV endocardium, RV free wall, and LA endocardium was scored. LV linear dimensions, LV volumes, and LV ejection fraction (LVEF), LA volume, and RV basal dimension were measured and compared between both types of images. Thereafter, 40 patients who underwent 2DE, 3DE, and cardiac magnetic resonance (CMR) imaging on the same day were retrospectively studied. LV volumes and LVEF derived from 2DE and 3DE were compared side by side against the CMR reference.

RESULTS

Intertechnique agreement in visualization scores was 87% for LV segments, 86% for the RV free wall, and 83% for the LA endocardium. The correlations between 2DE- and 3DE-derived measurements were 0.95, 0.97, and 0.97 for LV volumes and LVEF, respectively, and 0.88 for RV basal dimension. Three-dimensional echocardiography-derived measurements of LV volumes and LVEF were more similar to those on CMR than those obtained on conventional 2DE.

CONCLUSIONS

The feasibility of segmental assessment of cardiac chambers using 3DE-derived 2D views is similar to that using conventional 2DE. This approach provides similar quantitative information, including more accurate LV volumes and LVEF measurements compared with CMR, and thus promises to significantly shorten the duration of the echocardiographic examination.

Comparison between Automatic and Semiautomatic System for the 3D Echocardiographic Multiparametric Evaluation of RV Function and Dimension

Background: The right ventricle (RV) plays a pivotal role in cardiovascular diseases and 3-dimensional echocardiography (3DE) has gained acceptance for the evaluation of RV volumes and function. Recently, a new artificial intelligence (AI)–based automated 3DE software for RV evaluation has been proposed and validated against cardiac magnetic resonance. The aims of this study were three-fold: (i) feasibility of the AI-based 3DE RV quantification, (ii) comparison with the semi-automatic 3DE method and (iii) assessment of 2-dimensional echocardiography (2DE) and strain measurements obtained automatically. Methods: A total of 203 subject (122 normal and 81 patients) underwent a 2DE and both the semi-automatic and automatic 3DE methods for Doppler standard, RV volumes and ejection fraction (RVEF) measurements. Results: The automatic 3DE method was highly feasible, faster than 2DE and semi-automatic 3DE and data obtained were comparable with traditional measurements. Both in normal subjects and patients, the RVEF was similar to the two 3DE methods and 2DE and strain measurements obtained by the automated system correlated very well with the standard 2DE and strain ones. Conclusions: results showed that rapid analysis and excellent reproducibility of AI-based 3DE RV analysis supported the routine adoption of this automated method in the daily clinical workflow.

The Salzburg 10/7 HIIT shock cycle study: the effects of a 7-day high-intensity interval training shock microcycle with or without additional low-intensity training on endurance performance, well-being, stress and recovery in endurance trained athletes-study protocol of a randomized controlled trial

BACKGROUND

Performing multiple high-intensity interval training (HIIT) sessions in a compressed period of time (approximately 7-14 days) is called a HIIT shock microcycle (SM) and promises a rapid increase in endurance performance. However, the efficacy of HIIT-SM, as well as knowledge about optimal training volumes during a SM in the endurance-trained population have not been adequately investigated. This study aims to examine the effects of two different types of HIIT-SM (with or without additional low-intensity training (LIT)) compared to a control group (CG) on key endurance performance variables. Moreover, participants are closely monitored for stress, fatigue, recovery, and sleep before, during and after the intervention using innovative biomarkers, questionnaires, and wearable devices.

METHODS

This is a study protocol of a randomized controlled trial that includes the results of a pilot participant. Thirty-six endurance trained athletes will be recruited and randomly assigned to either a HIIT-SM (HSM) group, HIIT-SM with additional LIT (HSM + LIT) group or a CG. All participants will be monitored before (9 days), during (7 days), and after (14 days) a 7-day intervention, for a total of 30 days. Participants in both intervention groups will complete 10 HIIT sessions over 7 consecutive days, with an additional 30 min of LIT in the HSM + LIT group. HIIT sessions consist of aerobic HIIT, i.e., 5 × 4 min at 90-95% of maximal heart rate interspersed by recovery periods of 2.5 min. To determine the effects of the intervention, physiological exercise testing, and a 5 km time trial will be conducted before and after the intervention.

RESULTS

The feasibility study indicates good adherence and performance improvement of the pilot participant. Load monitoring tools, i.e., biomarkers and questionnaires showed increased values during the intervention period, indicating sensitive variables.

CONCLUSION

This study will be the first to examine the effects of different total training volumes of HIIT-SM, especially the combination of LIT and HIIT in the HSM + LIT group. In addition, different assessments to monitor the athletes' load during such an exhaustive training period will allow the identification of load monitoring tools such as innovative biomarkers, questionnaires, and wearable technology.

TRIAL REGISTRATION

clinicaltrials.gov, NCT05067426. Registered 05 October 2021-Retrospectively registered, https://clinicaltrials.gov/ct2/show/NCT05067426 . Protocol Version Issue date: 1 Dec 2021. Original protocol. Authors: TLS, NH.

Three-dimensional echocardiographic assessment of left ventricular volume in different heart diseases using a fully automated quantification software

BACKGROUND

HeartModel (HM) is a fully automated adaptive quantification software that can quickly quantify left heart volume and left ventricular function. This study used HM to quantify the left ventricular end-diastolic (LVEDV) and end-systolic volumes (LVESV) of patients with dilated cardiomyopathy (DCM), coronary artery heart disease with segmental wall motion abnormality, and hypertrophic cardiomyopathy (HCM) to determine whether there were differences in the feasibility, accuracy, and repeatability of measuring the LVEDV, LVESV, LV ejection fraction (LVEF) and left atrial end-systolic volume (LAESV) and to compare these measurements with those obtained with traditional two-dimensional (2D) and three-dimensional (3D) methods.

AIM

To evaluate the application value of HM in quantifying left heart chamber volume and LVEF in clinical patients.

METHODS

A total of 150 subjects who underwent 2D and 3D echocardiography were divided into 4 groups: (1) 42 patients with normal heart shape and function (control group, Group A); (2) 35 patients with DCM (Group B); (3) 41 patients with LV remodeling after acute myocardial infarction (Group C); and (4) 32 patients with HCM (Group D). The LVEDV, LVESV, LVEF and LAESV obtained by HM with (HM-RE) and without regional endocardial border editing (HM-NE) were compared with those measured by traditional 2D/3D echocardiographic methods to assess the correlation, consistency, and repeatability of all methods.

RESULTS

(1) The parameters measured by HM were significantly different among the groups (P < 0.05 for all). Compared with Groups A, C, and D, Group B had higher LVEDV and LVESV (P < 0.05 for all) and lower LVEF (P < 0.05 for all); (2) HM-NE overestimated LVEDV, LVESV, and LAESV with wide biases and underestimated LVEF with a small bias; contour adjustment reduced the biases and limits of agreement (bias: LVEDV, 28.17 mL, LVESV, 14.92 mL, LAESV, 8.18 mL, LVEF, -0.04%). The correlations between HM-RE and advanced cardiac 3D quantification (3DQA) (r_s = 0.91-0.95, P < 0.05 for all) were higher than those between HM-NE (r_s = 0.85-0.93, P < 0.05 for all) and the traditional 2D methods. The correlations between HM-RE and 3DQA were good for Groups A, B, and C but remained weak for Group D (LVEDV and LVESV, r_s = 0.48-0.54, P < 0.05 for all); and (3) The intraobserver and interobserver variability for the HM-RE measurements were low.

CONCLUSION

HM can be used to quantify the LV volume and LVEF in patients with common heart diseases and sufficient image quality. HM with contour editing is highly reproducible and accurate and may be recommended for clinical practice.

Real-time three-dimensional echocardiography and two-dimensional speckle tracking imaging in the evaluation of left atrial function in patients with triple-vessel coronary artery disease without myocardial infarction

OBJECTIVE

To evaluate left atrial function in patients with triple-vessel disease (TVD) without myocardial infarction by real-time three-dimensional echocardiography (RT-3DE) and two-dimensional speckle tracking imaging (2D-STE).

METHODS

Sixty patients with coronary artery disease (CAD) without myocardial infarction were classified into two groups in accordance with the coronary angiography results: group B (all triple-vessel stenosis ≥ 50% and < 75%) and group C (all triple-vessel stenosis ≥ 75%). Thirty healthy individuals were selected as group A. LA volume related parameters including left atrial maximum volume index (LAVImax), LA passive and active ejection fraction (LAPEF, LAAEF) and LA total ejection fraction (LATEF) were measured by RT-3DE. The global peak atrial longitudinal systolic strain (LASRs), early and late diastolic LA strain (LASRe and LASRa) rates were measured by 2D-STE.

RESULTS

We found statistically significant differences between 2D-STE and RT-3DE related parameters of these three groups. Furthermore, in groups B and C, N-terminal fragment brain natriuretic peptides (NT-pro-BNP) and left ventricular end-diastolic pressure (LVEDP) were found to be significantly correlated with LASRs and LASRa. And NT-pro-BNP had a moderate correlation with LVEDP.

CONCLUSIONS

2D-STE and RT-3DE can assess the LA function in patients with TVD without myocardial infarction. And LA strain values may provide additional information for predicting increased LVEDP and NT-pro-BNP.

Additional value of left atrium remodeling assessed by three-dimensional echocardiography for the prediction of atrial fibrillation recurrence after cryoballoon ablation

Cryoballoon ablation (CBA) is a safe and efficient therapeutic option for atrial fibrillation (AF). However, AF recurrence occurs in 25% of the patients, leading to repeated ablations and complications. Previous reports have shown that left atrium (LA) assessed by M-Mode and two-dimensional echocardiography (2DE) predicts AF recurrence. Nevertheless, these methods imply geometrical assumptions of the LA remodeling, which is a three-dimensional process. We hypothesized that LA remodeling by three-dimensional echocardiography (3DE) has an additional value for AF recurrence prediction post-CBA. 172 consecutive patients (62.2 ± 12.2 years, 61% male) were prospectively recruited. Echocardiography was performed before CBA. Blanking period was defined as the first three months post-ablation. The primary endpoint was AF recurrence after the blanking period. 50 (29%) patients had AF recurrence. 3DE LA maximum volume index (LAVI) had the highest incremental predictive value for AF recurrence (HR 5.50, 95% CI 1.34 -22.45, p < 0.001). In patients with non-dilated LA diameter index and LAVI by 2DE, LAVI by 3DE was able to discriminate AF recurrence with a sensitivity of 90% and a specificity of 66%, for an optimal cut-off value of 30.4 ml/m2. LA remodeling by 3DE predicted AF recurrence, even in patients with non-dilated LA by M-Mode and 2DE, suggesting that 3DE might reflect better and earlier the asymmetric and variable nature of LA remodeling and it should be considered for systematic use to evaluate AF recurrence risk post-CBA.

Left Heart Chamber Volumetric Assessment by Automated Three-Dimensional Echocardiography in Heart Transplant Recipients

Background

Recently, a new automated software (Heart Model) was developed to obtain three-dimensional (3D) left heart chamber volumes. The aim of this study was to verify the feasibility and accuracy of the automated 3D echocardiographic algorithm in heart transplant (HTx) patients. Conventional manual 3D transthoracic echocardiographic (TTE) tracings and cardiac magnetic resonance (CMR) images were used as a reference for comparison.

Methods

This study enrolled 103 healthy HTx patients prospectively. In protocol 1, left ventricular end-diastolic volume (LVEDV), LV end-systolic volume (LVESV), left atrial max volume (LAVmax), LA minimum volume (LAVmin) and LV ejection fraction (LVEF) were obtained using the automated 3D echocardiography (3DE) and compared with corresponding values obtained through the manual 3DE. In protocol 2, 28 patients’ automated 3DE measurements were compared with CMR reference values. The impacts of contour edit and surgical technique were also tested.

Results

Heart Model was feasible in 97.1% of the data sets. In protocol 1, there was strong correlation between 3DE and manual 3DE for all the parameters (r = 0.77 to 0.96, p<0.01). Compared to values obtained through manual measurements, LV volumes and LVEF were overestimated by the automated algorithm and LA volumes were underestimated. All the biases were small except for that of LAVmin. After contour adjustment, the biases reduced and all the limits of agreement were clinically acceptable. In protocol 2, the correlations for LV and LA volumes were strong between automated 3DE with contour edit and CMR (r = 0.74 to 0.93, p<0.01) but correlation for LVEF remained moderate (r = 0.65, p < 0.01). Automated 3DE overestimated LV volumes but underestimated LVEF and LA volumes compared with CMR. The limits of agreement were clinically acceptable only for LVEDV and LAVmax.

Conclusion

Simultaneous quantification of left heart volumes and LVEF with the automated Heart Model program is rapid, feasible and to a great degree it is accurate in HTx recipients. Nevertheless, only LVEDV and LAVmax measured by automated 3DE with contour edit seem applicable for clinical practice when compared with CMR. Automated 3DE for HTx recipients is a worthy attempt, though further verification and optimization are needed.

Quantification of chronic aortic regurgitation using left and right ventricular stroke volumes obtained from two new automated three-dimensional transthoracic echocardiographic software: feasibility and accuracy

The present study aimed to evaluate the feasibility and accuracy of chronic aortic regurgitation (CAR) quantification using left and right ventricular stroke volumes (LVSV and RVSV, respectively) obtained from two new automated three-dimensional transthoracic echocardiographic software-Dynamic HeartModel (DHM) and 3D Auto RV. Patients (n=116) with more than mild isolated CAR were included and divided into two groups: central (n=53) and eccentric CAR (n=63) groups. LVSV and RVSV were automatically measured by DHM and 3D Auto RV. Next, aortic regurgitant volume (ARVol) was calculated three ways: as the difference between LVSV and RVSV, by the two-dimensional proximal isovelocity surface area (PISA) method, and using effective regurgitant orifice area derived from real-time three-dimensional echocardiography (RT3DE) multiplied by CAR velocity time integral (the reference standard). DHM plus 3D Auto RV correlated well with RT3DE in ARVol measurement in both groups (central, r = 0.90; eccentric, r = 0.96), with no significant difference based on consistency analysis. In the eccentric group, PISA led to an obvious underestimation (mean difference= - 4.20 ml, P < 0.05). The kappa agreement between DHM plus 3D Auto RV and RT3DE in grading CAR severity in both groups was good (central, k = 0.89; eccentric, k = 0.86), but that between PISA and RT3DE in the eccentric CAR group was suboptimal (k = 0.74). This study indicates that ARVol quantification using DHM plus 3D Auto RV is feasible and reproducible in patients with more than mild isolated CAR. This new method has great correlation and agreement with RT3DE in ARVol measurement, with evident advantages over PISA in eccentric CAR.

Automated three-dimensional echocardiographic quantification for left ventricular volume and function in patients with hypertrophic cardiomyopathy

BACKGROUND

Accurate, reproducible, noninvasive determination of left ventricular (LV) volumes and ejection fraction (EF) is important for clinical assessment, selection of therapy, and serial monitoring of patients with hypertrophic cardiomyopathy (HCM). Current clinical Two-dimensional echocardiography (2DE) may cause inaccurate measurements in patients with HCM because of their asymmetric ventricles and limitations of 2DE technology. Three-dimensional echocardiography (3DE) have demonstrated significantly greater accuracy. However, the time-consuming workflow limits the clinical utility of 3DE.

AIM

We aim to compare the performance of a novel automated 3DE system (HeartModel, Philips Healthcare) with 2DE in a group of patients with HCM. Cardiac magnetic resonance (CMR) was reference standard.

METHODS

Fifty-three patients with HCM were examined by automated 3DE (3DEA), two-dimensional biplane Simpson's method (2DBP), manual 3DE method, and CMR, respectively. For patients with poor automated quantification, manual correction was performed. The Pearson correlation coefficient and Bland-Altman analysis and paired Student t tests were used to assess inter-technique agreement.

RESULTS

3DEA measurements with contour editing correlate well with CMR and manual 2DE and 3DE measurements (r = .80-.96). The analysis time of 3DEA was shorter than that of 2DBP (3DEA, 141 ± 15s; 2DBP, 174 ± 17 s). Inter-observer variability was reduced significantly with use of 3DEA.

CONCLUSION

Compared with current clinical 2DBP method, the analysis time of automated 3DE was much shorter with the added benefit of enhanced accuracy and reproducibility. Patients with asymmetric chamber may rely more on the timesaving automated 3DE quantification in the future.

Three-Dimensional Echocardiography Assessment of Right Ventricular Volumes and Function: Technological Perspective and Clinical Application

Right ventricular (RV) function has important prognostic value in a variety of cardiovascular diseases. Due to complex anatomy and mode of contractility, conventional two-dimensional echocardiography does not provide sufficient and accurate RV function assessment. Currently, three-dimensional echocardiography (3DE) allows for an excellent and reproducible assessment of RV function owing to overcoming these limitations of traditional echocardiography. This review focused on 3DE and discussed the following points: (i) acquisition of RV dataset for 3DE images, (ii) reliability, feasibility, and reproducibility of RV volumes and function measured by 3DE with different modalities, (iii) the clinical application of 3DE for RV function quantification.

Artificial Intelligence in Echocardiography

Artificial intelligence in diagnostic cardiac-imaging platforms is advancing rapidly. In particular, artificial intelligence algorithms have increased the efficiency and accuracy of echocardiographic cardiovascular imaging, resulting in more complex echocardiographic imaging techniques and expanded use among noncardiologists. Here, we provide an overview of real-world applications of artificial intelligence in echocardiography including automatic high-quality computer-optimized image acquisition sequences, automated measurements, and algorithms for the rapid and accurate interpretation of cardiac physiology. These advances will not replace physicians but will improve their productivity, workflow, and diagnostic performance.

Short-term memory neural network-based cognitive computing in sports training complexity pattern recognition

With the development of Chinese sports, many sports training researchers try to use artificial intelligence technology to study the training methods and training elements of athletes. However, in reality, these methods are often based on different basic training principles, resulting in the reduction in the generalization ability of artificial intelligence networks. This paper studies the complexity of sports training principles by using an artificial intelligence network model. Based on the improved model of dropout optimization algorithm, this paper proposes an artificial intelligence sports training node prediction method based on the combination of dropout optimization algorithm and short-term memory neural network (LSTM), which avoids the establishment of complex sports training models. Based on artificial intelligence operation and maintenance records and sports training core capacity experimental data, the maximum node static estimation of artificial intelligence sports training is realized. The research shows that the node prediction model is established by using the method described in this paper. Through experimental comparison and analysis, the model has high prediction accuracy. Due to the state memory function of LSTM, it has advantages in the prediction of 2000 data on a long time scale. The mean absolute error percentage of the prediction results is less than 3.4%, and the maximum absolute error percentage is less than 5.2%. The artificial intelligence network model in this paper has good generalization ability. Compared with other models, the model proposed in this paper can get more accurate prediction results in sports training of different groups and effectively alleviate the problem of overfitting. Therefore, traditional stadiums and gymnasiums should actively introduce artificial intelligence technology with a more positive attitude, to realize the development and innovation in technology application, service innovation, management efficiency, and function integration.

Standardization of normal values for cardiac chamber size in echocardiography

Echocardiography is used worldwide to evaluate cardiac size and function. To determine what values are abnormal, it is essential to establish normal reference values for echocardiography. The current guidelines for chamber quantification specify normative values for cardiac chambers and recommend that gender and body size be taken into account. However, these normative data were established using databases for which a variety of measurement methods were used and the majority of subjects consisted of Whites in Europe and the United States. However, several regional studies from other countries suggest that cardiac size varies globally. To overcome these limitations, the Normal Reference Ranges for Echocardiography study and the World Alliance of Societies of Echocardiography Normal Values study have recently been conducted to examine similarities and differences in cardiac chamber size and to establish normal reference values while taking worldwide diversity into account. The results from these studies have demonstrated that standardization of normal reference values for cardiac size is important. This review article aims to summarize the current status of normative echocardiographic values for cardiac chamber size.

AI and the cardiologist: when mind, heart and machine unite

Artificial intelligence (AI) and deep learning has made much headway in the consumer and advertising sector, not only affecting how and what people purchase these days, but also affecting behaviour and cultural attitudes. It is poised to influence nearly every aspect of our being, and the field of cardiology is not an exception. This paper aims to brief the clinician on the advances in AI and machine learning in the field of cardiology, its applications, while also recognising the potential for future development in these two mammoth fields. With the advent of big data, new opportunities are emerging to build AI tools, with better accuracy, that will directly aid not only the clinician but also allow nations to provide better healthcare to its citizens.

Heart Model A.I. Three-Dimensional Echocardiographic Evaluation of Left Ventricular Function and Parameter Setting

Objective

This study aims to explore the feasibility of HeartModel ^A.I. (HM) three-dimensional echocardiography (3DE) to assess left ventricular function and discover suitable border parameter settings.

Methods

A total of 113 patients that underwent echocardiography in our hospital were eligible for inclusion. The HM 3DE (HM method) and conventional 3DE (3D method) were used to analyze echocardiography images. The HM was set to different border settings (end-diastolic [ED] and end-systolic [ES] settings) to assess different left ventricular systolic function parameters including left ventricular end diastolic volume (LVEDV), left ventricular end systolic volume (LVESV), and left ventricular ejection fraction (LVEF), and left ventricular diastolic function parameters including maximal left atrium volume (LAV_MAX). All of these parameters were evaluated using the HM method and then compared with the 3D method.

Results

The differences in LVEDV, LVESV, and LVEF measured with different HM border settings were statistically significant (P<0.05) and were strongly correlated with the 3D method. For LVEF, the reading using the HM method with ED and ES = 70 and 30 showed the best agreement with the 3D method, and the difference in the readings was not statistically significant (P > 0.05). For LVEDV and LVESV, the reading using the HM method with ED and ES = 40 and 20 showed the best agreement with the 3D method, but the difference in the readings was statistically significant (P < 0.05). The measurements taken using the HM method were more reproducible than those taken using the 3D method (P<0.05). The measurement time when using the HM method was significantly less than the 3D method (P<0.05). In terms of LAV_MAX, the correlation between the HM and 3D methods was strong, but the requirements for agreement were not satisfied.

Conclusion

Evaluation of the left ventricular function using HM 3DE is feasible, saves time, and is reproducible. To assess the left ventricular function, the border parameter setting of ED and ES = 70 and 30 provided the best fit for the Chinese population.

Feasibility and Accuracy of a Fully Automated Right Ventricular Quantification Software With Three-Dimensional Echocardiography: Comparison With Cardiac Magnetic Resonance

Background: A novel, fully automated right ventricular (RV) software for three-dimensional quantification of RV volumes and function was developed. The direct comparison of the software performance with cardiac magnetic resonance (CMR) was limited. Therefore, the aim of this study was to test the feasibility, accuracy, and reproducibility of a fully automated RV quantification software against CMR imaging as a reference.

Methods: A total of 170 patients who underwent both CMR and three-dimensional echocardiography were enrolled. RV end-diastolic volume (RVEDV), RV end-systolic volume (RVESV), and RV ejection fraction (RVEF) were obtained using fully automated three-dimensional RV quantification software and compared with a CMR reference. For inter-technical agreement, Spearman correlation and Bland–Altman analysis were used.

Results: The fully automated RV quantification software was feasible in 149 patients. RVEDV and RVESV were underestimated, and RVEF was overestimated compared with CMR values. RV measurements obtained from the manual editing method correlated better with CMR values than that without manual editing (RVEDV, 0.924 vs. 0.794: RVESV, 0.955 vs. 0.854; RVEF, 0.941 vs. 0.781 respectively, all p < 0.0001) with less bias and narrower limit of agreement (LOA). The bias and LOA for RV volumes and EF using the automated software without and with manual editing were greater in patients with severely impaired RV function or low frame rate than those with normal and mild impaired RV function, or high frame rate. The fully automated RV three-dimensional measurements were highly reproducible.

Conclusion: The novel fully automated RV software shows good feasibility and reproducibility, and the measurements had a high correlation with CMR values. These findings support the routine application of the novel 3D automated RV software in clinical practice.

The Use of Artificial Intelligence in Automation in the Fields of Gynaecology and Obstetrics - an Assessment of the State of Play

The long-awaited progress in digitalisation is generating huge amounts of medical data every day, and manual analysis and targeted, patient-oriented evaluation of this data is becoming increasingly difficult or even infeasible. This state of affairs and the associated, increasingly complex requirements for individualised precision medicine underline the need for modern software solutions and algorithms across the entire healthcare system. The utilisation of state-of-the-art equipment and techniques in almost all areas of medicine over the past few years has now indeed enabled automation processes to enter - at least in part - into routine clinical practice. Such systems utilise a wide variety of artificial intelligence (AI) techniques, the majority of which have been developed to optimise medical image reconstruction, noise reduction, quality assurance, triage, segmentation, computer-aided detection and classification and, as an emerging field of research, radiogenomics. Tasks handled by AI are completed significantly faster and more precisely, clearly demonstrated by now in the annual findings of the ImageNet Large-Scale Visual Recognition Challenge (ILSVCR), first conducted in 2015, with error rates well below those of humans. This review article will discuss the potential capabilities and currently available applications of AI in gynaecological-obstetric diagnostics. The article will focus, in particular, on automated techniques in prenatal sonographic diagnostics.

Feasibility and Accuracy of the Automated Software for Dynamic Quantification of Left Ventricular and Atrial Volumes and Function in a Large Unselected Population

We aimed to evaluate the feasibility and accuracy of machine learning-based automated dynamic quantification of left ventricular (LV) and left atrial (LA) volumes in an unselected population. We enrolled 600 unselected patients (12% in atrial fibrillation) clinically referred for transthoracic echocardiography (2DTTE), who also underwent 3D echocardiography (3DE) imaging. LV ejection fraction (EF), LV, and LA volumes were obtained from 2D images; 3D images were analyzed using dynamic heart model (DHM) software (Philips) resulting in LV and LA volume–time curves. A subgroup of 140 patients also underwent cardiac magnetic resonance (CMR) imaging. Average time of analysis, feasibility, and image quality were recorded, and results were compared between 2DTTE, DHM, and CMR. The use of DHM was feasible in 522/600 cases (87%). When feasible, the boundary position was considered accurate in 335/522 patients (64%), while major (n = 38) or minor (n = 149) border corrections were needed. The overall time required for DHM datasets was approximately 40 seconds. As expected, DHM LV volumes were larger than 2D ones (end-diastolic volume: 173 ± 64 vs. 142 ± 58 mL, respectively), while no differences were found for LV EF and LA volumes (EF: 55% ± 12 vs. 56% ± 14; LA volume 89 ± 36 vs. 89 ± 38 mL, respectively). The comparison between DHM and CMR values showed a high correlation for LV volumes (r = 0.70 and r = 0.82, p < 0.001 for end-diastolic and end-systolic volume, respectively) and an excellent correlation for EF (r = 0.82, p < 0.001) and LA volumes. The DHM software is feasible, accurate, and quick in a large series of unselected patients, including those with suboptimal 2D images or in atrial fibrillation.

Artificial intelligence in echocardiography: detection, functional evaluation, and disease diagnosis

Ultrasound is one of the most important examinations for clinical diagnosis of cardiovascular diseases. The speed of image movements driven by the frequency of the beating heart is faster than that of other organs. This particularity of echocardiography poses a challenge for sonographers to diagnose accurately. However, artificial intelligence for detection, functional evaluation, and disease diagnosis has gradually become an alternative for accurate diagnosis and treatment using echocardiography. This work discusses the current application of artificial intelligence in echocardiography technology, its limitations, and future development directions.

Artificial intelligence and cardiovascular imaging: A win-win combination

Rapid development of artificial intelligence (AI) is gaining grounds in medicine. Its huge impact and inevitable necessity are also reflected in cardiovascular imaging. Although AI would probably never replace doctors, it can significantly support and improve their productivity and diagnostic performance. Many algorithms have already proven useful at all stages of the cardiac imaging chain. Their crucial practical applications include classification, automatic quantification, notification, diagnosis, and risk prediction. Consequently, more reproducible and repeatable studies are obtained, and personalized reports may be available to any patient. Utilization of AI also increases patient safety and decreases healthcare costs. Furthermore, AI is particularly useful for beginners in the field of cardiac imaging as it provides anatomic guidance and interpretation of complex imaging results. In contrast, lack of interpretability and explainability in AI carries a risk of harmful recommendations. This review was aimed at summarizing AI principles, essential execution requirements, and challenges as well as its recent applications in cardiovascular imaging.

Hemodynamic Heterogeneity of Reduced Cardiac Reserve Unmasked by Volumetric Exercise Echocardiography

Background: Two-dimensional volumetric exercise stress echocardiography (ESE) provides an integrated view of left ventricular (LV) preload reserve through end-diastolic volume (EDV) and LV contractile reserve (LVCR) through end-systolic volume (ESV) changes. Purpose: To assess the dependence of cardiac reserve upon LVCR, EDV, and heart rate (HR) during ESE. Methods: We prospectively performed semi-supine bicycle or treadmill ESE in 1344 patients (age 59.8 ± 11.4 years; ejection fraction = 63 ± 8%) referred for known or suspected coronary artery disease. All patients had negative ESE by wall motion criteria. EDV and ESV were measured by biplane Simpson rule with 2-dimensional echocardiography. Cardiac index reserve was identified by peak-rest value. LVCR was the stress-rest ratio of force (systolic blood pressure by cuff sphygmomanometer/ESV, abnormal values ≤2.0). Preload reserve was defined by an increase in EDV. Cardiac index was calculated as stroke volume index * HR (by EKG). HR reserve (stress/rest ratio) <1.85 identified chronotropic incompetence. Results: Of the 1344 patients, 448 were in the lowest tertile of cardiac index reserve with stress. Of them, 303 (67.6%) achieved HR reserve <1.85; 252 (56.3%) had an abnormal LVCR and 341 (76.1%) a reduction of preload reserve, with 446 patients (99.6%) showing ≥1 abnormality. At binary logistic regression analysis, reduced preload reserve (odds ratio [OR]: 5.610; 95% confidence intervals [CI]: 4.025 to 7.821), chronotropic incompetence (OR: 3.923, 95% CI: 2.915 to 5.279), and abnormal LVCR (OR: 1.579; 95% CI: 1.105 to 2.259) were independently associated with lowest tertile of cardiac index reserve at peak stress. Conclusions: Heart rate assessment and volumetric echocardiography during ESE identify the heterogeneity of hemodynamic phenotypes of impaired chronotropic, preload or LVCR underlying a reduced cardiac reserve.

The effect of intravenous ferric carboxymaltose on cardiac reverse remodelling following cardiac resynchronization therapy-the IRON-CRT trial

Aims

Iron deficiency is common in heart failure with reduced ejection fraction (HFrEF) and negatively affects cardiac function and structure. The study the effect of ferric carboxymaltose (FCM) on cardiac reverse remodelling and contractile status in HFrEF.

Methods and results

Symptomatic HFrEF patients with iron deficiency and a persistently reduced left ventricular ejection fraction (LVEF <45%) at least 6 months after cardiac resynchronization therapy (CRT) implant were prospectively randomized to FCM or standard of care (SOC) in a double-blind manner. The primary endpoint was the change in LVEF from baseline to 3-month follow-up assessed by three-dimensional echocardiography. Secondary endpoints included the change in left ventricular end-systolic (LVESV) and end-diastolic volume (LVEDV) from baseline to 3-month follow-up. Cardiac performance was evaluated by the force–frequency relationship as assessed by the slope change of the cardiac contractility index (CCI = systolic blood pressure/LVESV index) at 70, 90, and 110 beats of biventricular pacing. A total of 75 patients were randomized to FCM (n = 37) or SOC (n = 38). At baseline, both treatment groups were well matched including baseline LVEF (34 ± 7 vs. 33 ± 8, P = 0.411). After 3 months, the change in LVEF was significantly higher in the FMC group [+4.22%, 95% confidence interval (CI) +3.05%; +5.38%] than in the SOC group (−0.23%, 95% CI −1.44%; +0.97%; P < 0.001). Similarly, LVESV (−9.72 mL, 95% CI −13.5 mL; −5.93 mL vs. −1.83 mL, 95% CI −5.7 mL; 2.1 mL; P = 0.001), but not LVEDV (P = 0.748), improved in the FCM vs. the SOC group. At baseline, both treatment groups demonstrated a negative force–frequency relationship, as defined by a decrease in CCI at higher heart rates (negative slope). FCM resulted in an improvement in the CCI slope during incremental biventricular pacing, with a positive force–frequency relationship at 3 months. Functional status and exercise capacity, as measured by the Kansas City Cardiomyopathy Questionnaire and peak oxygen consumption, were improved by FCM.

Conclusions

Treatment with FCM in HFrEF patients with iron deficiency and persistently reduced LVEF after CRT results in an improvement of cardiac function measured by LVEF, LVESV, and cardiac force–frequency relationship.

Prognostic value of the left ventricular - left atrial volume ratio assessed using three-dimensional echocardiography with fully automated analytical software

BACKGROUND

we investigated the prognostic value of a new 3D echocardiography (3DE) parameter, the left ventricular-left atrial volume ratio (LVLAVR) in a diverse group of subjects.

METHODS

3DE full-volume datasets were analyzed in 307 patients using fully automated LV and LA quantification software (Dynamic Heart Model, Philips Medical Systems, Andover, MA, USA), which generated LV and LA volume curves using artificial intelligence and 3D speckle tracking technology. We measured LVLAVR at LV end-diastole (edLVLAVR; LV end-diastolic volume / LA minimal volume), LVLAVR at LV end-systole (esLVLAVR: LV end-systolic volume / LA maximal volume), and their differences (ΔLVLAVR: edLVLAVR - esLVLAVR). No manual editing was performed on data of any patient. The primary endpoint was a major adverse cardiac event (MACE), including cardiac death, heart failure resulting in hospitalization, myocardial infarction, or ventricular tachyarrhythmia.

RESULTS

feasibility of LVLAVR measurements was 90%. During a median follow-up of 21 months, 43 patients developed a primary endpoint. Univariate Cox proportional hazard analysis revealed that edLVLAVR [hazard ratio (HR): 0.72, p < 0.01] and ΔLVLAVR (HR: 0.62, p < 0.01) were significantly associated with MACE. Median values of both edLVLAVR (4.59) and ΔLVLAVR (2.90) successfully stratified patients into high- and low-risk populations for future MACEs. ΔLVLAVR was still significantly associated with MACEs after adjusting for age, chronic kidney disease (CKD) and LV ejection fraction or after adjusting for age, CKD, and E/ε'.

CONCLUSIONS

LVLAVR provided incremental value over traditional LV systolic and diastolic function parameters to predict future adverse outcomes. The analysis was fully automated, thereby eliminating measurement variability.