Calculation Of Left Ventricular Ejection Fraction Research Articles

Development of automated neural network prediction for echocardiographic left ventricular ejection fraction.

The echocardiographic measurement of left ventricular ejection fraction (LVEF) is fundamental to the diagnosis and classification of patients with heart failure (HF). This paper aimed to quantify LVEF automatically and accurately with the proposed pipeline method based on deep neural networks and ensemble learning. Within the pipeline, an Atrous Convolutional Neural Network (ACNN) was first trained to segment the left ventricle (LV), before employing the area-length formulation based on the ellipsoid single-plane model to calculate LVEF values. This formulation required inputs of LV area, derived from segmentation using an improved Jeffrey's method, as well as LV length, derived from a novel ensemble learning model. To further improve the pipeline's accuracy, an automated peak detection algorithm was used to identify end-diastolic and end-systolic frames, avoiding issues with human error. Subsequently, single-beat LVEF values were averaged across all cardiac cycles to obtain the final LVEF. This method was developed and internally validated in an open-source dataset containing 10,030 echocardiograms. The Pearson's correlation coefficient was 0.83 for LVEF prediction compared to expert human analysis (p < 0.001), with a subsequent area under the receiver operator curve (AUROC) of 0.98 (95% confidence interval 0.97 to 0.99) for categorisation of HF with reduced ejection (HFrEF; LVEF<40%). In an external dataset with 200 echocardiograms, this method achieved an AUC of 0.90 (95% confidence interval 0.88 to 0.91) for HFrEF assessment. The automated neural network-based calculation of LVEF is comparable to expert clinicians performing time-consuming, frame-by-frame manual evaluations of cardiac systolic function.

Artificial intelligence-assisted evaluation of cardiac function by oncology staff in chemotherapy patients.

Left ventricular ejection fraction (LVEF) calculation by echocardiography is pivotal in evaluating cancer patients' cardiac function. Artificial intelligence (AI) can facilitate the acquisition of optimal images and automated LVEF (autoEF) calculation. We sought to evaluate the feasibility and accuracy of LVEF calculation by oncology staff using an AI-enabled handheld ultrasound device (HUD). We studied 115 patients referred for echocardiographic LVEF estimation. All patients were scanned by a cardiologist using standard echocardiography (SE), and biplane Simpson's LVEF was the reference standard. Hands-on training using the Kosmos HUD was provided to the oncology staff before the study. Each patient was scanned by a cardiologist, a senior oncologist, an oncology resident, and a nurse using the TRIO AI and KOSMOS EF deep learning algorithms to obtain autoEF. The correlation between autoEF and SE-ejection fraction (EF) was excellent for the cardiologist (r = 0.90), the junior oncologist (r = 0.82), and the nurse (r = 0.84), and good for the senior oncologist (r = 0.79). The Bland-Altman analysis showed a small underestimation by autoEF compared with SE-EF. Detection of impaired LVEF < 50% was feasible with a sensitivity of 95% and specificity of 94% for the cardiologist; sensitivity of 86% and specificity of 93% for the senior oncologist; sensitivity of 95% and specificity of 91% for the junior oncologist; and sensitivity of 94% and specificity of 87% for the nurse. Automated LVEF calculation by oncology staff was feasible using AI-enabled HUD in a selected patient population. Detection of LVEF < 50% was possible with good accuracy. These findings show the potential to expedite the clinical workflow of cancer patients and speed up a referral when necessary.

Artificial intelligence calculated global longitudinal strain and left ventricular ejection fraction predicts cardiac events and all-cause mortality in patients with chest pain.

Assessment of left ventricular ejection fraction (LVEF) and myocardial deformation with global longitudinal strain (GLS) has shown promise in predicting adverse cardiovascular events. The aim of this study was to evaluate whether artificial intelligence (AI) calculated LVEF and GLS is associated with major adverse cardiac events (MACE) and all-cause mortality in patients presenting with chest pain. We studied 296 patients presenting with chest pain, who underwent transthoracic echocardiography (TTE). Clinical data, downstream clinical investigations and patient outcomes were collected. Resting TTE images underwent AI contouring for automated calculation of LVEF and GLS with Ultromics EchoGo Core 2.0. Regression analysis was performed to identify clinical and AI calculated parameters associated with MACE and all-cause mortality. During a median follow-up period of 7.8 years (IQR 6.4, 8.8), MACE occurred in 34 (11.5%) patients and all-cause mortality in 60 (20%) patients. AI calculated LVEF (Odds Ratio [OR] .96; 95% CI .93-.99 and .96; 95% CI .93-.99) and GLS (1.11; 95% CI 1.01-1.21 and 1.08; 95% CI 1.00-1.16) were independently associated with MACE and all-cause mortality, respectively. According to Cox proportional hazards, a LVEF<50% was associated with a 3.7 times MACE and 2.8 times all-cause mortality hazard rate compared to those with a LVEF≥50%. Those with a GLS≥15% was associated with a 2.5 times MACE and 2.3 times all-cause mortality hazard rate compared to those with a GLS≤15. AI calculated resting LVEF and GLS is independently associated with MACE and all-cause mortality in high CVD risk patients. These results may have significant clinical implications through improved risk stratification of patients with chest pain, accelerated workflow of labour-intensive technical measures, and reduced healthcare costs.

Left-ventricular volumes and ejection fraction from cardiac ECG-gated 15O-water positron emission tomography compared to cardiac magnetic resonance imaging using simultaneous hybrid PET/MR

Background15O-water PET is the gold standard for noninvasive quantification of myocardial blood flow. In addition to evaluation of ischemia, the assessment of cardiac function and remodeling is important in all cardiac diseases. However, since 15O-water is freely diffusible and standard uptake images show little contrast between the myocardium and blood pool, the assessment of left-ventricular (LV) volumes and ejection fraction (EF) is challenging. Therefore, the aim of the present study was to investigate the feasibility of calculating LV volumes and EF from first-pass analysis of 15O-water PET, by comparison with cardiac magnetic resonance imaging (CMR) using a hybrid PET/MR scanner. MethodsTwenty-four patients with known or suspected CAD underwent a simultaneous ECG-gated cardiac PET/MR scan. The 15O-water first-pass images (0-50 seconds) were analyzed using the CarPET software and the CMR images were analyzed using the software Segment, for LV volumes and EF calculations. The LV volumes and EF were compared using correlation and Bland–Altman analysis. In addition, inter- and intra-observer variability of LV volumes and EF were assessed for both modalities. ResultsThe correlation between PET and CMR was strong for volumes (r > 0.84) and moderate for EF (r = 0.52), where the moderate correlation for EF was partly due to the small range of EF values. Agreement was high for all parameters, with a slight overestimation of PET values for end-diastolic volume but with no significant mean bias for other parameters. Inter- and intra-observer agreement of volumes was high and comparable between PET and CMR. For EF, inter-observer agreement was higher for PET and intra-observer agreement was higher for CMR. ConclusionLV volumes and EF can be calculated by first-pass analysis of a 15O-water PET scan with high accuracy and comparable precision as with CMR.

Artificial intelligence based left ventricular ejection fraction and global longitudinal strain in cardiac amyloidosis.

Assessment of left ventricular ejection fraction (LVEF) and global longitudinal strain (GLS) plays a key role in the diagnosis of cardiac amyloidosis (CA). However, manual measurements are time consuming and prone to variability. We aimed to assess whether fully automated artificial intelligence (AI) calculation of LVEF and GLS provide similar estimates and can identify abnormalities in agreement with conventional manual methods, in patients with pre-clinical and clinical CA. We identified 51 patients (age 80±10 years, 53% male) with confirmed CA according to guidelines, who underwent echocardiography before and/or at the time of CA diagnosis (median (IQR) time between observations 3.87 (1.93, 5.44 years). LVEF and GLS were quantified from the apical 2- and 4-chamber views using both manual and fully automated methods (EchoGo Core 2.0, Ultromics). Inter-technique agreement was assessed using linear regression and Bland-Altman analyses and two-way ANOVA. The diagnostic accuracy and time for detecting abnormalities (defined as LVEF ≤ 50% and GLS ≥ -15.1%, respectively) using AI was assessed by comparisons to manual measurements as a reference. There were no significant differences in manual and automated LVEF and GLS values in either pre-CA (p=.791 and p=.105, respectively) or at diagnosis (p=.463 and p=.722). The two methods showed strong correlation on both the pre-CA (r=.78 and r=.83) and CA echoes (r=.74 and r=.80) for LVEF and GLS, respectively. The sensitivity and specificity of AI-derived indices for detecting abnormal LVEF were 83% and 86%, respectively, in the pre-CA echo and 70% and 79% at CA diagnosis. The sensitivity and specificity of AI-derived indices for detecting abnormal GLS was 82% and 86% in the pre-CA echo and 100% and 67% at the time of CA diagnosis. There was no significant difference in the relationship between LVEF (p=.99) and GLS (p=.19) and time to abnormality between the two methods. Fully automated AI-calculated LVEF and GLS are comparable to manual measurements in patients pre-CA and at the time of CA diagnosis. The widespread implementation of automated LVEF and GLS may allow for more rapid assessment in different disease states with comparable accuracy and reproducibility to manual methods.

Left ventricular assessment with artificial intelligence increases the diagnostic accuracy of stress echocardiography.

AimsTo evaluate whether left ventricular ejection fraction (LVEF) and global longitudinal strain (GLS), automatically calculated by artificial intelligence (AI), increases the diagnostic performance of stress echocardiography (SE) for coronary artery disease (CAD) detection.Methods and resultsSEs from 512 participants who underwent a clinically indicated SE (with or without contrast) for the evaluation of CAD from seven hospitals in the UK and US were studied. Visual wall motion scoring (WMS) was performed to identify inducible ischaemia. In addition, SE images at rest and stress underwent AI contouring for automated calculation of AI-LVEF and AI-GLS (apical two and four chamber images only) with Ultromics EchoGo Core 1.0. Receiver operator characteristic curves and multivariable risk models were used to assess accuracy for identification of participants subsequently found to have CAD on angiography. Participants with significant CAD were more likely to have abnormal WMS, AI-LVEF, and AI-GLS values at rest and stress (all P < 0.001). The areas under the receiver operating characteristics for WMS index, AI-LVEF, and AI-GLS at peak stress were 0.92, 0.86, and 0.82, respectively, with cut-offs of 1.12, 64%, and −17.2%, respectively. Multivariable analysis demonstrated that addition of peak AI-LVEF or peak AI-GLS to WMS significantly improved model discrimination of CAD [C-statistic (bootstrapping 2.5th, 97.5th percentile)] from 0.78 (0.69–0.87) to 0.83 (0.74–0.91) or 0.84 (0.75–0.92), respectively.ConclusionAI calculation of LVEF and GLS by contouring of contrast-enhanced and unenhanced SEs at rest and stress is feasible and independently improves the identification of obstructive CAD beyond conventional WMSI.

New advances in medical imaging technology for the evaluation of anthracycline-induced cardiotoxicity.

New advances in medical imaging technology for the evaluation of anthracycline-induced cardiotoxicity.

Machine learning algorithm using publicly available echo database for simplified "visual estimation" of left ventricular ejection fraction.

BACKGROUNDLeft ventricular ejection fraction calculation automation typically requires complex algorithms and is dependent of optimal visualization and tracing of endocardial borders. This significantly limits usability in bedside clinical applications, where ultrasound automation is needed most.AIMTo create a simple deep learning (DL) regression-type algorithm to visually estimate left ventricular (LV) ejection fraction (EF) from a public database of actual patient echo examinations and compare results to echocardiography laboratory EF calculations. METHODSA simple DL architecture previously proven to perform well on ultrasound image analysis, VGG16, was utilized as a base architecture running within a long short term memory algorithm for sequential image (video) analysis. After obtaining permission to use the Stanford EchoNet-Dynamic database, researchers randomly removed approximately 15% of the approximately 10036 echo apical 4-chamber videos for later performance testing. All database echo examinations were read as part of comprehensive echocardiography study performance and were coupled with EF, end systolic and diastolic volumes, key frames and coordinates for LV endocardial tracing in csv file. To better reflect point-of-care ultrasound (POCUS) clinical settings and time pressure, the algorithm was trained on echo video correlated with calculated ejection fraction without incorporating additional volume, measurement and coordinate data. Seventy percent of the original data was used for algorithm training and 15% for validation during training. The previously randomly separated 15% (1263 echo videos) was used for algorithm performance testing after training completion. Given the inherent variability of echo EF measurement and field standards for evaluating algorithm accuracy, mean absolute error (MAE) and root mean square error (RMSE) calculations were made on algorithm EF results compared to Echo Lab calculated EF. Bland-Atlman calculation was also performed. MAE for skilled echocardiographers has been established to range from 4% to 5%. RESULTSThe DL algorithm visually estimated EF had a MAE of 8.08% (95%CI 7.60 to 8.55) suggesting good performance compared to highly skill humans. The RMSE was 11.98 and correlation of 0.348. CONCLUSIONThis experimental simplified DL algorithm showed promise and proved reasonably accurate at visually estimating LV EF from short real time echo video clips. Less burdensome than complex DL approaches used for EF calculation, such an approach may be more optimal for POCUS settings once improved upon by future research and development.

Use of artificial intelligence for real-time automatic quantification of left ventricular ejection fraction by a novel handheld ultrasound device

Abstract Funding Acknowledgements Type of funding sources: Other. Main funding source(s): Hellenic Society of Cardiology Background/Introduction: Transthoracic echocardiography is the most widely used imaging modality for the assessment of left ventricular ejection fraction (LVEF), which is crucial for patient care and management. Most recently, artificial intelligence (AI) has been employed to automatically identify LV endocardial boundaries and calculate LVEF. Technological advancements have enabled the development of small handheld ultrasound devices (HUDs) that can provide echocardiographic images at the point of care; however until now the HUDs have presented limited quantification capabilities. The application of AI algorithms to point-of-care echocardiography may facilitate the acquisition and accurate interpretation of a high volume of imaging data in real-time. Purpose To evaluate the accuracy of a novel HUD with AI-assisted algorithm (autoEF) to automatically calculate LVEF. Methods We prospectively included consecutive patients who were referred to a tertiary hospital echocardiography laboratory for a standard echocardiography examination. The modified biplane Simpson’s method was used to determine LV volumes and function from the apical four-chamber and apical two-chamber views. All patients were subsequently scanned with the Kosmos HUD and a fully automated estimation of the LVEF was possible after acquisition of the same two apical views within seconds by the device itself with the use of the AI-assisted autoEF algorithm. The image quality for each examination was assessed and classified as good, moderate and poor. The autoEF measurements were compared head-to-head with the manually traced biplane Simpson’s rule measurements on cart-based systems as the reference standard, using linear regression and Bland-Altman analysis. Results The study comprised 100 consecutive patients (57 ± 15 years old, 61% male), including 38 patients with abnormal LVEF &amp;lt; 50%. The image quality for the cart-based systems acquisition was assessed as good in 45%, moderate in 50% and poor in 5% of patients and for the HUD acquisition as good in 31%, moderate in 57% and poor in 12% of patients. AutoEF measurement by AI-assisted algorithm was feasible in all patients with LVEF measurements on cart-based systems. There was good agreement between the reference standard and Kosmos autoEF algorithm with a correlation coefficient r = 0.87, 95%CI 0.81-0.91, (p &amp;lt; 0.0001). The corresponding Bland-Altman plot showed a small non-significant bias of -1.42% (p = 0.058), with limits of agreement ±14.5% for the auto-EF. The paired comparison of the LVEF calculation by the 2 methods did not reveal a significant difference between reference standard and HUD autoEF [56% (IQR 40% - 62%) vs 53% (IQR 43% - 59%) respectively, p = 0.106]. Conclusion The AI-assisted autoEF algorithm in a novel HUD can accurately calculate LVEF in real-time as compared to the recommended manual biplane Simpson’s method on cart-based systems in an "all-comers" patient population. Abstract Figure. Correlation plot for LVEF measurements Abstract Figure. Bland-Altman plot

Prognostic value of cardiovascular magnetic resonance left ventricular volumetry and geometry in patients receiving an implantable cardioverter defibrillator

BackgroundCurrent indications for implantable cardioverter defibrillator (ICD) implantation for sudden cardiac death prevention rely primarily on left ventricular (LV) ejection fraction (LVEF). Currently, two different contouring methods by cardiovascular magnetic resonance (CMR) are used for LVEF calculation. We evaluated the comparative prognostic value of these two methods in the ICD population, and if measures of LV geometry added predictive value.MethodsIn this retrospective, 2-center observational cohort study, patients underwent CMR prior to ICD implantation for primary or secondary prevention from January 2005 to December 2018. Two readers, blinded to all clinical and outcome data assessed CMR studies by: (a) including the LV trabeculae and papillary muscles (TPM) (trabeculated endocardial contours), and (b) excluding LV TPM (rounded endocardial contours) from the total LV mass for calculation of LVEF, LV volumes and mass. LV sphericity and sphere-volume indices were also calculated. The primary outcome was a composite of appropriate ICD shocks or death.ResultsOf the 372 consecutive eligible patients, 129 patients (34.7%) had appropriate ICD shock, and 65 (17.5%) died over a median duration follow-up of 61 months (IQR 38–103). LVEF was higher when including TPM versus excluding TPM (36% vs. 31%, p < 0.001). The rate of appropriate ICD shock or all-cause death was higher among patients with lower LVEF both including and excluding TPM (p for trend = 0.019 and 0.004, respectively). In multivariable models adjusting for age, primary prevention, ischemic heart disease and late gadolinium enhancement, both LVEF (HR per 10% including TPM 0.814 [95%CI 0.688–0.962] p = 0.016, vs. HR per 10% excluding TPM 0.780 [95%CI 0.639–0.951] p = 0.014) and LV mass index (HR per 10 g/m2 including TPM 1.099 [95%CI 1.027–1.175] p = 0.006; HR per 10 g/m2 excluding TPM 1.126 [95%CI 1.032–1.228] p = 0.008) had independent prognostic value. Higher LV end-systolic volumes and LV sphericity were significantly associated with increased mortality but showed no added prognostic value.ConclusionBoth CMR post-processing methods showed similar prognostic value and can be used for LVEF assessment. LVEF and indexed LV mass are independent predictors for appropriate ICD shocks and all-cause mortality in the ICD population.

Evaluation of idiopathic dilated cardiomyopathy with cardiac magnetic resonance imaging

Purpose: The present study was aimed to assess the prevalence, location, and patterns of late gadolinium enhancement (LGE) in idiopathic dilated cardiomyopathy (DCM) on cardiac magnetic resonance (CMR) imaging and to correlate the left ventricular (LV) functions obtained by cine CMR with the values obtained by echocardiography. Methods: This was a prospective single-center study covering a 2-year study period. The authors studied the prevalence, location, and patterns of LGE in idiopathic DCM on CMR and correlated the ventricular functions obtained by CMR with those obtained by echocardiography. Results: LGE was seen in 18/40 (45%) and was absent in 22/40 (55%) of patients. With regard to location, septal enhancement was the most common, seen in 8 (20%) followed by free-wall enhancement in 4 (10%) and a concomitant septal and free-wall enhancement in 6 (15%). In terms of pattern, midwall enhancement was observed in 10 (25%), subepicardial in 2 (5%), subendocardial in 4 (10%), and focal and transmural enhancement in 1 each. The maximum correlation for calculation of LV ejection fraction (EF) was obtained between CMR and two-dimensional echocardiography (P = 0.442). Conclusion: CMR is an accurate tool to determine the phenotype of DCM by identifying the presence, location, and pattern of LGE which has a prognostic value and is used to guide management. CMR is the most accurate assessment tool for the calculation of EF and other volumetric variables in DCM.

A machine learning algorithm supports ultrasound-na\xefve novices in the acquisition of diagnostic echocardiography loops and provides accurate estimation of LVEF

Left ventricular ejection fraction (LVEF) is the most important parameter in the assessment of cardiac function. A machine-learning algorithm was trained to guide ultrasound-novices to acquire diagnostic echocardiography images. The artificial intelligence (AI) algorithm then estimates LVEF from the captured apical-4-chamber (AP4), apical-2-chamber (AP2), and parasternal-long-axis (PLAX) loops. We sought to test this algorithm by having first-year medical students without previous ultrasound knowledge scan real patients. Nineteen echo-naïve first-year medical students were trained in the basics of echocardiography by a 2.5 h online video tutorial. Each student then scanned three patients with the help of the AI. Image quality was graded according to the American College of Emergency Physicians scale. If rated as diagnostic quality, the AI calculated LVEF from the acquired loops (monoplane and also a “best-LVEF” considering all views acquired in the particular patient). These LVEF calculations were compared to images of the same patients captured and read by three experts (ground-truth LVEF [GT-EF]). The novices acquired diagnostic-quality images in 33/57 (58%), 49/57 (86%), and 39/57 (68%) patients in the PLAX, AP4, and AP2, respectively. At least one of the three views was obtained in 91% of the attempts. We found an excellent agreement between the machine’s LVEF calculations from images acquired by the novices with the GT-EF (bias of 3.5% ± 5.6 and r = 0.92, p < 0.001 in the “best-LVEF” algorithm). This pilot study shows first evidence that a machine-learning algorithm can guide ultrasound-novices to acquire diagnostic echo loops and provide an automated LVEF calculation that is in agreement with a human expert.

MR T2* Evaluation of the Hepatic and Myocardial Iron Deposition in Thalasemia Major Patients and the Correlation of the Results with Serum Ferritin Levels and Cardiac Functions

INTRODUCTION: The purpose of this study was to evaluate the correlation between myocardial iron deposition and cardiac functions along with the correlations between myocardial iron deposition, hepatic iron deposition and serum ferritin levels in beta thalasemia major patients. METHODS: 145 beta thalasemia major patients (85 males and 60 females age between 9-53 years) between March 2016 and September 2018 and were retrospectively evaluated. T2* calculations were done for the heart and the liver. For functional evaluation of the heart, left ventricular ejection fraction calculation and wall motion analysis were done. The serum ferritin levels between 20-250 ng/ml were accepted as normal. The correlation between myocardial iron deposition and cardiac functions as well as the correlations between myocardial iron deposition, hepatic iron deposition and serum ferritin levels were statistically evaluated. RESULTS: The statistical analysis revealed a significant correlation between cardiac functional abnormalities and the severity of myocardial iron deposition. A statistically significant correlation was also found between myocardial iron deposition and serum ferritin levels in regard of both the presence and severity. Similarly, hepatic iron deposition and serum ferritin levels were found to be correlated. On the other hand, no statistically significant correlation was detected between hepatic and cardiac iron accumulations. DISCUSSION AND CONCLUSION: MRI is an accurate tool to quantatively evaluate hepatic and myocardial iron deposition in thalasemia major patients. The periodical follow up of patients with MRI examinations for hepatic and myocardial iron deposition in addition to serum ferritin levels may help to modify the treatment in patients with transfusion dependent anemias.

Determinants of left ventricular ejection fraction and a novel method to improve its assessment of myocardial contractility

BackgroundThe aim of this study was to quantify the impact of different cardiovascular factors on left ventricular ejection fraction (LVEF) and test a novel LVEF calculation considering these factors.Results10 pigs were studied. The experimental protocol consisted of sequentially changing afterload, preload and contractility. LV pressure–volume (PV) loops and peripheral arterial pressure were obtained before and after each intervention. LVEF was calculated as stroke volume (SV)/end-diastolic volume (EDV). We studied global cardiac function variables: LV end-systolic elastance (Ees), effective arterial elastance (Ea), end-diastolic volume and heart rate. Diastolic function was evaluated by means of the ventricular relaxation time (τ) and ventricular stiffness constant (β) obtained from the end-diastolic PV relationship. Ventriculo-arterial coupling (VAC), an index of cardiovascular performance, was calculated as Ea/Ees. LV mechanical efficiency (LVeff) was calculated as the ratio of stroke work to LV pressure–volume area. A linear mixed model was used to determine the impact of cardiac factors (Ees, Ea, EDV and heart rate), VAC and LVeff on LVEF during all experimental conditions. LVEF was mainly related to Ees and Ea. There was a strong relationship between LVEF and both VAC and LVeff (r2 = 0.69 and r2 = 0.94, respectively). The relationship between LVEF and Ees was good (r2 = 0.43). Adjusting LVEF to afterload ({text{LVEF}}_{rm EA} = {text{EF}} times sqrt {text{Ea}}) performed better for estimating Ees (r2 = 0.75) and improved the tracking of LV contractility changes, even when a peripheral Ea was used as surrogate (Ea = radial MAP/SV; r2 = 0.73).ConclusionsLVEF was mainly affected by contractility and afterload changes and was strongly related to VAC and LVeff. An adjustment to LVEF that considers the impact of afterload provided a better assessment of LV contractility.

Automatic biplane left ventricular ejection fraction estimation with mobile point-of-care ultrasound using multi-task learning and adversarial training.

Left ventricular ejection fraction (LVEF) is one of the key metrics to assess the heart functionality, and cardiac ultrasound (echo) is a standard imaging modality for EF measurement. There is an emerging interest to exploit the point-of-care ultrasound (POCUS) usability due to low cost and ease of access. In this work, we aim to present a computationally efficient mobile application for accurate LVEF estimation. Our proposed mobile application for LVEF estimation runs in real time on Android mobile devices that have either a wired or wireless connection to a cardiac POCUS device. We propose a pipeline for biplane ejection fraction estimation using apical two-chamber (AP2) and apical four-chamber (AP4) echo views. A computationally efficient multi-task deep fully convolutional network is proposed for simultaneous LV segmentation and landmark detection in these views, which is integrated into the LVEF estimation pipeline. An adversarial critic model is used in the training phase to impose a shape prior on the LV segmentation output. The system is evaluated on a dataset of 427 patients. Each patient has a pair of captured AP2 and AP4 echo studies, resulting in a total of more than 40,000 echo frames. The mobile system reaches a noticeably high average Dice score of 92% for LV segmentation, an average Euclidean distance error of 2.85 pixels for the detection of anatomical landmarks used in LVEF calculation, and a median absolute error of 6.2% for LVEF estimation compared to the expert cardiologist's annotations and measurements. The proposed system runs in real time on mobile devices. The experiments show the effectiveness of the proposed system for automatic LVEF estimation by demonstrating an adequate correlation with the cardiologist's examination.

Left Ventricular Ejection Fraction Assessment: Unraveling the Bias between Area- and Volume-based Estimates.

Calculating left ventricular ejection fraction (LVEF) accurately is crucial for the clinical diagnosis of cardiac disease, patient management, or other therapeutic treatment decisions. The measure of a patient's LVEF often affects their candidacy for cardiovascular intervention. Ultrasound (US) is one of the imaging modalities used to non-invasively assess LVEF, and it is the most common and least expensive. Despite the advances in 3D US transducer technology, only limited US machines are equipped with such transducer to enable true 3D US image acquisition. Thus, 2D US images remain to be widely used by cardiologists to image the heart and their interpretation is inherently based on two dimensional information immediately available in the US images. Past knowledge indicates that visual estimation of the LVEF based on the area changes of the left ventricle blood pool between systole and diastole (as depicted in 2D ultrasound images) may significantly underestimate the ejection fraction, rendering some patients as suitable candidates for potentially unnecessary interventions or implantation of assistive devices. True LVEF should be calculated based on changes in LV volumes, but equipment and time constraint limit the current technique to assess 3D LV geometry. The estimation of the systolic and diastolic blood pool volumes requires additional work beyond a simple visual assessment of the blood pool area changed in the 2D US images. Specifically, following the manual segmentation of the endocardial LV border, 3D volume would be assessed by reconstructing a LV volume from multiple tomographic views. In this work, we leverage on two idealized mathematical models of the left ventricle - a truncated prolate spheroid (TPS) and a paraboloid geometric model to characterize the LV shape according to the range of possible dimensions gathered from our patient-specific multi-plane US imaging data. The objective of this work is to reveal the necessity of calculating LVEFs based on volumes by showing that LVEF estimated using area changes underestimate the LVEF computed using volume changes. Additionally, we present a method to reconstruct the LV volume from 2D blood pool representations identified in the multi-plane 2D US images and use the reconstructed 3D volume throughout the cardiac cycle to estimate the LVEF. Our preliminary results show that the area-based LVEF significantly underestimates the true volume-based LVEF across both the theoretical simulations using idealized geometric models of the LV shape, as well as the patient-specific US imaging data. Specifically, both the TPS and paraboloid model showed an area-based LVEF of 41.3 ± 4.7% and a volume-based LVEF of 55.4 ± 5.7%, while the US image data showed an area-based LVEF of 34.7 ± 11.9% and a volume-based LVEF of 48.0 ± 14.0%. In summary, the area-based LVEF estimations using both the idealized TPS and paraboloid models was 14.1% lower than volume- based LVEF calculations using corresponding models. Furthermore, the area-based LVEF based on reconstructed LV volumes are 13.3% lower than volume-based estimates. Evidently, there is a need to further investigate a method to enable practical volume-based LVEF calculations to avoid the need for clinicians to estimate LVEF based on visual, holistic assessment of the blood pool area changes that improperly infer volumetric blood pool changes.

Heart Failure With Preserved, Mid-Range, and Reduced Ejection Fraction

The European Society of Cardiology (ESC) recently published new guidelines for the diagnosis and treatment of acute and chronic heart failure (HF).1 The new nomenclature includes separating patients with HF into 3 distinct groups depending on the left ventricular ejection fraction (LVEF): preserved LVEF (≥50%), mid-range LVEF (40–49%), and reduced LVEF (≤40%). Although there have been several studies that argue for and against stratifying HF patients by LVEF, the latest guidelines continue to focus mainly on the LVEF as the central determinant of prognosis in HF. However, further characterization of HF phenotype using etiology, comorbidities, and nonresponse to therapy among the 3 proposed groups are not incorporated into the definition. It is important to identify pathophysiological mechanisms and specific etiologies that underlie the clinical status, beyond the simplistic definition of preserved, mid-range, and reduced LVEF. Moreover, the term “preserved” could be misleading and confusing: quite comforting and mistakenly reassuring. As observed in the literature and in clinical practice, patients with preserved LVEF may have worse prognosis in terms of rehospitalization and mortality. Furthermore, it is necessary to highlight that the determination of LVEF from 2D echocardiographic images with Simpson’s biplane technique is relatively unreliable, with intra and interobserver variability of up to 13% and 15%, respectively, because of foreshortened views and geometric assumptions.2 Moreover, LVEF calculation is sensitive to changes in hemodynamic loading conditions. This is what occurs in patients with mitral regurgitation who have preserved LVEF despite severe ventricular dysfunction.3,4 The consequence of such variability in measurement and sensitivity to loading conditions may lead to a significant overlap among the 3 proposed categories that are separated by only a few percentage points. Moreover, calculating LVEF is considered a simple method to estimate ventricular function, but in fact it may be too simplistic. In the management of HF patients, it is more important to focus on ventricular function estimated by chamber volumes and pressures, as well as by Doppler flows and tissue Doppler imaging (TDI). In fact, in our opinion, the key means by which to determine the prognosis of HF patients involves establishing the presence or absence of ventricular dysfunction, that could be (1) systolic, ie, with increased ventricular volumes; (2) diastolic, ie, with abnormalities in transmitral and pulmonary veins flows, in TDI mitral annular velocities, and in left atrium volume; or (3) systo-diastolic, ie, including features of both systolic and diastolic dysfunction. The presence of systolic, diastolic, or systo-diastolic ventricular dysfunction determines low cardiac output, which is the crucial pathophysiological element of HF.

Radiation reduction and faster acquisition times with SPECT gated blood pool scans using a high-efficiency cardiac SPECT camera

BackgroundPlanar gated blood pool scans are an established method for the evaluation of left ventricular ejection fraction (LVEF) but the camera technology used for these studies has not significantly changed in decades. The purpose of this study was to determine the diagnostic accuracy of new high-efficiency SPECT gated blood pool scans compared to traditional scans and determine if they can be performed with lower radiation doses or faster acquisition times. MethodsPatients undergoing a planar gated blood pool scan on a Na-I SPECT camera who consented to participate were subsequently imaged for 5 minutes in “List Mode” using a high-efficiency SPECT camera. LVEF was calculated for both the planar study and at 1, 2, 3, 4, and 5 minutes of acquisition on the high-efficiency camera. Counts acquired in the field of view, counts in the cardiac blood pool and LVEF were compared. ResultsA total of 46 patients were analyzed (48% male, mean age 55 years, and BMI 27.6 kg/m2) who received an average Tc-99m dose of 20.3 mCi (5.3 mSv), 17 (37%) with abnormal LVEF’s. The Na-I camera averaged 24,514 counts/min/mCi in the field of view and 8662 counts/min/mCi in the cardiac blood pool while the high-efficiency camera averaged 65,219 counts/min/mCi and 41,427 counts/min/mCi, respectively. Compared to the planar calculation of LVEF, 1-minute SPECT LVEF was on average 8.6 ± 10.7 higher, 2 minutes 3.5 ± 7.6 higher, 3 minutes 2.9 ± 8.5 higher, 4 minutes 2.5 ± 7.0 higher, and 5 minutes 1.1 ± 6.2 higher. Good correlation was seen between the SPECT LVEF’s and the planar LVEF’s across all acquisition times with correlation coefficients of 0.74-0.93. ConclusionsHigh-efficiency SPECT technology can reduce radiation exposure to patients during gated blood pool imaging or decrease acquisition time while maintaining diagnostic accuracy. Based on the improved count sensitivity with high-efficiency SPECT, a 50% reduction in injected activity may be achievable while maintaining short imaging times of 5 minutes, with further reduction possible at longer imaging times.

A study investigating variability of left ventricular ejection fraction using manual and automatic processing modes in a single setting

PurposeA planar multi-gated cardiac blood pool acquisition is a non-invasive technique commonly used to measure left ventricular ejection fraction (LVEF). It is essential that the calculation of LVEF be accurate, repeatable and reproducible for serial monitoring of patients. Different processing modes may be used in calculating the LVEF which require various degrees of manipulation. In addition, different operators with varying levels of experience may process the same data set. It is not known whether the inter-operator variability of LVEF values within a single nuclear medicine department has the potential to affect the calculated LVEF and in turn affect patient management. The aim of the study was to determine variability of LVEF values among operators with different levels of experience using two processing modes. MethodsA descriptive cross-sectional study was carried out in a single setting. Four operators with varying levels of experience analysed 120 left anterior oblique projections using manual and automatic processing modes to calculate the LVEF. Inter- and intra-operator correlation was determined. ResultsManual processing showed moderate to strong agreement (r1 = 0.653) between operators. Automatic processing indicated almost perfect (r1 = 0.812) inter-operator correlation. Intra-operator correlation demonstrated a trend of decreasing variability between processing modes with increasing levels of experience. ConclusionDespite the overall inter-operator agreement, significant intra-operator variability was evident in results from operators with less experience. However, the discrepancies were such that the differences in LVEF would not play a role in patient management. It is recommended that automatic processing be used for determining LVEF to limit inter-operator variability. Additionally operator experience should be considered in the absence of standardised processing protocols when different processing modes are available in a single setting.

Consistency of myocardial mass computations as a quality control check on rest and stress left ventricular ejection fractions computed from (82)Rb PET data.

Changes in left ventricular (LV) ejection fraction (EF) seen in gated Rb data are of interest because the heart is in a genuinely different physiologic state during stress than at rest. A measure that validates internal consistency of LV EF data would be highly desirable. Left ventricular mass calculations are performed simultaneously with EF determinations, requiring similar operator choices, and although LV volumes may change from rest to stress, mass values should be constant. Constancy of LV mass calculations could provide a useful internal check on the consistency of LV EF computations. We retrospectively reviewed data for 205 patients referred for evaluation of known or suspected coronary disease who had rest and regadenoson stress gated Rb PET/CT myocardial perfusion imaging. Equilibrium gated myocardial perfusion PET data were analyzed to calculate LV volumes, EF, and simultaneously mass values. Rest mass ranged from 62 to 284 g (median, 115 g), stress mass from 39 to 315 g (median, 120 g), and differences were -25 to +25 g (median, 1 g). Rest and stress mass values were statistically similar (121 ± 37 g vs 124 ± 49 g, P = 0.45) and correlated strongly with one another (r = 0.94, P < 0.0001). Left ventricular mass calculations are constant from rest to stress over a wide range of ventricular volumes and ejection fractions. Consistency of LV mass values can serve as confirmation of the appropriateness of operator choices when LV EF calculations are performed.