Fully Automated Artificial Intelligence Assessment of Aortic Stenosis by Echocardiography.

BACKGROUND: Aortic stenosis (AS) is a common form of valvular heart disease, present in over 12% of the population age 75 years and above. Transthoracic echocardiography (TTE) is the first line of imaging in the adjudication of AS severity but is time-consuming and requires expert sonographic and interpretation capabilities to yield accurate results. Artificial intelligence (AI) technology has emerged as a useful tool to address these limitations but has not yet been applied in a fully hands-off manner to evaluate AS. Here, we correlate artificial neural network measurements of key hemodynamic AS parameters to experienced human reader assessment. METHODS: Two-dimensional and Doppler echocardiographic images from patients with normal aortic valves and all degrees of AS were analyzed by an artificial neural network (Us2.ai) with no human input to measure key variables in AS assessment. Trained echocardiographers blinded to AI data performed manual measurements of these variables, and correlation analyses were performed. RESULTS: Our cohort included 256 patients with an average age of 67.6 ± 9.5 years. Across all AS severities, AI closely matched human measurement of aortic valve peak velocity (r = 0.97, P < .001), mean pressure gradient (r = 0.94, P < .001), aortic valve area by continuity equation (r = 0.88, P < .001), stroke volume index (r = 0.79, P < .001), left ventricular outflow tract velocity-time integral (r = 0.89, P < .001), aortic valve velocity-time integral (r = 0.96, P < .001), and left ventricular outflow tract diameter (r = 0.76, P < .001). CONCLUSIONS: Artificial neural networks have the capacity to closely mimic human measurement of all relevant parameters in the adjudication of AS severity. Application of this AI technology may minimize interscan variability, improve interpretation and diagnosis of AS, and allow for precise and reproducible identification and management of patients with AS.

Application of a Novel Two-Dimensional Echocardiographic Calcium Quantification Method to Assess All Severities of Aortic Stenosis.

BACKGROUND: Aortic valve (AV) calcification (AVC) is a strong predictor of aortic stenosis (AS) severity. The two-dimensional AVC (2D-AVC) ratio, a gain-independent ratio composed of the average pixel density of the AV and the aortic annulus, has previously shown strong correlations with two-dimensional (2D) echocardiographic hemodynamic parameters for severe AS and AVC by cardiac computed tomography. We hypothesize that the 2D-AVC ratio correlates with hemodynamic parameters in all severities of AS. METHODS: A total of 285 patients with a normal AV (n = 49), aortic sclerosis (n = 75), or mild (n = 38), moderate (n = 72), or severe (n = 51) AS undergoing 2D echocardiography were retrospectively evaluated, and the 2D-AVC ratios were correlated to mean AV gradient, peak AV velocity, AV area, and dimensionless index. The 2D-AVC ratios of various AS severities were compared against each other via area under the curve (AUC) analysis. RESULTS: The 2D-AVC ratio is strongly correlated with mean AV gradient (r = 0.79, P < .0001) and peak AV velocity (r = 0.78, P < .0001). There was moderate correlation with the AV area (r = -0.58, P < .0001) and dimensionless index (r = -0.67, P < .0001) across all AS severities. The 2D-AVC ratio also distinguished nonmoderate AS (mild AS + normal AV) from moderate or greater (moderate + severe) AS (AUC = 0.93) and moderate versus severe AS (AUC = 0.88). CONCLUSION: The 2D-AVC ratio exhibits moderate to strong correlation with 2D echocardiographic hemodynamic parameters across all severities of AS.

Coronary Artery Radial Deformation and Velocity in Native and Stented Arteries.

Introduction: Coronary arteries are exposed to a variety of complex biomechanical forces during a normal cardiac cycle. These forces have the potential to contribute to coronary stent failure. Recent advances in stent design allow for the transmission of native pulsatile biomechanical forces in the stented vessel. However, there is a significant lack of evidence in a human model to measure vessel motion in native coronary arteries and stent conformability. Thus, we aimed to characterize and define coronary artery radial deformation and the effect of stent implantation on arterial deformation. Materials and Methods: Intravascular ultrasound (IVUS) pullback DICOM images were obtained from human coronary arteries using a coronary ultrasound catheter. Using two-dimensional speckle tracking, coronary artery radial deformation was defined as the inward and outward displacement (mm) and velocity (cm/s) of the arterial wall during the cardiac cycle. These deformation values were obtained in native and third-generation drug-eluting stented artery segments. Results: A total of 20 coronary artery segments were independently analyzed pre and poststent implantation for a total of 40 IVUS runs. Stent implantation impacted the degree of radial deformation and velocity. Mean radial deformation in native coronary arteries was 0.1230 mm ± 0.0522 mm compared to 0.0775 mm ± 0.0376 mm in stented vessels (p=0.0031). Mean radial velocity in native coronary arteries was 0.1194 cm/s ± 0.0535 cm/s compared to 0.0840 cm/s ± 0.0399 cm/s in stented vessels (p=0.0228). Conclusion: In this in vivo analysis of third-generation stents, stent implantation attenuates normal human coronary deformation during the cardiac cycle. The implications of these findings on stent failure and improved clinical outcomes require further investigation.

A quantitative gain-independent assessment of the left atrial appendage as a method of thromboembolic risk stratification.

BACKGROUND: Visual assessment of the left atrial appendage (LAA) by echocardiography for the presence of thrombus is inherently qualitative. However, whether quantitative assessments can provide increased value over qualitative assessment has not been thoroughly examined. METHODS: One hundred and thirty-eight patients (mean age 59 ± 13 years, 70% male) undergoing transesophageal echocardiography prior to pulmonary vein isolation or electrical cardioversion were retrospectively studied. LAA were examined by two expert readers and identified as thrombus, sludge, spontaneous echocardiograph contrast, or normal. LAA were then separately examined to calculate a gain-independent ratio between the average pixel density of the LAA cavity and that of the LAA wall (C/W ratio). RESULTS: C/W ratio was significantly related with qualitative LAA analysis (p < 0.0001) and with thromboembolic events (OR 1.60, 95% CI 1.095-2.347, p = 0.02). The C/W ratio (AUC 0.73, 95% CI 0.60-0.86) was a reliable predictor for future thromboembolic events when compared to expert reader LAA assessment (Expert Reader 1 AUC = 0.72, 95% CI 0.53-0.90; Expert Reader 2 AUC = 0.69). CONCLUSIONS: The C/W ratio may be a complementary method to adjudicate thromboembolic risk in patients with AF that is readily quantifiable at time of TEE.

A Novel Two-Dimensional Echocardiography Method to Objectively Quantify Aortic Valve Calcium and Predict Aortic Stenosis Severity.

Aortic valve calcium (AVC) is a strong predictor of aortic stenosis (AS) severity and is typically calculated by multidetector computed tomography (MDCT). We propose a novel method using pixel density quantification software to objectively quantify AVC by two-dimensional (2D) transthoracic echocardiography (TTE) and distinguish severe from non-severe AS. A total of 90 patients (mean age 76 ± 10 years, 75% male, mean AV gradient 32 ± 11 mmHg, peak AV velocity 3.6 ± 0.6 m/s, AV area (AVA) 1.0 ± 0.3 cm2, dimensionless index (DI) 0.27 ± 0.08) with suspected severe aortic stenosis undergoing 2D echocardiography were retrospectively evaluated. Parasternal short axis aortic valve views were used to calculate a gain-independent ratio between the average pixel density of the entire aortic valve in short axis at end diastole and the average pixel density of the aortic annulus in short axis (2D-AVC ratio). The 2D-AVC ratio was compared to echocardiographic hemodynamic parameters associated with AS, MDCT AVC quantification, and expert reader interpretation of AS severity based on echocardiographic AVC interpretation. The 2D-AVC ratio exhibited strong correlations with mean AV gradient (r = 0.72, p < 0.001), peak AV velocity (r = 0.74, p < 0.001), AVC quantified by MDCT (r = 0.71, p <0.001) and excellent accuracy in distinguishing severe from non-severe AS (area under the curve = 0.93). Conversely, expert reader interpretation of AS severity based on echocardiographic AVC was not significantly related to AV mean gradient (t = 0.23, p = 0.64), AVA (t = 2.94, p = 0.11), peak velocity (t = 0.59, p = 0.46), or DI (t = 0.02, p = 0.89). In conclusion, these data suggest that the 2D-AVC ratio may be a complementary method for AS severity adjudication that is readily quantifiable at time of TTE.

Quantitative analysis of spectral Doppler clicks in assessment of aortic stenosis.

OBJECTIVES: This study was performed to evaluate an additional echocardiographic spectral Doppler marker, which would identify severe aortic stenosis (AS). BACKGROUND: Echocardiography is most commonly utilized to assess AS and has been validated against invasive measurements. However, the data obtained are not always in agreement, leaving a conundrum regarding the true severity of AS and can lead to other diagnostic procedures. This highlights the importance of improved noninvasive diagnostic techniques. METHODS: Forty-eight indeterminate cases of calcific AS that had been previously evaluated by both echocardiography and cardiac catheterization were included in the study, using cardiac catheterization as the gold standard for calculation of aortic valve area (AVA). The intensity of opening and closing of the aortic valve, represented by bright vertical deflections on the CW spectral waveform, was quantified using ImageJ software to generate pixel intensity histograms to create opening and closing click (OC and CC) ratios. These ratios were compared with echocardiographic variables and catheterization AVA. RESULTS: Thirty-five patients were found to have severe AS and 13 patients were found to have nonsevere AS, as assessed by cardiac catheterization. CC ratio was found to be a significant predictor of severe AS with an OR 0.024 (95% CI: 0.002-0.378, P = .0079). Adding CC to a model using standard echocardiographic parameters resulted in significant improvement in the C-statistic (0.693 to 0.835, P = .0134). CONCLUSIONS: An additional Doppler marker measuring the aortic valve CC ratio has been found to improve detection of severe AS.

Coronary artery rotation in native and stented porcine coronary arteries.

INTRODUCTION: Coronary arteries are exposed to several complex biomechanical forces during the cardiac cycle. These biomechanical forces potentially contribute to both native coronary artery disease, development of atherosclerosis and eventual stent failure. The aim of the present study was to characterize and define coronary artery axial rotation and the effect of stent implantation on this biomechanical factor. METHODS: Intravascular ultrasound (IVUS) images were obtained from porcine coronary arteries and analyzed in ultrasound analysis software used to evaluate myocardial strain and torsion in echocardiography. In this study the software was utilized for a novel application to evaluate coronary artery rotation and time-to-peak (TTP) rotation in porcine coronary arteries. Clockwise (CW) and counterclockwise (CCW) rotation of coronary arteries during the cardiac cycle and (TTP) rotation were measured. RESULTS: A total of 11 (4 LAD, 4 LCX, 3 RCA) coronary artery segments were independently analyzed pre- and post-stent implantation for a total of 22 IVUS runs. CW and CCW rotation and TTP varied widely within coronary artery segments and between different coronary arteries. Stent implantation impacted degree, direction and TTP of coronary rotation. Measurement reliability was assessed and the intraclass correlation coefficient for maximum average CCW was 0.990 (95% confidence interval 0.980-0.996, P < 0.0001), indicating excellent agreement. CONCLUSIONS: Coronary arteries display wide spectrum of CW and CCW rotation during the cardiac cycle. Coronary stents impact the degree and direction of coronary artery rotation. The implications of these findings on development of atherosclerosis and stent failure require further investigation.

Should the Celiac Artery Be Used as an Anatomical Marker for the Descending Thoracic Aorta During Transesophageal Echocardiography?

BACKGROUND: Transesophageal echocardiography (TEE) is a pivotal tool for diagnosis of aortic diseases. However, there are no suitable anatomical markers to describe location of disease in the descending thoracic aorta. In the past, we have used distance from the dental incisors to report location of disease, but this has no anatomical relevance. Our recent data comparing TEE and computed tomography (CT) have shown that the celiac artery is an accurate anatomical marker where disease is described as distance relative to the celiac artery. This study was designed to determine whether utilization of the celiac artery as an anatomical marker with TEE is practically feasible. METHODS: A clinical trial was performed at the University of Illinois at Chicago and the Jesse Brown VA Medical Center. A total of 160 patients referred for TEE were consecutively enrolled over a period of 18 months. RESULTS: The celiac artery was visualized in 97% of the patients. CONCLUSIONS: The celiac artery is a reliable anatomical marker with TEE and should be routinely used to locate disease in the descending thoracic aorta.

When an unidentified foreign object appears in the inferior vena cava: recognizing the presence of TIPS stent on transthoracic echocardiographic imaging.

We describe the case of 65-year-old female with a history of hypertension, diabetes, and cirrhosis. In the subcostal view on a routine transthoracic echocardiogram (TTE), she is found to have an unidentified round prosthetic appearing object in the inferior vena cava (IVC). Upon further investigation, the object was identified as a transjugular intrahepatic portosystemic shunt (TIPS) stent, which was seen in cross section in a hepatic vein draining into the IVC. Most echocardiographers are unfamiliar with the appearance of a TIPS on TTE. Being able to recognize this will help avoid misdiagnosis and unnecessary further imaging.

Transesophageal echocardiography of the descending thoracic aorta: establishing an accurate anatomic marker using the celiac artery.

OBJECTIVE: We performed transesophageal echocardiography (TEE) and computed tomography (CT) on patients with aortic pathology to describe a more anatomically coherent marker on TEE studies by using the celiac artery as a reference. BACKGROUND: As there are no anatomic markers for the eight-vertebrae long descending thoracic aorta, aortic disease (AD) is routinely reported as a distance from the dental incisors in TEE studies. This method does not provide an anatomically accurate location of AD relative to recognizable anatomy. METHODS: Ten patients referred for contrast CT and TEE for evaluation of embolic events were studied. Twenty-seven focal aortic lesions found on TEE were measured relative to their distance from the celiac artery. The agreement among the two methods of quantification of aortic lesions from the celiac artery was assessed by univariate regression analysis and by the Bland-Altman method. Difference in the mean values between the two groups was analyzed by paired t-test. RESULTS: The P value for the two-tailed t-test for the difference between the two modalities was 0.122. The Pearson coefficient for comparison of CT and TEE data was 0.98. The coefficient of determination for TEE versus CT data was 0.96. CONCLUSIONS: The TEE CA reference marker proves to be an accurate method for localizing disease in the descending thoracic aorta relative to CT findings. Reporting of aortic disease relative to this marker is more clinically applicable than the current method of measurement. The CA reference marker should be routinely reported in TEE studies to enhance the diagnosis of aortic disease.

Mobile ascending aortic atheroma diagnosed by transesophageal echocardiography as source of peripheral vascular embolism.

Complex aortic atheromas are an important differential diagnosis to consider in evaluating sources of arterial embolization. Diagnosis of the embolic source is an essential first step, so treatment can then be initiated to prevent further reoccurrence. We report the case of a 36-year-old man, without significant medical history, who presented to the University of Illinois at Chicago with peripheral vascular embolism to the lower extremities. Computed tomography with contrast angiography and transthoracic echocardiography failed to reveal a source of the thromboembolism. A complex mobile atheroma was discovered in the ascending aorta during transesophageal echocardiography. The case presented is noteworthy when considering the following: the relative rarity of complex atheromas of the ascending aorta, the young age of the patient with no history of atherosclerotic disease, and the failure of computed tomography angiography to reveal the embolic source despite literature supporting high sensitivities for aortic plaque detection compared with transesophageal echocardiography.