Automatic Assessment of Mitral Regurgitation Severity Using the Mask R-CNN Algorithm with Color Doppler Echocardiography Images.

Accurate assessment of mitral regurgitation (MR) severity is critical in clinical diagnosis and treatment. No single echocardiographic method has been recommended for MR quantification thus far. We sought to define the feasibility and accuracy of the mask regions with a convolutional neural network (Mask R-CNN) algorithm in the automatic qualitative evaluation of MR using color Doppler echocardiography images. The authors collected 1132 cases of MR from hospital A and 295 cases of MR from hospital B and divided them into the following four types according to the 2017 American Society of Echocardiography (ASE) guidelines: grade I (mild), grade II (moderate), grade III (moderate), and grade IV (severe). Both grade II and grade III are moderate. After image marking with the LabelMe software, a method using the Mask R-CNN algorithm based on deep learning (DL) was used to evaluate MR severity. We used the data from hospital A to build the artificial intelligence (AI) model and conduct internal verification, and we used the data from hospital B for external verification. According to severity, the accuracy of classification was 0.90, 0.89, and 0.91 for mild, moderate, and severe MR, respectively. The Macro F1 and Micro F1 coefficients were 0.91 and 0.92, respectively. According to grading, the accuracy of classification was 0.90, 0.87, 0.81, and 0.91 for grade I, grade II, grade III, and grade IV, respectively. The Macro F1 and Micro F1 coefficients were 0.89 and 0.89, respectively. Automatic assessment of MR severity is feasible with the Mask R-CNN algorithm and color Doppler electrocardiography images collected in accordance with the 2017 ASE guidelines, and the model demonstrates reasonable performance and provides reliable qualitative results for MR severity.

The role of trans-thoracic echocardiography in the assessment of aortic annular diameter.

ABSTRACT: We aimed to compare two-dimension transthoracic echocardiogram (2D-TTE) and three-dimension transthoracic echocardiogram (3D-TTE) measurements of the aortic annular diameter using multi-detector CT (MDCT) as a gold standard.This prospective observational study included 50 consecutive patients who came to the cardiology department, Al-Azhar University Hospital, New Damietta, for MDCT coronary angiography. The study was carried out in the period from July 2016 until February 2017. All patients were subjected to informed consent, clinical history, physical examination, transthoracic echocardiography 2D and 3D, and MDCT.The aortic annular areas measured by MDCT and 3D-TTE were significantly larger than areas by 2D-TTE. A good correlation (r = 0.82) was observed between the areas obtained by 3D-TTE and MDCT; however, the correlation between the values by 2D-TTE and MDCT was rough (r = 0.30). Eccentricity Index (EI) values in 28% of the patients were greater than 0.1, that is, the aortic annulus was elliptical.Accuracy of aortic annular diameter measurement by 3D-TTE was superior to that by 2D-TTE. Three-D TTE and MDCT revealed that the shape of the aortic annulus was elliptical in 28% to 30% respectively of study subjects. There is a strong concordance between the minimum and the maximum diameter determine by 3D-TTE and MDCT.

Utility of live/real time three-dimensional transesophageal echocardiography in the assessment and percutaneous intervention of bioprosthetic pulmonary valve stenosis.

Accurate echocardiographic evaluation of the pulmonary valve is technically difficult because of its close proximity to the left lung, which often limits decision making. Pulmonary valvotomy is the intervention of choice for symptomatic pulmonary valve stenosis, but fluoroscopy lacks appropriate real time anatomic detail. In this report, we present a case where direct imaging of the pulmonary valve with live/real time three-dimensional transesophageal echocardiography (3DTEE) aided in accurate evaluation and was then used to help guide and monitor successful valvuloplasty of a stenotic pulmonary valve bioprosthesis. We demonstrate that even in cases where two-dimensional (2D) evaluation of the pulmonary valve is difficult, the use of live/real time 3DTEE allows for accurate evaluation of bioprosthetic pulmonary valve structure and function, and enhances the precision and monitoring of percutaneous valvuloplasty.

Quantitative assessment of left ventricular function by 3-dimensional speckle-tracking echocardiography in patients with chronic heart failure: a meta-analysis.

OBJECTIVES: To provide a comprehensive analysis of the clinical utility of 3-dimensional (3D) speckle-tracking echocardiography for left ventricular (LV) function in patients with chronic heart failure (CHF). METHODS: Literature searches were conducted in the PubMed, Embase, Web of Science, and China BioMedicine databases on relevant articles published before October 1, 2012. Crude standardized mean differences with 95% confidence intervals (CIs) were calculated. RESULTS: Seven case-control studies were included with a total of 375 patients with CHF and 181 healthy control participants. Meta-analysis results showed that the LV ejection fraction in the patients was significantly lower than in the controls (standardized mean difference, -4.62; 95% CI, -6.19 to -3.04), whereas the LV end-diastolic volume (LVEDV) and LV end-systolic volume (LVESV) in the patients were higher than in the controls (LVEDV: standardized mean difference, 1.76; 95% CI, 1.09 to 2.44; LVESV: standardized mean difference, 2.04, 95% CI, 1.30 to 2.78). The results also indicated that the patients had a greater delay in the standard deviation of the time to peak area tracking and the maximum difference in the time to peak area tracking in the 16 LV segments than the controls (standard deviation of the time to peak area tracking: standardized mean difference, 3.01; 95% CI, 1.73 to 4.29; maximum difference in the time to peak area tracking: standardized mean difference, 3.26; 95% CI, 1.58 to 4.93). Furthermore, global longitudinal, circumferential, and radial strain were also significantly impaired in the patients compared to the controls (longitudinal strain: standardized mean difference, 2.75; 95% CI, 1.11 to 4.39; circumferential strain: standardized mean difference, 2.71; 95% CI, 1.15 to 4.27; radial strain: standardized mean difference, 1.80; 95% CI, 0.45 to 3.14). CONCLUSIONS: This meta-analysis suggests that LV function in patients with CHF can be noninvasively and objectively measured by 3D speckle-tracking echocardiography.

Assessment of age-related changes in left ventricular twist by 3-dimensional speckle-tracking echocardiography.

OBJECTIVES: The purpose of this study was to determine the normal value of left ventricular (LV) twist in 3-dimensional (3D) geometry and to study the effects of aging on 3D LV twist by sophisticated newly developed 3D speckle-tracking echocardiographic techniques. METHODS: Recent developments in miniaturized ultrasound arrays have provided us with high-quality 3D echocardiographic data. Speckle tracking based on 3D images is robust to out-of-plane motion error, whereas 2-dimensional speckle tracking is inherently unable to analyze 3D cardiac motion and may lead to measurement inaccuracies. Three-dimensional LV volumetric images were acquired from 124 healthy volunteers (aged 21-82 years) and were analyzed by a recent speckle-tracking method. Left ventricular twist was analyzed as apical rotation relative to the base in the 3D coordinates. The measured parameters in this study were peak apical rotation, peak basal rotation, peak LV twist, normalized peak LV twist, and peak untwist velocity. RESULTS: As seen from the apex, the normal LV maintains a wringing systolic displacement with an initial counterclockwise rotation followed by a clockwise rotation in the LV basal plane and a counterclockwise rotation in the LV apical plane. In general, the apical and basal twist increases during the aging process, leading to an increased LV twist value. The mean peak twist ± SD in young participants (21-35 years) was 11.73° ± 2.67°, whereas the value for older participants (>65 years) was 18.57° ± 3.08° (P < .001). CONCLUSIONS: Three-dimensional speckle-tracking echocardiography can be an effective noninvasive method for assessing 3D LV twist. Age-related differences in the 3D LV twist may be the result of the age-related changes in the endocardial myofibers.

Three-dimensional echocardiography: assessment of inter- and intra-operator variability and accuracy in the measurement of left ventricular cavity volume and myocardial mass.

Accurate left ventricular (LV) volume and mass estimation is a strong predictor of cardiovascular morbidity and mortality. We propose that our technique of 3D echocardiography provides an accurate quantification of LV volume and mass by the reconstruction of 2D images into 3D volumes, thus avoiding the need for geometric assumptions. We compared the accuracy and variability in LV volume and mass measurement using 3D echocardiography with 2D echocardiography, using in vitro studies. Six operators measured the LV volume and mass of seven porcine hearts, using both 3D and 2D techniques. Regression analysis was used to test the accuracy of results and an ANOVA test was used to compute variability in measurement. LV volume measurement accuracy was 9.8% (3D) and 18.4% (2D); LV mass measurement accuracy was 5% (3D) and 9.2% (2D). Variability in LV volume quantification with 3D echocardiography was %SEMinter = 13.5%, %SEMintra = 11.4%, and for 2D echocardiography was %SEMinter = 21.5%, %SEMintra = 19.1%. We derived an equation to predict uncertainty in measurement of LV volume and mass using 3D echocardiography, the results of which agreed with our experimental results to within 13%. 3D echocardiography provided twice the accuracy for LV volume and mass measurement and half the variability for LV volume measurement as compared with 2D echocardiography.