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.

[Quantitative assessment of left ventricular systolic dyssynchrony in relation to systolic function by real-time three-dimensional echocardiography-derived regional systolic dyssynchrony index in chronic heart failure patients].

OBJECTIVE: To quantitatively assess the left ventricular systolic dyssynchrony in patients with chronic heart failure based on the regional systolic dyssynchrony index (R-SDI) derived from real-time three-dimensional echocardiography (RT-3DE), and investigate the relation between R-SDI and the left ventricular systolic function. METHODS: Forty-two patients with chronic heart failure (LVEF<50%) were classified into severe dysfunction group (group A, LVEF<40%) and mild dysfunction group (group B, LVEF≥40%), with 33 healthy subjects as the control group (LVEF>50%). RT-3DE was performed for each subject to obtain the left volume-time curves and the 16, 12, and 6 segment R-SDI. The value of R-SDI in assessing left ventricular systolic dyssynchrony and its correlation with LVEF were analyzed. RESULTS: The 16, 12, and 6R-SDI were significantly higher in the chronic heart failure group than in the control group (P<0.01). The R-SDI of group A was significantly greater than those of group B in the chronic heart failure patients (P<0.01), and 16R-SDI, 12R-SDI, and 6R-SDI were inversely correlated with LVEF of the patients (r=-0.843, -0.840, and -0.841, respectively, P<0.01). CONCLUSIONS: R-SDI can be used to assess the left ventricular mechanic systolic dyssynchrony, and the degree of the dyssynchrony is inversely correlated with LVEF. RT-3DE can serve as a valuable modality for quantitative evaluation of left ventricular dyssynchrony in chronic heart failure patients.