Object:To explore the feasibility of using artificial intelligence for quality control of echocardiographic images.Methods:Retrospectively，5 000 two-dimensional echocardiographic video images within the period from 2021 to 2023 were randomly retrieved from the echocardiography database of Nanjing Drum Tower Hospital，Affiliated Hospital of Medical School，Nanjing University. Among these selected images，1 559 of them were apical views. The physician team formulated the scoring rules，which specifically included four scoring criteria：gain，scaling ratio，cardiac axis angle，and structure. Subsequently，the data were labeled with view classification and image quality scores. The labeled data were further partitioned into the training set（ n = 643），the validation set（ n = 276），and the test set（ n = 640）. The training and validation sets were utilized for constructing the models for view classification and quality assessment，while the test set was employed to verify the models' effectiveness. The view classification module was implemented using the SlowFast model，and the quality assessment module involved algorithms such as ResNet，Video Swin Transformer，SSD，and U-Net. Results:The average accuracy，precision，recall rate and F1 score of the classification model in identifying each apical view were 0.987 1，0.983 0，0.987 1 and 0.984 9 respectively，and the inference time was（333.4 ± 105.4）ms. The average accuracies of the quality assessment module in terms of gain，scaling ratio，cardiac axis angle and display of main structures were 0.915 1，0.928 2，0.938 7 and 0.965 6 respectively，and the overall scoring accuracy was 0.912 7.Conclusions:The echocardiogram quality control system developed in this research can effectively classify and evaluate the quality of two-dimensional images of the apical views in echocardiograms. Moreover，it guarantees the objectivity，timeliness and high-efficiency of quality control，which has reference value for the establishment of the echocardiogram quality control system.

Objective:To quantitatively evaluate the effects of left bundle branch block（LBBB）on left ventricular structure，function and myocardial perfusion using left ventricular pressure-strain loop and single photon emission computed tomography（SPECT），and to investigate the relationship between myocardial work，myocardial perfusion and pathological changes of left ventricular remodeling in left bundle branch block induced cardiomyopathy（LBBB-CM）.Methods:Fourteen male beagle dogs were selected，and the main trunk of the left bundle branch was ablated to create an LBBB dog model. Electrocardiogram（ECG），transesophageal echocardiography and arterial blood pressure data of LBBB dogs were collected before and 12 months after the ablation of left bundle branch trunk. Global and segmental myocardial work parameters were obtained by left ventricular pressure-strain loop. The differences of above parameters between baseline and 12 months after the ablation of left bundle branch were compared. SPECT was performed in LBBB dogs 12 months after the creation of LBBB. The hearts were harvested for anatomy observation and histopathological analysis in LBBB dogs and another 7 male beagle dogs（normal control group）matched by age and weight. The correlation between myocardial perfusion（percentage of regional tracer uptake）and myocardial work parameters，myocardial fibrosis in LBBB dogs were analyzed.Results:Compared with baseline，the left ventricular end-diastolic volume of 12 months after the ablation increased［（20.78 ± 5.32）ml vs（26.71 ± 7.94）ml， P = 0.003］，left ventricular ejection fraction decreased［（59.17 ± 5.67）% vs（47.69 ± 5.45）%， P<0.001］；left ventricular global/segmental longitudinal strain，global/segmental constructive work and global/segmental work efficiency decreased（all P<0.05），left ventricular global/segmental wasted work increased（all P<0.001）. Heterogenous perfusion defect was observed in LBBB dogs by SPECT，compared with lateral wall segments，the percentage of regional tracer uptake of septum was decreased（all P<0.05）. Gross anatomical and myocardial pathological changes were manifested as cardiomegaly，flaky or focal grayish thickening of endocardium，cardiomyocyte degeneration and fibrosis. Compared with normal control group，the collagen fiber volume fraction（CVF）in all segmental endocardium and partial segmental myocardium of LBBB dogs were significantly increased（all P<0.05）. Percentage of regional tracer uptake was positively correlated with segmental myocardial work（SMW）and segmental myocardial efficiency（SWE）（ r s = 0.49，0.31；both P<0.001），and negatively correlated with CVF and segmental wasted work（SWW）（ r s = -0.51，-0.49；both P<0.001）. Conclusions:Isolated LBBB is not benign，which can result in left ventricular remodeling，decreased cardiac constructive function，abnormal myocardial perfusion，endocardial fibrosis and myocardial fibrosis.The parameters of myocardial work assecsed by echocardiograpgy and myocardial perfusion，as non-invasive examination，can to some extent reflect the degree of left ventricular remodeling in LBBB-CM.

Permanent left superior vena cava aneurysm is a rare mediastinal venous lesion，the majority of the literature is in the form of case reports. In this article，a 50-year-old female with an incidental permanent left superior vena cava aneurysm discovered on echocardiography in Nanjing Gulou Hospital，and the right heart contrast-enhanced echocardiographic played an important role in the process of clear diagnosis. The patient was observed without intervention. No complications were attributable to the permanent left superior vena cava aneurysm during follow-up.

Object:To explore the feasibility of using artificial intelligence for quality control of echocardiographic images.Methods:Retrospectively，5 000 two-dimensional echocardiographic video images within the period from 2021 to 2023 were randomly retrieved from the echocardiography database of Nanjing Drum Tower Hospital，Affiliated Hospital of Medical School，Nanjing University. Among these selected images，1 559 of them were apical views. The physician team formulated the scoring rules，which specifically included four scoring criteria：gain，scaling ratio，cardiac axis angle，and structure. Subsequently，the data were labeled with view classification and image quality scores. The labeled data were further partitioned into the training set（ n = 643），the validation set（ n = 276），and the test set（ n = 640）. The training and validation sets were utilized for constructing the models for view classification and quality assessment，while the test set was employed to verify the models' effectiveness. The view classification module was implemented using the SlowFast model，and the quality assessment module involved algorithms such as ResNet，Video Swin Transformer，SSD，and U-Net. Results:The average accuracy，precision，recall rate and F1 score of the classification model in identifying each apical view were 0.987 1，0.983 0，0.987 1 and 0.984 9 respectively，and the inference time was（333.4 ± 105.4）ms. The average accuracies of the quality assessment module in terms of gain，scaling ratio，cardiac axis angle and display of main structures were 0.915 1，0.928 2，0.938 7 and 0.965 6 respectively，and the overall scoring accuracy was 0.912 7.Conclusions:The echocardiogram quality control system developed in this research can effectively classify and evaluate the quality of two-dimensional images of the apical views in echocardiograms. Moreover，it guarantees the objectivity，timeliness and high-efficiency of quality control，which has reference value for the establishment of the echocardiogram quality control system.

Objective:To quantitatively evaluate the effects of left bundle branch block（LBBB）on left ventricular structure，function and myocardial perfusion using left ventricular pressure-strain loop and single photon emission computed tomography（SPECT），and to investigate the relationship between myocardial work，myocardial perfusion and pathological changes of left ventricular remodeling in left bundle branch block induced cardiomyopathy（LBBB-CM）.Methods:Fourteen male beagle dogs were selected，and the main trunk of the left bundle branch was ablated to create an LBBB dog model. Electrocardiogram（ECG），transesophageal echocardiography and arterial blood pressure data of LBBB dogs were collected before and 12 months after the ablation of left bundle branch trunk. Global and segmental myocardial work parameters were obtained by left ventricular pressure-strain loop. The differences of above parameters between baseline and 12 months after the ablation of left bundle branch were compared. SPECT was performed in LBBB dogs 12 months after the creation of LBBB. The hearts were harvested for anatomy observation and histopathological analysis in LBBB dogs and another 7 male beagle dogs（normal control group）matched by age and weight. The correlation between myocardial perfusion（percentage of regional tracer uptake）and myocardial work parameters，myocardial fibrosis in LBBB dogs were analyzed.Results:Compared with baseline，the left ventricular end-diastolic volume of 12 months after the ablation increased［（20.78 ± 5.32）ml vs（26.71 ± 7.94）ml， P = 0.003］，left ventricular ejection fraction decreased［（59.17 ± 5.67）% vs（47.69 ± 5.45）%， P<0.001］；left ventricular global/segmental longitudinal strain，global/segmental constructive work and global/segmental work efficiency decreased（all P<0.05），left ventricular global/segmental wasted work increased（all P<0.001）. Heterogenous perfusion defect was observed in LBBB dogs by SPECT，compared with lateral wall segments，the percentage of regional tracer uptake of septum was decreased（all P<0.05）. Gross anatomical and myocardial pathological changes were manifested as cardiomegaly，flaky or focal grayish thickening of endocardium，cardiomyocyte degeneration and fibrosis. Compared with normal control group，the collagen fiber volume fraction（CVF）in all segmental endocardium and partial segmental myocardium of LBBB dogs were significantly increased（all P<0.05）. Percentage of regional tracer uptake was positively correlated with segmental myocardial work（SMW）and segmental myocardial efficiency（SWE）（ r s = 0.49，0.31；both P<0.001），and negatively correlated with CVF and segmental wasted work（SWW）（ r s = -0.51，-0.49；both P<0.001）. Conclusions:Isolated LBBB is not benign，which can result in left ventricular remodeling，decreased cardiac constructive function，abnormal myocardial perfusion，endocardial fibrosis and myocardial fibrosis.The parameters of myocardial work assecsed by echocardiograpgy and myocardial perfusion，as non-invasive examination，can to some extent reflect the degree of left ventricular remodeling in LBBB-CM.

Permanent left superior vena cava aneurysm is a rare mediastinal venous lesion，the majority of the literature is in the form of case reports. In this article，a 50-year-old female with an incidental permanent left superior vena cava aneurysm discovered on echocardiography in Nanjing Gulou Hospital，and the right heart contrast-enhanced echocardiographic played an important role in the process of clear diagnosis. The patient was observed without intervention. No complications were attributable to the permanent left superior vena cava aneurysm during follow-up.

Objective To explore the value of deep learning(DL)models semi-automatic training system for automatic optimization of clinical image quality control of transthoracic echocardiography(TTE).Methods Totally 1 250 TTE videos from 402 patients were retrospectively collected,including 490 apical four chamber(A4C),310 parasternal long axis view of left ventricle(PLAX)and 450 parasternal short axis view of great vessel(PSAXGv).The videos were divided into development set(245 A4C,155 PLAX,225 PSAXGV),semi-automated training set(98 A4C,62 PLAX,90 PSAXGV)and test set(147 A4C,93 PLAX,135 PSAXGV)at the ratio of 5:2:3.Based on development set and semi-automatic training set,DL model of quality control was semi-automatically iteratively optimized,and a semi-automatic training system was constructed,then the efficacy of DL models for recognizing TTE views and assessing imaging quality of TTE were verified in test set.Results After optimization,the overall accuracy,precision,recall,and F1 score of DL models for recognizing TTE views in test set improved from 97.33％,97.26％,97.26％and 97.26％to 99.73％,99.65％,99.77％and 99.71％,respectively,while the overall accuracy for assessing A4C,PLAX and PSAXGV TTE as standard views in test set improved from 89.12％,83.87％and 90.37％to 93.20％,90.32％and 93.33％,respectively.Conclusion The developed DL models semi-automatic training system could improve the efficiency of clinical imaging quality control of TTE and increase iteration speed.

Objective:To analyze the value of three-dimensional speckle tracking echocardiography (3D-STE) in evaluation of left ventricular diastolic function in elderly patients with heart failure (HF).Methods:130 elderly patients with heart failure (HF pEF) with preserved left ventricular ejection fraction in Gulou Hospital Affiliated to Medical College of Nanjing University from January 2018 to October 2019 were studied. All of them were examined by conventional ultrasound, 3D-STE and left-heart catheterization. Their cardiac three-dimensional full-volume dynamic images were collected and then analyzed with three-dimensional speckle tracking technique. The global longitudinal strain (GLS), global radial strain (GRS), global circumferential strain (GCS), and global area strain (GAS) were measured. According to the detected left ventricular end diastolic pressure (LVEDP), the patients were divided into the normal left ventricular diastolic function group (LVEDP≤15 mmHg) and the left ventricular diastolic dysfunction group (LVEDP>15 mmHg). The GLS, GRS, GCS and GAS of the two groups were compared. Pearson correlation analysis was performed to analyze the correlation between GLS, GRS, GCS, GAS and LVEDP, and ROC curves were used to analyze efficiencies of GLS, GRS, GCS and GAS in prediction of left ventricular diastolic dysfunction.Results:The absolute values of GLS, GRS, GCS and GAS of the left ventricular diastolic dysfunction group were lower than those of the normal left ventricular diastolic function group ( P<0.05). The GLS, GCS and GAS were positively correlated with LVEDP ( P<0.05), while GRS was negatively correlated with LVEDP ( P<0.05). The AUC values of GLS, GRS, GCS and GAS for predicting left ventricular diastolic dysfunction were 0.667, 0.775, 0.762 and 0.840, respectively. The sensitivities were 79.17%, 72.22%, 69.44% and 80.56%, specificities were 48.28%, 70.69%, 82.76% and 77.59%, accuracy rates were 65.38%, 71.54%, 75.38% and 79.23%, respectively. Conclusions:The 3D-STE-related strain parameters GLS, GRS, GCS and GAS can be used as ultrasound indexes for assessment of left ventricular diastolic function in elderly patients with HF pEF, which is helpful for early detection of changes in left ventricular diastolic function in elderly patients with HF.

Objective: To explore correlation between QRS complex duration and left ventricular ejection fraction (LVEF) in patients with complete left bundle branch block (CLBBB).Methods: A total of 213 patients, who were diagnosed as left bundle branch block by ECG in our hospital from Feb 2012 to Jun 2013, were selected.According to QRS complex duration, patients were divided into CLBBB group (n=182) and incomplete left bundle branch block (ICLBBB) group (n=31).Linear correlation analysis was used to analyze the correlation between QRS complex duration and LVEF, and receiver operating characteristic curve (ROC) was used to analyze optimal cutoff point of QRS complex duration for predicting LVEF<50%.Results: Compared with ICLBBB group, there was significant rise in QRS complex duration [(104.61±8.85) ms vs.(149.36±17.25) ms] and significant reduction in LVEF [(54.26±4.96)% vs.(45.22±12.57)%] in CLBBB group, P<0.01 both.Linear correlation analysis indicated that QRS complex duration was significant inversely correlated with LVEF (r=-0.55, P=0.001) in CLBBB patients.ROC analysis indicated that optimal cutoff point of QRS complex duration for predicting LVEF<50% was 151ms, the area under the curve was 0.79 (P=0.001),its sensitivity was 68.1% and specificity was 83.5%.Conclusion: QRS complex duration is significant inversely correlated with LVEF in CLBBB patients, which can be used as a simple index predicting reduced LVEF.