Objective To observe the value of deep learning (DL) models for automatic classification of echocardiographic views. Methods Totally 100 patients after heart transplantation were retrospectively enrolled and divided i...Objective To observe the value of deep learning (DL) models for automatic classification of echocardiographic views. Methods Totally 100 patients after heart transplantation were retrospectively enrolled and divided into training set, validation set and test set at a ratio of 7 ∶ 2 ∶ 1. ResNet18, ResNet34, Swin Transformer and Swin Transformer V2 models were established based on 2D apical two chamber view, 2D apical three chamber view, 2D apical four chamber view, 2D subcostal view, parasternal long-axis view of left ventricle, short-axis view of great arteries, short-axis view of apex of left ventricle, short-axis view of papillary muscle of left ventricle, short-axis view of mitral valve of left ventricle, also 3D and CDFI views of echocardiography. The accuracy, precision, recall, F1 score and confusion matrix were used to evaluate the performance of each model for automatically classifying echocardiographic views. The interactive interface was designed based on Qt Designer software and deployed on the desktop. Results The performance of models for automatically classifying echocardiographic views in test set were all good, with relatively poor performance for 2D short-axis view of left ventricle and superior performance for 3D and CDFI views. Swin Transformer V2 was the optimal model for automatically classifying echocardiographic views, with high accuracy, precision, recall and F1 score was 92.56%, 89.01%, 89.97% and 89.31%, respectively, which also had the highest diagonal value in confusion matrix and showed the best classification effect on various views in t-SNE figure. Conclusion DL model had good performance for automatically classifying echocardiographic views, especially Swin Transformer V2 model had the best performance. Using interactive classification interface could improve the interpretability of prediction results to some extent.展开更多
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 1250 TTE vid...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 1250 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(PSAX GV).The videos were divided into development set(245 A4C,155 PLAX,225 PSAX GV),semi-automated training set(98 A4C,62 PLAX,90 PSAX GV)and test set(147 A4C,93 PLAX,135 PSAX GV)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 PSAX GV 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.展开更多
Objective To observe the value of deep learning echocardiographic intelligent model for evaluation on left ventricular(LV)regional wall motion abnormalities(RWMA).Methods Apical two-chamber,three-chamber and four-cham...Objective To observe the value of deep learning echocardiographic intelligent model for evaluation on left ventricular(LV)regional wall motion abnormalities(RWMA).Methods Apical two-chamber,three-chamber and four-chamber views two-dimensional echocardiograms were obtained prospectively in 205 patients with coronary heart disease.The model for evaluating LV regional contractile function was constructed using a five-fold cross-validation method to automatically identify the presence of RWMA or not,and the performance of this model was assessed taken manual interpretation of RWMA as standards.Results Among 205 patients,RWMA was detected in totally 650 segments in 83 cases.LV myocardial segmentation model demonstrated good efficacy for delineation of LV myocardium.The average Dice similarity coefficient for LV myocardial segmentation results in the apical two-chamber,three-chamber and four-chamber views was 0.85,0.82 and 0.88,respectively.LV myocardial segmentation model accurately segmented LV myocardium in apical two-chamber,three-chamber and four-chamber views.The mean area under the curve(AUC)of RWMA identification model was 0.843±0.071,with sensitivity of(64.19±14.85)%,specificity of(89.44±7.31)%and accuracy of(85.22±4.37)%.Conclusion Deep learning echocardiographic intelligent model could be used to automatically evaluate LV regional contractile function,hence rapidly and accurately identifying RWMA.展开更多
Artificial intelligence(AI)technology has been increasingly used in medical field with its rapid developments.Echocardiography is one of the best imaging methods for clinical diagnosis of heart diseases,and combining ...Artificial intelligence(AI)technology has been increasingly used in medical field with its rapid developments.Echocardiography is one of the best imaging methods for clinical diagnosis of heart diseases,and combining with AI could further improve its diagnostic efficiency.Though the applications of AI in echocardiography remained at a relatively early stage,a variety of automated quantitative and analytical techniques were rapidly emerging and initially entered clinical practice.The status of clinical applications of AI in echocardiography were reviewed in this article.展开更多
Objective To observe the clinical application value of total free-breathing cardiac MR(CMR)examination preliminarily.Methods Two patients who underwent CMR scanning under free-breathing state,including cine,motion cor...Objective To observe the clinical application value of total free-breathing cardiac MR(CMR)examination preliminarily.Methods Two patients who underwent CMR scanning under free-breathing state,including cine,motion correction T1 and T2 mapping,blood flow imaging,and late gadolinium enhancement scanning were retrospectively enrolled,and the qualities of the above images were evaluated and compared with that of conventional CMR images under breath-holding state.Results No significant difference of imaging quality was found between total free-breathing and conventional breath-holding CMR.The differences of left ventricular ejection fraction,cardiac output,left ventricular end-diastolic volume index and left ventricular mass measured based on CMR images under different breath conditions were limited.Conclusion Total free-breathing CMR was feasible in clinical practice,which could provide"one-stop"evaluation of cardiac structure,function and myocardial histological characteristics,hence having promising clinical prospects.展开更多
Objective: To evaluate of the role of transesophageal echocardiography (TEE)in percutaneous closure of atrial septal defects (ASD) with the Amplatzer septal occluder. Methods:Sixty- two patients (10 to 55 years of age...Objective: To evaluate of the role of transesophageal echocardiography (TEE)in percutaneous closure of atrial septal defects (ASD) with the Amplatzer septal occluder. Methods:Sixty- two patients (10 to 55 years of age) were selected for percutaneous closure of ASD bytrans-esophageal echocardiography, which was also used to monitor the procedure, to select theappropriate size of the Amplatzer device, to verify its position, and to access the immediateresults of the procedure. During the follow-up, transthoracic echocardiography (TTE) or TEE was usedto evaluate the presence and magnitude of residual shunt (RS), device position, and right cardiacchamber diameters. Results: The mean ASD diameter by TTE ([19. 1 +- 5. 8] mm) was significantlysmaller (P< 0. 001) than the stretched diameter of the ASD (25. 1 +- 6. 4) mm. There are nosignificant differences between the TEE -measured value (23. 5+_6. 2) mm and the stretched diameterof the ASD (P > 0. 05). Due to proper patient selection all procedures were successful. There wasimmediate and complete closure in 61/62 patients, only one patients had trivial residual shunt.Follow- up was performed using TTE or TEE right after operation, 1 d, 1 month, 3 months, 6 monthsand yearly thereafter. Ail, patients remain asymptomatic without any clinical or technical problems.Conclusion: With the aid of TEE, percutaneous closure of ASD can be performed successfully, safely,and effectively.展开更多
Liquid metal filling flow process in the microscale during the centrifugal casting process was studied by means of similar physical simulation. The research was focused on derived similarity criterion. Based on the tr...Liquid metal filling flow process in the microscale during the centrifugal casting process was studied by means of similar physical simulation. The research was focused on derived similarity criterion. Based on the traditional flow equations, the flow equation and the Bernoulli＇s equation for liquid metal flows in micro-scale space were derived, which provides a mathematical model for numerical simulation of micro-scale flow. In the meanwhile, according to the micro-flow equation and the similarity theory, the similarity criterion for the physical simulation of the mold filling behaviors was presented under centrifugal force field, so as to achieve the visual observation and quantitative analysis of micro-flow process.展开更多
A new cooling technique based on thermal driving in high centrifugal field （TDHCF） is developed for gas turbine rotational components, such as turbine blades. The key point of TDHCF is to enhance heat transfer by th...A new cooling technique based on thermal driving in high centrifugal field （TDHCF） is developed for gas turbine rotational components, such as turbine blades. The key point of TDHCF is to enhance heat transfer by the fluid thermal driving in closed loop small channels placed in the high centrifugal field. Heat transfer characteristics of the new cooling technique are analyzed. In experiments, two different fluids （liquid water and Freon R12） are used as thermal driving media （fluid inside the loop channel）. And the channel width d is 1 mm and the height h is 30 mm. The temperature is measured by thermocouples and an average heat transfer coefficient KH is defined to indicate heat transfer capacity of TDHCF. Experimental results show that KH is enhanced when heat flux and the rotating speed increase. And thermal properties of thermal driving media are also influenced by KH. Larger KH can be achieved by using Freon R12 as thermal driving medium compared with using liquid water. It can increase to 2 300 W/（m^2 · K） and it is much higher than that of the normal air cooling method （usually at the level of 600-1200 W/（m^2·K））. All fundamental studies of TDHCF show that there actually exists thermal driving in the closed loop small channel in the centrifugal field to improve heat transfer characteristics.展开更多
Objective: To evaluate the therapeutic effect, safety and complications oftranscathetering Amplatzer device in the closure of patent ductus arteriosus (PDA) and atrial septaldefects (ASD) in children. Methods: Patient...Objective: To evaluate the therapeutic effect, safety and complications oftranscathetering Amplatzer device in the closure of patent ductus arteriosus (PDA) and atrial septaldefects (ASD) in children. Methods: Patients with PDA (n = 25) and ASD ( n = 16), confirmed byechocardiography, were treated by transcatheterization. Amplatzer occluder device was placed by thetranscatheterization with the image support of X-ray and transthoracic echocardiography ( TTE) . TheTTE, ECG and X-ray examination were engaged to evaluate the therapeutic results on the time pointsof 24 h , 1, 3 , 6, 12 months after the operation, and all these cases were engaged to the follow-upexamination. Results: The cardioangiographic diameter was 13.0-28.0 mm ([19.3+-4.9] mm) in ASD and2.0-7.7 mm ([3.9+-1.5] mm) in PDA . The diameter of the Amplatzer occluder selected were 13.0-30.0mm ( [20.6+-5.1] mm) in ASD and 4.0-12.0 mm ([6.6+-1.9] mm) in PDA , respectively. All the Amplatzeroccluders were placed successfully. There were no complications during and after the operation.Very small residual shunt was still found soon after the operation in 10 cases , and there were noresidual or recanalization after three months of the operation. The pulmonary artery pressure andheart size were significantly decreased in follow-up examination . Conclusion: Transcatheteringclosure with Amplatzer device is an effective, simple and safe technique in the treatment of ASD andPDA in children.展开更多
In gas injection refining processes,wide dispersion of small bubbles in the bath is indispensable for high refining efficiency.Eccentric mechanical stirring with unidirectional impeller rotation was tested using a wat...In gas injection refining processes,wide dispersion of small bubbles in the bath is indispensable for high refining efficiency.Eccentric mechanical stirring with unidirectional impeller rotation was tested using a water model for pursuing better bubble disintegration and dispersion.Effects of various factors on bubble disintegration and dispersion were investigated.These factors were stirring mode,eccentricity and rotation speed,nozzle structure,nozzle immersion depth,and gas flow rate.Gas injection from a nozzle at the end of the impeller shaft and from an immersed lance was studied.Under eccentric stirring,a vortex was formed away from the shaft.Small bubbles were produced in the strong turbulence or high shear stress field near the rotating impeller and moved in the direction to the vortex keeping up with the macroscopic flow induced by the mechanical stirring.Thus small bubbles could disperse widely in the bath under eccentric stirring with unidirectional rotation.展开更多
By means of similar physical simulation, liquid metal filling flow pattern in the microscale during the centrifugal casting process was studied. It was found that, in microscale, the flow channel with the maximum cros...By means of similar physical simulation, liquid metal filling flow pattern in the microscale during the centrifugal casting process was studied. It was found that, in microscale, the flow channel with the maximum cross-sectional area was filled first, and the micro flow channels with 0.1 mm in diameter were filled when the rotational speed was increased to 964 r/min. The total fluid energy remained constant during the mould filling, and the changes of cross-sectional area only occurred in the microflow channels with 0.3 mm in diameter. Filling velocity increased with processing time, and a peak value was achieved rapidly, followed by a gentle increase as the process proceeded further. The time required to achieve the peak filling rate decreased dramatically with increase of rotational speed.展开更多
文摘Objective To observe the value of deep learning (DL) models for automatic classification of echocardiographic views. Methods Totally 100 patients after heart transplantation were retrospectively enrolled and divided into training set, validation set and test set at a ratio of 7 ∶ 2 ∶ 1. ResNet18, ResNet34, Swin Transformer and Swin Transformer V2 models were established based on 2D apical two chamber view, 2D apical three chamber view, 2D apical four chamber view, 2D subcostal view, parasternal long-axis view of left ventricle, short-axis view of great arteries, short-axis view of apex of left ventricle, short-axis view of papillary muscle of left ventricle, short-axis view of mitral valve of left ventricle, also 3D and CDFI views of echocardiography. The accuracy, precision, recall, F1 score and confusion matrix were used to evaluate the performance of each model for automatically classifying echocardiographic views. The interactive interface was designed based on Qt Designer software and deployed on the desktop. Results The performance of models for automatically classifying echocardiographic views in test set were all good, with relatively poor performance for 2D short-axis view of left ventricle and superior performance for 3D and CDFI views. Swin Transformer V2 was the optimal model for automatically classifying echocardiographic views, with high accuracy, precision, recall and F1 score was 92.56%, 89.01%, 89.97% and 89.31%, respectively, which also had the highest diagonal value in confusion matrix and showed the best classification effect on various views in t-SNE figure. Conclusion DL model had good performance for automatically classifying echocardiographic views, especially Swin Transformer V2 model had the best performance. Using interactive classification interface could improve the interpretability of prediction results to some extent.
文摘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 1250 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(PSAX GV).The videos were divided into development set(245 A4C,155 PLAX,225 PSAX GV),semi-automated training set(98 A4C,62 PLAX,90 PSAX GV)and test set(147 A4C,93 PLAX,135 PSAX GV)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 PSAX GV 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.
文摘Objective To observe the value of deep learning echocardiographic intelligent model for evaluation on left ventricular(LV)regional wall motion abnormalities(RWMA).Methods Apical two-chamber,three-chamber and four-chamber views two-dimensional echocardiograms were obtained prospectively in 205 patients with coronary heart disease.The model for evaluating LV regional contractile function was constructed using a five-fold cross-validation method to automatically identify the presence of RWMA or not,and the performance of this model was assessed taken manual interpretation of RWMA as standards.Results Among 205 patients,RWMA was detected in totally 650 segments in 83 cases.LV myocardial segmentation model demonstrated good efficacy for delineation of LV myocardium.The average Dice similarity coefficient for LV myocardial segmentation results in the apical two-chamber,three-chamber and four-chamber views was 0.85,0.82 and 0.88,respectively.LV myocardial segmentation model accurately segmented LV myocardium in apical two-chamber,three-chamber and four-chamber views.The mean area under the curve(AUC)of RWMA identification model was 0.843±0.071,with sensitivity of(64.19±14.85)%,specificity of(89.44±7.31)%and accuracy of(85.22±4.37)%.Conclusion Deep learning echocardiographic intelligent model could be used to automatically evaluate LV regional contractile function,hence rapidly and accurately identifying RWMA.
文摘Artificial intelligence(AI)technology has been increasingly used in medical field with its rapid developments.Echocardiography is one of the best imaging methods for clinical diagnosis of heart diseases,and combining with AI could further improve its diagnostic efficiency.Though the applications of AI in echocardiography remained at a relatively early stage,a variety of automated quantitative and analytical techniques were rapidly emerging and initially entered clinical practice.The status of clinical applications of AI in echocardiography were reviewed in this article.
文摘Objective To observe the clinical application value of total free-breathing cardiac MR(CMR)examination preliminarily.Methods Two patients who underwent CMR scanning under free-breathing state,including cine,motion correction T1 and T2 mapping,blood flow imaging,and late gadolinium enhancement scanning were retrospectively enrolled,and the qualities of the above images were evaluated and compared with that of conventional CMR images under breath-holding state.Results No significant difference of imaging quality was found between total free-breathing and conventional breath-holding CMR.The differences of left ventricular ejection fraction,cardiac output,left ventricular end-diastolic volume index and left ventricular mass measured based on CMR images under different breath conditions were limited.Conclusion Total free-breathing CMR was feasible in clinical practice,which could provide"one-stop"evaluation of cardiac structure,function and myocardial histological characteristics,hence having promising clinical prospects.
文摘Objective: To evaluate of the role of transesophageal echocardiography (TEE)in percutaneous closure of atrial septal defects (ASD) with the Amplatzer septal occluder. Methods:Sixty- two patients (10 to 55 years of age) were selected for percutaneous closure of ASD bytrans-esophageal echocardiography, which was also used to monitor the procedure, to select theappropriate size of the Amplatzer device, to verify its position, and to access the immediateresults of the procedure. During the follow-up, transthoracic echocardiography (TTE) or TEE was usedto evaluate the presence and magnitude of residual shunt (RS), device position, and right cardiacchamber diameters. Results: The mean ASD diameter by TTE ([19. 1 +- 5. 8] mm) was significantlysmaller (P< 0. 001) than the stretched diameter of the ASD (25. 1 +- 6. 4) mm. There are nosignificant differences between the TEE -measured value (23. 5+_6. 2) mm and the stretched diameterof the ASD (P > 0. 05). Due to proper patient selection all procedures were successful. There wasimmediate and complete closure in 61/62 patients, only one patients had trivial residual shunt.Follow- up was performed using TTE or TEE right after operation, 1 d, 1 month, 3 months, 6 monthsand yearly thereafter. Ail, patients remain asymptomatic without any clinical or technical problems.Conclusion: With the aid of TEE, percutaneous closure of ASD can be performed successfully, safely,and effectively.
基金Project(51005053)supported by the National Science Foundation for Young Scientists of China
文摘Liquid metal filling flow process in the microscale during the centrifugal casting process was studied by means of similar physical simulation. The research was focused on derived similarity criterion. Based on the traditional flow equations, the flow equation and the Bernoulli＇s equation for liquid metal flows in micro-scale space were derived, which provides a mathematical model for numerical simulation of micro-scale flow. In the meanwhile, according to the micro-flow equation and the similarity theory, the similarity criterion for the physical simulation of the mold filling behaviors was presented under centrifugal force field, so as to achieve the visual observation and quantitative analysis of micro-flow process.
文摘A new cooling technique based on thermal driving in high centrifugal field （TDHCF） is developed for gas turbine rotational components, such as turbine blades. The key point of TDHCF is to enhance heat transfer by the fluid thermal driving in closed loop small channels placed in the high centrifugal field. Heat transfer characteristics of the new cooling technique are analyzed. In experiments, two different fluids （liquid water and Freon R12） are used as thermal driving media （fluid inside the loop channel）. And the channel width d is 1 mm and the height h is 30 mm. The temperature is measured by thermocouples and an average heat transfer coefficient KH is defined to indicate heat transfer capacity of TDHCF. Experimental results show that KH is enhanced when heat flux and the rotating speed increase. And thermal properties of thermal driving media are also influenced by KH. Larger KH can be achieved by using Freon R12 as thermal driving medium compared with using liquid water. It can increase to 2 300 W/（m^2 · K） and it is much higher than that of the normal air cooling method （usually at the level of 600-1200 W/（m^2·K））. All fundamental studies of TDHCF show that there actually exists thermal driving in the closed loop small channel in the centrifugal field to improve heat transfer characteristics.
文摘Objective: To evaluate the therapeutic effect, safety and complications oftranscathetering Amplatzer device in the closure of patent ductus arteriosus (PDA) and atrial septaldefects (ASD) in children. Methods: Patients with PDA (n = 25) and ASD ( n = 16), confirmed byechocardiography, were treated by transcatheterization. Amplatzer occluder device was placed by thetranscatheterization with the image support of X-ray and transthoracic echocardiography ( TTE) . TheTTE, ECG and X-ray examination were engaged to evaluate the therapeutic results on the time pointsof 24 h , 1, 3 , 6, 12 months after the operation, and all these cases were engaged to the follow-upexamination. Results: The cardioangiographic diameter was 13.0-28.0 mm ([19.3+-4.9] mm) in ASD and2.0-7.7 mm ([3.9+-1.5] mm) in PDA . The diameter of the Amplatzer occluder selected were 13.0-30.0mm ( [20.6+-5.1] mm) in ASD and 4.0-12.0 mm ([6.6+-1.9] mm) in PDA , respectively. All the Amplatzeroccluders were placed successfully. There were no complications during and after the operation.Very small residual shunt was still found soon after the operation in 10 cases , and there were noresidual or recanalization after three months of the operation. The pulmonary artery pressure andheart size were significantly decreased in follow-up examination . Conclusion: Transcatheteringclosure with Amplatzer device is an effective, simple and safe technique in the treatment of ASD andPDA in children.
基金Projects (50974035,51074047) supported by the National Natural Science Foundation of ChinaProject (20090407) supported by the Doctoral Fund of Ministry of Education,ChinaProject (200921007) supported by Liaoning Key Science and Technology,China
文摘In gas injection refining processes,wide dispersion of small bubbles in the bath is indispensable for high refining efficiency.Eccentric mechanical stirring with unidirectional impeller rotation was tested using a water model for pursuing better bubble disintegration and dispersion.Effects of various factors on bubble disintegration and dispersion were investigated.These factors were stirring mode,eccentricity and rotation speed,nozzle structure,nozzle immersion depth,and gas flow rate.Gas injection from a nozzle at the end of the impeller shaft and from an immersed lance was studied.Under eccentric stirring,a vortex was formed away from the shaft.Small bubbles were produced in the strong turbulence or high shear stress field near the rotating impeller and moved in the direction to the vortex keeping up with the macroscopic flow induced by the mechanical stirring.Thus small bubbles could disperse widely in the bath under eccentric stirring with unidirectional rotation.
基金Project (51005053) supported by the National Science Foundation for Young Scientists of China
文摘By means of similar physical simulation, liquid metal filling flow pattern in the microscale during the centrifugal casting process was studied. It was found that, in microscale, the flow channel with the maximum cross-sectional area was filled first, and the micro flow channels with 0.1 mm in diameter were filled when the rotational speed was increased to 964 r/min. The total fluid energy remained constant during the mould filling, and the changes of cross-sectional area only occurred in the microflow channels with 0.3 mm in diameter. Filling velocity increased with processing time, and a peak value was achieved rapidly, followed by a gentle increase as the process proceeded further. The time required to achieve the peak filling rate decreased dramatically with increase of rotational speed.
