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 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
Objective To observe the efficacy of deep learning(DL)model based on PET/CT and its combination with Cox proportional hazard model for predicting progressive disease(PD)of lung invasive adenocarcinoma within 5 years a...Objective To observe the efficacy of deep learning(DL)model based on PET/CT and its combination with Cox proportional hazard model for predicting progressive disease(PD)of lung invasive adenocarcinoma within 5 years after surgery.Methods The clinical,PET/CT and 5-year follow-up data of 250 patients with lung invasive adenocarcinoma were retrospectively analyzed.According to PD or not,the patients were divided into the PD group(n=71)and non-PD group(n=179).The basic data and PET/CT findings were compared between groups,among which the quantitative variables being significant different between groups were transformed to categorical variables using receiver operating characteristic(ROC)curve and corresponding cut-off value.Multivariant Cox proportional hazard model was used to select independent predicting factors of PD of lung invasive adenocarcinoma within 5 years after surgery.The patients were divided into training,validation and test sets at the ratio of 6∶2∶2,and PET/CT data in training set and validation set were used to train model and tuning parameters to build the PET/CT DL model,and the combination model was built in serial connection of DL model and the predictive factors.In test set,the efficacy of each model for predicting PD of lung invasive adenocarcinoma within 5 years after surgery was assessed and compared using the area under the curve(AUC).Results Patients'gender and smoking status,as well as the long diameter,SUV max and SUV mean of lesions measured on PET images,the long diameter,short diameter and type of lesions showed on CT were statistically different between groups(all P<0.05).Smoking(HR=1.787[1.053,3.031],P=0.031)and lesion SUV max>4.15(HR=5.249[1.062,25.945],P=0.042)were both predictors of PD of lung invasive adenocarcinoma within 5 years after surgery.In test set,the AUC of PET/CT DL model for predicting PD was 0.847,of the combination model was 0.890,of the latter was higher than of the former(P=0.036).Conclusion DL model based on PET/CT had high efficacy for predicting PD of lung invasive adenocarcinoma within 5 years after surgery.Combining with Cox proportional hazard model could further improve its predicting efficacy.展开更多
Objective To establish a body composition analysis system based on chest CT,and to observe its value for evaluating content of chest muscle and adipose.Methods T7—T8 layer CT images of 108 pneumonia patients were col...Objective To establish a body composition analysis system based on chest CT,and to observe its value for evaluating content of chest muscle and adipose.Methods T7—T8 layer CT images of 108 pneumonia patients were collected(segmented dataset),and chest CT data of 984 patients were screened from the COVID 19-CT dataset(10 cases were randomly selected as whole test dataset,the remaining 974 cases were selected as layer selection dataset).T7—T8 layer was classified based on convolutional neural network(CNN)derived networks,including ResNet,ResNeXt,MobileNet,ShuffleNet,DenseNet,EfficientNet and ConvNeXt,then the accuracy,precision,recall and specificity were used to evaluate the performance of layer selection dataset.The skeletal muscle(SM),subcutaneous adipose tissue(SAT),intermuscular adipose tissue(IMAT)and visceral adipose tissue(VAT)were segmented using classical fully CNN(FCN)derived network,including FCN,SegNet,UNet,Attention UNet,UNET++,nnUNet,UNeXt and CMUNeXt,then Dice similarity coefficient(DSC),intersection over union(IoU)and 95 Hausdorff distance(HD)were used to evaluate the performance of segmented dataset.The automatic body composition analysis system was constructed based on optimal layer selection network and segmentation network,the mean absolute error(MAE),root mean squared error(RMSE)and standard deviation(SD)of MAE were used to evaluate the performance of automatic system for testing the whole test dataset.Results The accuracy,precision,recall and specificity of DenseNet network for automatically classifying T7—T8 layer from chest CT images was 95.06%,84.83%,92.27%and 95.78%,respectively,which were all higher than those of the other layer selection networks.In segmentation of SM,SAT,IMAT and overall,DSC and IoU of UNet++network were all higher,while 95HD of UNet++network were all lower than those of the other segmentation networks.Using DenseNet as the layer selection network and UNet++as the segmentation network,MAE of the automatic body composition analysis system for predicting SM,SAT,IMAT,VAT and MAE was 27.09,6.95,6.65 and 3.35 cm 2,respectively.Conclusion The body composition analysis system based on chest CT could be used to assess content of chest muscle and adipose.Among them,the UNet++network had better segmentation performance in adipose tissue than SM.展开更多
Objective To observe the value of preoperative CT radiomics models for predicting composition of in vivo urinary calculi.Methods Totally 543 urolithiasis patients were retrospectively enrolled and divided into calcium...Objective To observe the value of preoperative CT radiomics models for predicting composition of in vivo urinary calculi.Methods Totally 543 urolithiasis patients were retrospectively enrolled and divided into calcium oxalate monohydrate stone group(group A,n=373),anhydrous uric acid stone group(group B,n=86),carbonate apatite group(group C,n=30),ammonium urate stone group(group D,n=28)and ammonium magnesium phosphate hexahydrate stone group(group E,n=26)according to the composition of calculi,also divided into training set and test set at the ratio of 7∶3.Radiomics features were extracted and screened based on plain CT images of urinary system.Five binary task models(model A—E corresponding to group A—E)and a quinary task model were constructed using least absolute shrinkage and selection operator algorithm for predicting the composition of calculi in vivo.Then receiver operating characteristic curves were drawn,and the area under the curves(AUC)were calculated to evaluate the predictive efficacy of binary task models,while the accuracy,precision,recall and F1 score were used to evaluate the predictive efficacy of the quinary task model.Results All binary task models had good efficacy for predicting the composition of urinary calculi in vivo,with AUC of 0.860—0.948 in training set and of 0.856—0.933 in test set.The accuracy,precision,recall and F1 score of the quinary task model for predicting the composition of in vivo urinary calculi was 82.25%,83.79%,46.23%and 0.596 in training set,respectively,while was 80.63%,75.26%,43.48%and 0.551 in test set,respectively.Conclusion Binary task radiomics models based on preoperative plain CT had good efficacy for predicting the composition of in vivo urinary calculi,while the quinary task radiomics model had high accuracy but relatively poor stability.展开更多
Objective To observe value of 0D-1D coupling model and 3D fluid-structure interaction(FSI)model based on coronary CT angiography(CCTA)for displaying hemodynamic characteristics of coronary artery stenosis.Methods Base...Objective To observe value of 0D-1D coupling model and 3D fluid-structure interaction(FSI)model based on coronary CT angiography(CCTA)for displaying hemodynamic characteristics of coronary artery stenosis.Methods Based on CCTA data of the stenosed left anterior descending branch(LAD)in a patient with coronary heart disease,an 0D-1D coupling model and 3D FSI model were built,respectively.Then hemodynamic characteristic indexes,including the pressure,flow velocity and wall shear stress(WSS)were obtained in every 0.01 s during 1 s at 5 sampling points(i.e.sampling point 1—5)using these 2 models,respectively,and the consistencies of the results between models were evaluated with Spearman correlation coefficient r s.Results The time consuming for construction of 0D-1D coupling model and 3D FSI model was 0.033 min and 704 min,respectively.Both models showed basically distribution of the pressure,flow velocity and WSS of the stenosed LAD.For more details,the pressure at the stenosed segment of LAD and the proximal segment of stenosis were both higher,which gradually decreased at the distal segment of stenosis,and the flow velocity at the proximal segment of stenosis was in a relatively slow and uniform condition,with significantly increased flow velocity and WSS at the stenosed segment.Compared with 3D FSI model,0D-1D vascular coupling model was relatively unrefined and lack of distal flow lines when displaying blood flow velocity.For sampling point 2 at the stenosed segment of LAD,no significant consistency for pressure between 2 models was found(P=0.118),but strong consistency for the flow velocity and WSS(r s=0.730,0.807,both P<0.05).The consistencies of pressure,flow velocity and WSS between 2 models at the proximal and distal segment of stenosis,i.e.1,3—5 sampling points were week to moderate(r s=0.237—0.669,all P<0.05).Conclusion 0D-1D coupling model exhibited outstanding computational efficiency and might provide relatively reasonable results,while 3D FSI model showed higher accuracy for details and streamline when simulating LAD stenosis.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 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Objective To observe the efficacy of deep learning(DL)model based on PET/CT and its combination with Cox proportional hazard model for predicting progressive disease(PD)of lung invasive adenocarcinoma within 5 years after surgery.Methods The clinical,PET/CT and 5-year follow-up data of 250 patients with lung invasive adenocarcinoma were retrospectively analyzed.According to PD or not,the patients were divided into the PD group(n=71)and non-PD group(n=179).The basic data and PET/CT findings were compared between groups,among which the quantitative variables being significant different between groups were transformed to categorical variables using receiver operating characteristic(ROC)curve and corresponding cut-off value.Multivariant Cox proportional hazard model was used to select independent predicting factors of PD of lung invasive adenocarcinoma within 5 years after surgery.The patients were divided into training,validation and test sets at the ratio of 6∶2∶2,and PET/CT data in training set and validation set were used to train model and tuning parameters to build the PET/CT DL model,and the combination model was built in serial connection of DL model and the predictive factors.In test set,the efficacy of each model for predicting PD of lung invasive adenocarcinoma within 5 years after surgery was assessed and compared using the area under the curve(AUC).Results Patients'gender and smoking status,as well as the long diameter,SUV max and SUV mean of lesions measured on PET images,the long diameter,short diameter and type of lesions showed on CT were statistically different between groups(all P<0.05).Smoking(HR=1.787[1.053,3.031],P=0.031)and lesion SUV max>4.15(HR=5.249[1.062,25.945],P=0.042)were both predictors of PD of lung invasive adenocarcinoma within 5 years after surgery.In test set,the AUC of PET/CT DL model for predicting PD was 0.847,of the combination model was 0.890,of the latter was higher than of the former(P=0.036).Conclusion DL model based on PET/CT had high efficacy for predicting PD of lung invasive adenocarcinoma within 5 years after surgery.Combining with Cox proportional hazard model could further improve its predicting efficacy.
文摘Objective To establish a body composition analysis system based on chest CT,and to observe its value for evaluating content of chest muscle and adipose.Methods T7—T8 layer CT images of 108 pneumonia patients were collected(segmented dataset),and chest CT data of 984 patients were screened from the COVID 19-CT dataset(10 cases were randomly selected as whole test dataset,the remaining 974 cases were selected as layer selection dataset).T7—T8 layer was classified based on convolutional neural network(CNN)derived networks,including ResNet,ResNeXt,MobileNet,ShuffleNet,DenseNet,EfficientNet and ConvNeXt,then the accuracy,precision,recall and specificity were used to evaluate the performance of layer selection dataset.The skeletal muscle(SM),subcutaneous adipose tissue(SAT),intermuscular adipose tissue(IMAT)and visceral adipose tissue(VAT)were segmented using classical fully CNN(FCN)derived network,including FCN,SegNet,UNet,Attention UNet,UNET++,nnUNet,UNeXt and CMUNeXt,then Dice similarity coefficient(DSC),intersection over union(IoU)and 95 Hausdorff distance(HD)were used to evaluate the performance of segmented dataset.The automatic body composition analysis system was constructed based on optimal layer selection network and segmentation network,the mean absolute error(MAE),root mean squared error(RMSE)and standard deviation(SD)of MAE were used to evaluate the performance of automatic system for testing the whole test dataset.Results The accuracy,precision,recall and specificity of DenseNet network for automatically classifying T7—T8 layer from chest CT images was 95.06%,84.83%,92.27%and 95.78%,respectively,which were all higher than those of the other layer selection networks.In segmentation of SM,SAT,IMAT and overall,DSC and IoU of UNet++network were all higher,while 95HD of UNet++network were all lower than those of the other segmentation networks.Using DenseNet as the layer selection network and UNet++as the segmentation network,MAE of the automatic body composition analysis system for predicting SM,SAT,IMAT,VAT and MAE was 27.09,6.95,6.65 and 3.35 cm 2,respectively.Conclusion The body composition analysis system based on chest CT could be used to assess content of chest muscle and adipose.Among them,the UNet++network had better segmentation performance in adipose tissue than SM.
文摘Objective To observe the value of preoperative CT radiomics models for predicting composition of in vivo urinary calculi.Methods Totally 543 urolithiasis patients were retrospectively enrolled and divided into calcium oxalate monohydrate stone group(group A,n=373),anhydrous uric acid stone group(group B,n=86),carbonate apatite group(group C,n=30),ammonium urate stone group(group D,n=28)and ammonium magnesium phosphate hexahydrate stone group(group E,n=26)according to the composition of calculi,also divided into training set and test set at the ratio of 7∶3.Radiomics features were extracted and screened based on plain CT images of urinary system.Five binary task models(model A—E corresponding to group A—E)and a quinary task model were constructed using least absolute shrinkage and selection operator algorithm for predicting the composition of calculi in vivo.Then receiver operating characteristic curves were drawn,and the area under the curves(AUC)were calculated to evaluate the predictive efficacy of binary task models,while the accuracy,precision,recall and F1 score were used to evaluate the predictive efficacy of the quinary task model.Results All binary task models had good efficacy for predicting the composition of urinary calculi in vivo,with AUC of 0.860—0.948 in training set and of 0.856—0.933 in test set.The accuracy,precision,recall and F1 score of the quinary task model for predicting the composition of in vivo urinary calculi was 82.25%,83.79%,46.23%and 0.596 in training set,respectively,while was 80.63%,75.26%,43.48%and 0.551 in test set,respectively.Conclusion Binary task radiomics models based on preoperative plain CT had good efficacy for predicting the composition of in vivo urinary calculi,while the quinary task radiomics model had high accuracy but relatively poor stability.
文摘Objective To observe value of 0D-1D coupling model and 3D fluid-structure interaction(FSI)model based on coronary CT angiography(CCTA)for displaying hemodynamic characteristics of coronary artery stenosis.Methods Based on CCTA data of the stenosed left anterior descending branch(LAD)in a patient with coronary heart disease,an 0D-1D coupling model and 3D FSI model were built,respectively.Then hemodynamic characteristic indexes,including the pressure,flow velocity and wall shear stress(WSS)were obtained in every 0.01 s during 1 s at 5 sampling points(i.e.sampling point 1—5)using these 2 models,respectively,and the consistencies of the results between models were evaluated with Spearman correlation coefficient r s.Results The time consuming for construction of 0D-1D coupling model and 3D FSI model was 0.033 min and 704 min,respectively.Both models showed basically distribution of the pressure,flow velocity and WSS of the stenosed LAD.For more details,the pressure at the stenosed segment of LAD and the proximal segment of stenosis were both higher,which gradually decreased at the distal segment of stenosis,and the flow velocity at the proximal segment of stenosis was in a relatively slow and uniform condition,with significantly increased flow velocity and WSS at the stenosed segment.Compared with 3D FSI model,0D-1D vascular coupling model was relatively unrefined and lack of distal flow lines when displaying blood flow velocity.For sampling point 2 at the stenosed segment of LAD,no significant consistency for pressure between 2 models was found(P=0.118),but strong consistency for the flow velocity and WSS(r s=0.730,0.807,both P<0.05).The consistencies of pressure,flow velocity and WSS between 2 models at the proximal and distal segment of stenosis,i.e.1,3—5 sampling points were week to moderate(r s=0.237—0.669,all P<0.05).Conclusion 0D-1D coupling model exhibited outstanding computational efficiency and might provide relatively reasonable results,while 3D FSI model showed higher accuracy for details and streamline when simulating LAD stenosis.
