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 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 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
Teaching assessment plays a very important part in college English teaching, and effective formative assessment can encourage students＇ learner autonomy, improve their ability, and stimulate their creativity as well....Teaching assessment plays a very important part in college English teaching, and effective formative assessment can encourage students＇ learner autonomy, improve their ability, and stimulate their creativity as well. Based on the foreign and domestic studies, this paper first reviews the definition and types of assessment, and then analyses the factors which influence the application of formative assessment in the process of college English teaching.展开更多
Objective: To study the imaging features of extra-axial tumors and tumor-likelesions involving both middle and posterior cranial fossae and to make a classification. Methods:Sixty cases of pathologically confirmed ext...Objective: To study the imaging features of extra-axial tumors and tumor-likelesions involving both middle and posterior cranial fossae and to make a classification. Methods:Sixty cases of pathologically confirmed extra-axil tumors and tumor-like lesions involving bothmiddle and posterior cranial fossae were analyzed. They were divided into central and lateral types,the latter of which were subdivided into three types: middle cranial fossae type, posterior cranialfossae type and the over-riding type. The constitution and imaging features of each type wereanalyzed. Results: There were 12 cases of central type, including chordoma (n=5), pituitary adenoma(n=3), nasopharyngeal carcinoma (n=2), craniopharyn-gioma (n=1) and meningioma (n=l). 48 cases oflateral type including trigeminal nerve tumors (n=14), meningioma (n=12), epidermoid cyst (n=11),dural cavernous hemangioma (n=4), dermoid cyst (n=2), metastasis (n=2), hemangiopericytoma (n=1),paraganglioma of glonius jugular (n=1) and nasopharyngeal carcinoma (n=1). Each type of the lesionshad its own shape features, some of which were characteristic for some specific tumors. Most of thetumors and tumor-like lesions could be qualitatively diagnosed according to their imagingcharacteristics and the extent of the lesions could be defined definitely. Conclusion: It is helpfulto categorize extra-axial tumors and tumor-like lesions involving both middle and posterior cranialfossae according to their location for qualitative diagnosis and description of the extent of theselesions. It is of great clinical value in providing more precise and thorough imaging informationfor planning therapeutic methods and route of operation.展开更多
Imaging technologies are utilized to study the brain morphology and the functions of rat models of Parkinson disease （PD）. Magnetic resonance imaging （MRI） and magnetic resonance angiography （MRA） are used to ob...Imaging technologies are utilized to study the brain morphology and the functions of rat models of Parkinson disease （PD）. Magnetic resonance imaging （MRI） and magnetic resonance angiography （MRA） are used to obtain morphological imaging data. Functional imaging data, such as the spectrum and blood flow changes are obtained by proton magnetic resonance spectroscopy （1H-MRS） and CT perfusion （CTP）. Results show that PD rat models have no characteristic morphological imaging abnormalities, but exist regional cerebral blood flow （CBF） reductions and spectral changes in the striatum.展开更多
Objective: To evaluate the clinical and radiological factors that affect therecurrence of the meningioma patient so as to effectively prevent and cure recurrence of meningiomapatients more earlier. Methods: The clinic...Objective: To evaluate the clinical and radiological factors that affect therecurrence of the meningioma patient so as to effectively prevent and cure recurrence of meningiomapatients more earlier. Methods: The clinical features and radiological aspects in 145 cases ofmeningiomas undergoing operation during 1993-1997 were retrospectively studied. The data of only 83cases of all 145 cases were available. The factors were evaluated with univariate and multivariateanalysis. Results: With univariate analysis, 7 factors showed highly significance to recurrence ofmeningiomas: tumor size, tumor location, tumor shape, edema, extent of resection, pathologicalgrade, CT enhancement. With multivariate analysis, 4 factors showed significant danger to recurrenceof meningiomas: pathological grade, extent of resection, tumor shape and CT enhancement.Conclusion: The main factors that affect the recurrence of meningioma patients are pathologicalgrade, extent of resection, tumor shape and CT enhancement.展开更多
[Objective] The goal of this paper was to measure anemia prevalence and identify factors that correlate with anemia among school-aged children in rural areas, provide a scientific basis for effective prevention and tr...[Objective] The goal of this paper was to measure anemia prevalence and identify factors that correlate with anemia among school-aged children in rural areas, provide a scientific basis for effective prevention and treatment. [Method] The data set covered three provinces in northwest area. We detected hemoglobin of the sample pupils randomly chosen from the 3rd-6th grade of 305 rural elementary schools in 26 poor counties, and carried out questionnaires among them. [Result] 25.24% of the pupils had anemia, most of them were girl and the lower grade stu- dents. The multiple-regression revealed that the eating habits and family condition had certain impact on their anemia. [Conclusion] Anemia is still a serious problem of rural pupils. Improving diet conditions, providing balanced meals, enhancing the knowledge of the principals, teachers and parents about anemia and the importance of students＇ nutritional status and health contribute to the prevention and treatment of anemia of rural pupils.展开更多
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 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 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.
文摘Teaching assessment plays a very important part in college English teaching, and effective formative assessment can encourage students＇ learner autonomy, improve their ability, and stimulate their creativity as well. Based on the foreign and domestic studies, this paper first reviews the definition and types of assessment, and then analyses the factors which influence the application of formative assessment in the process of college English teaching.
文摘Objective: To study the imaging features of extra-axial tumors and tumor-likelesions involving both middle and posterior cranial fossae and to make a classification. Methods:Sixty cases of pathologically confirmed extra-axil tumors and tumor-like lesions involving bothmiddle and posterior cranial fossae were analyzed. They were divided into central and lateral types,the latter of which were subdivided into three types: middle cranial fossae type, posterior cranialfossae type and the over-riding type. The constitution and imaging features of each type wereanalyzed. Results: There were 12 cases of central type, including chordoma (n=5), pituitary adenoma(n=3), nasopharyngeal carcinoma (n=2), craniopharyn-gioma (n=1) and meningioma (n=l). 48 cases oflateral type including trigeminal nerve tumors (n=14), meningioma (n=12), epidermoid cyst (n=11),dural cavernous hemangioma (n=4), dermoid cyst (n=2), metastasis (n=2), hemangiopericytoma (n=1),paraganglioma of glonius jugular (n=1) and nasopharyngeal carcinoma (n=1). Each type of the lesionshad its own shape features, some of which were characteristic for some specific tumors. Most of thetumors and tumor-like lesions could be qualitatively diagnosed according to their imagingcharacteristics and the extent of the lesions could be defined definitely. Conclusion: It is helpfulto categorize extra-axial tumors and tumor-like lesions involving both middle and posterior cranialfossae according to their location for qualitative diagnosis and description of the extent of theselesions. It is of great clinical value in providing more precise and thorough imaging informationfor planning therapeutic methods and route of operation.
基金Supported by the National Natural Science Foundation of China (30671997)~~
文摘Imaging technologies are utilized to study the brain morphology and the functions of rat models of Parkinson disease （PD）. Magnetic resonance imaging （MRI） and magnetic resonance angiography （MRA） are used to obtain morphological imaging data. Functional imaging data, such as the spectrum and blood flow changes are obtained by proton magnetic resonance spectroscopy （1H-MRS） and CT perfusion （CTP）. Results show that PD rat models have no characteristic morphological imaging abnormalities, but exist regional cerebral blood flow （CBF） reductions and spectral changes in the striatum.
文摘Objective: To evaluate the clinical and radiological factors that affect therecurrence of the meningioma patient so as to effectively prevent and cure recurrence of meningiomapatients more earlier. Methods: The clinical features and radiological aspects in 145 cases ofmeningiomas undergoing operation during 1993-1997 were retrospectively studied. The data of only 83cases of all 145 cases were available. The factors were evaluated with univariate and multivariateanalysis. Results: With univariate analysis, 7 factors showed highly significance to recurrence ofmeningiomas: tumor size, tumor location, tumor shape, edema, extent of resection, pathologicalgrade, CT enhancement. With multivariate analysis, 4 factors showed significant danger to recurrenceof meningiomas: pathological grade, extent of resection, tumor shape and CT enhancement.Conclusion: The main factors that affect the recurrence of meningioma patients are pathologicalgrade, extent of resection, tumor shape and CT enhancement.
文摘[Objective] The goal of this paper was to measure anemia prevalence and identify factors that correlate with anemia among school-aged children in rural areas, provide a scientific basis for effective prevention and treatment. [Method] The data set covered three provinces in northwest area. We detected hemoglobin of the sample pupils randomly chosen from the 3rd-6th grade of 305 rural elementary schools in 26 poor counties, and carried out questionnaires among them. [Result] 25.24% of the pupils had anemia, most of them were girl and the lower grade stu- dents. The multiple-regression revealed that the eating habits and family condition had certain impact on their anemia. [Conclusion] Anemia is still a serious problem of rural pupils. Improving diet conditions, providing balanced meals, enhancing the knowledge of the principals, teachers and parents about anemia and the importance of students＇ nutritional status and health contribute to the prevention and treatment of anemia of rural pupils.
