Objective To evaluate the performance of reconstruction networks with different sparse views under the condition of keeping the same number of model parameters.Methods The number of network channels and network layers were adjusted to make the parameter quantity of each network similar when keeping the structure of each image-domain network and dual-domain network unchanged.The reconstruction performance of each network at different sparsity levels was compared.The AAPM Low-Dose CT Grand Challenge datasets were used in the experiment,including 10 976 images for training,979 images for validation,and 4 256 images for testing.The performance of each model was evaluated visually in combination with objective metrics such as peak signal-to-noise ratio,structural similarity and root mean square error.Results Before adjusting the model parameters,the hybrid domain network Tensor-Net obtained the best visual evaluation and objective evaluation metrics.After parament adjustment,with a similar number of parameters,Tensor-Net outperformed the other models at various projection angles in image anatomical detail recovery,but its structural similarity was slightly lower than that of RED-CNN.The parameters of the hybrid domain model Dual-FBPConvNet were all worse than those of FBPConvNet.Conclusion The hybrid domain model is advantageous in sparse-view CT reconstruction,but it faces more serious overfitting problems.Using a larger image domain model can achieve results similar to those of hybrid domain model.

Objective To investigate the low-dose CT image denoising and generalization performance of the existing mainstream deep learning based denoising networks.Methods The public AAPM Mayo challenge dataset was used to train the denoising network using 3 image-domain methods(REDCNN,WGAN-VGG,CTformer)and 2 projection-image dual-domain methods(VVBP-UNet,CLEAR),separately.The denoising networks were evaluated quantitatively for peak signal-to-noise ratio(PSNR),structural similarity index,root mean square error,number of network parameters and floating point operations,and their generalization performance was analyzed on the AbdomenCT-1K Dataset.Results Image-domain denoising networks effectively suppressed low-dose CT image noise,with REDCNN demonstrating the best denoising performance and achieving a PSNR of 42.0988 dB.The dual-domain denoising networks were better at preserving tiny tissue structures while removing image noise,with VVBP-UNet performing the best and increasing PSNR to 42.150 9 dB.Conclusion The projection-image dual-domain method exhibits superior denoising and generalization performances than the image-domain method,despite requiring a relatively large amount of network parameters and computations.When computing resources are sufficient,the denoising results obtained by dual-domain method better fulfill the requirements for clinical diagnosis.

Objective To investigate the low-dose CT image denoising and generalization performance of the existing mainstream deep learning based denoising networks.Methods The public AAPM Mayo challenge dataset was used to train the denoising network using 3 image-domain methods(REDCNN,WGAN-VGG,CTformer)and 2 projection-image dual-domain methods(VVBP-UNet,CLEAR),separately.The denoising networks were evaluated quantitatively for peak signal-to-noise ratio(PSNR),structural similarity index,root mean square error,number of network parameters and floating point operations,and their generalization performance was analyzed on the AbdomenCT-1K Dataset.Results Image-domain denoising networks effectively suppressed low-dose CT image noise,with REDCNN demonstrating the best denoising performance and achieving a PSNR of 42.0988 dB.The dual-domain denoising networks were better at preserving tiny tissue structures while removing image noise,with VVBP-UNet performing the best and increasing PSNR to 42.150 9 dB.Conclusion The projection-image dual-domain method exhibits superior denoising and generalization performances than the image-domain method,despite requiring a relatively large amount of network parameters and computations.When computing resources are sufficient,the denoising results obtained by dual-domain method better fulfill the requirements for clinical diagnosis.

Objective To evaluate the performance of reconstruction networks with different sparse views under the condition of keeping the same number of model parameters.Methods The number of network channels and network layers were adjusted to make the parameter quantity of each network similar when keeping the structure of each image-domain network and dual-domain network unchanged.The reconstruction performance of each network at different sparsity levels was compared.The AAPM Low-Dose CT Grand Challenge datasets were used in the experiment,including 10 976 images for training,979 images for validation,and 4 256 images for testing.The performance of each model was evaluated visually in combination with objective metrics such as peak signal-to-noise ratio,structural similarity and root mean square error.Results Before adjusting the model parameters,the hybrid domain network Tensor-Net obtained the best visual evaluation and objective evaluation metrics.After parament adjustment,with a similar number of parameters,Tensor-Net outperformed the other models at various projection angles in image anatomical detail recovery,but its structural similarity was slightly lower than that of RED-CNN.The parameters of the hybrid domain model Dual-FBPConvNet were all worse than those of FBPConvNet.Conclusion The hybrid domain model is advantageous in sparse-view CT reconstruction,but it faces more serious overfitting problems.Using a larger image domain model can achieve results similar to those of hybrid domain model.

Objective To study epidemic of schistosomiasis in the Qiandao Lake reservoir area,and to provide a reference for prevention and control of schistosomiasis in the construction of large water conservancy projects in the epidemic area of schistosomiasis.Methods The data over the years of snail condition and monitoring of schistosomiasis before and after building the dam,and water conservancy project reconstruction related information were collected.Based on the survey results of the river channel,the lake beach and the dissipation zone in the reservoir area,the influence of Xin'an River water conservancy project on epidemic of schistosomiasis in the Qiandao Lake reservoir area was analyzed,and the epidemic factors of the schistosomiasis in the Three Gorges reservoir were compared and analyzed.Results Before the dam was built,an area of 38 144 000 m2 was examined but Oncomelania was undetected.The Qiandao Lake reservoir area belonged to a non epidemic area of schistosomiasis.After the dam was built,557 cases of schistosomiasis were found in 6 232 immigrants during 1962-1965,resulting in an imported epidemic.In 1970-1980,an area of 379 654 m2 in which Oncomelania was found was examined and snails were mainly distributed in some rice fields and ditches in the end of the reservoir.949 cases of local schistosomiasis were found in the snails.The condition and condition of the snail are gradually controlled through several decades of comprehensive prevention and control.Compared with the epidemic factors of schistosomiasis in Qiandao Lake and the Three Gorges reservoir,the environment of elevation beach and ecologically fragile fluctuation zone coexist in the two reservoir areas.Conclusion From the long-term longitudinal monitoring data of the Qiandao Lake reservoir area and the epidemic regularity of schistosomiasis and the comparison with the ecology of the Three Gorges reservoir,it is concluded that the two reservoir areas will not cause a large range of schistosomiasis epidemic in general,but it does not exclude the possibility of the breeding of the inputting Oncomelania.

BACKGROUNDMyocarditis is a common, potentially life-threatening disease that presents a wide rang of symptoms in children, as an important underlying etiology of other myocardial diseases such as dilated and arrhythmogenic right ventricular cardiomyopathy. The incidence of nonfatal myocarditis is probably greater than that of the one actually diagnosed, which is the result of the challenges of establishing the diagnosis in standard clinical settings. Currently, no single clinical or imaging finding confirms the diagnosis of myocarditis with absolute certainty. Historically, clinical exam, electrocardiogram (ECG), serology and echocardiography had an unsatisfactory diagnostic accuracy in myocarditis. Endomyocardial biopsy remains as a widely accepted standard, but may not be suitable for every patient, especially for those with less severe disease. Our aim was to find the changes in cardiovascular magnetic resonance (CMR) imaging of children with myocarditis diagnosed by clinical criteria.

METHODSWe studied 25 children (18 male, 7 female; aged from 5-17 years) with diagnosed myocarditis by clinical criteria. CMR included function analyses, T2-weighted imaging, T1-weighted imaging before and after i.v. gadolinium injection (early gadolinium enhancement (EGE) and late gadolinium enhancement (LGE)).

RESULTSThe T2 ratio was elevated in 21 children (84%, 11 in anterolateral (44%), 5 in inferolateral (20%), and 5 in septum (20%)), EGE was present in 9 children (36%, 3 in anterolateral (12%), 4 in inferolateral (20%), and 2 in septum (8%)), and LGE was present in 5 children (20%, 2 in anterolateral (8%), 1 in inferolateral (4%), 1 in septum (4%), and 1 in midwall of left ventricular (LV) wall). In 9 children (36%), two (or more) out of three sequences (T2, EGE, LGE) were abnormal.

CONCLUSIONSThe CMR findings in children with clinically diagnosed myocarditis vary within the groups, including regional or global myocardial signal increase in T2-weighted images, EGE and LGE in T1-weighted images. The T2 ratio elevation is the most common CMR finding. Children with mild cardiac symptoms may also appear serious myocardial injuries.

Adolescent ; Child ; Child, Preschool ; Female ; Humans ; Magnetic Resonance Imaging ; methods ; Male ; Myocarditis ; pathology ; Myocardium ; pathology

Background Myocarditis is a common,potentially life-threatening disease that presents a wide rang of symptoms in children,as an important underlying etiology of other myocardial diseases such as dilated and arrhythmogenic right ventricular cardiomyopathy.The incidence of nonfatal myocarditis is probably greater than that of the one actually diagnosed,which is the result of the challenges of establishing the diagnosis in standard clinical settings.Currently,no single clinical or imaging finding confirms the diagnosis of myocarditis with absolute certainty.Historically,clinical exam,electrocardiogram (ECG),serology and echocardiography had an unsatisfactory diagnostic accuracy in myocarditis.Endomyocardial biopsy remains as a widely accepted standard,but may not be suitable for every patient,especially for those with less severe disease.Our aim was to find the changes in cardiovascular magnetic resonance (CMR) imaging of children with myocarditis diagnosed by clinical criteria.Methods We studied 25 children (18 male,7 female; aged from 5-17 years) with diagnosed myocarditis by clinical criteria.CMR included function analyses,T2-weighted imaging,T1-weighted imaging before and after i.v.gadolinium injection (early gadolinium enhancement (EGE) and late gadolinium enhancement (LGE)).Results The T2 ratio was elevated in 21 children (84％,11 in anterolateral (44％),5 in inferolateral (20％),and 5 in septum (20％)),EGE was present in 9 children (36％,3 in anterolateral (12％),4 in inferolateral (20％),and 2 in septum (8％)),and LGE was present in 5 children (20％,2 in anterolateral (8％),1 in inferolateral (4％),1 in septum (4％),and 1 in midwall of left ventricular (LV) wall).In 9 children (36％),two (or more) out of three sequences (T2,EGE,LGE) were abnormal.Conclusions The CMR findings in children with clinically diagnosed myocarditis vary within the groups,including regional or global myocardial signal increase in T2-weighted images,EGE and LGE in T1-weighted images.The T2 ratio elevation is the most common CMR finding.Children with mild cardiac symptoms may also appear serious myocardial injuries.

ObjectiveTo assess the performance of dual-source CT (DSCT) for left atrial volume and function evaluation and compare this performance to that of cardiac cine MR ( CMR ),which was considered as the standard reference technique.Methods Forty-nine patients referred for CT coronary angiography were enrolled in this study.DSCT data sets and FIESTA cines of the vertical long axis covering the left atrium and the short axis covering the left ventricle were obtained on the same day without additional medicine.All images were analyzed to obtain left atrial volume at different time and its function values.All the parameters were corrected by body surface area.Inter-modality agreement was tested through linear regression and Bland-Altman analyses.Repeated measurements were performed to determine inter-observer variation.ResultsThe indexed measurements of DSCT and CMR were (47.4 ± 11.1 ) and (46.2 ± 9.7 )ml/m2 for LAVmax,( 22.2 ± 6.9) and ( 21.3 ± 5.8 ) ml/m2 for LAVmin,( 34.8 ± 8.8 ) and ( 33.6 ± 7.8 )ml/m2 for LAVp,(24.0 ±5.7)and(21.5 ±5.0) ml/m2 for LARV,(11.6 ±3.9)and(10.9 ±3.9) ml/m2 for LAPV,(12.4 ±3.9)and(10.7 ±3.6) ml/m2 for LAAV,(22.6 ±8.4)and(21.0 ±6.4) ml/m2 for LACV,(52.8 ± 7.4) ％ and ( 54.5 ± 6.3 ) ％ for LAEF,respectively.The correlation coefficients between DSCT and CMR measurements for LAVmax,LAVmin,LAVp,LARV,LAPV,LAAV,LACV and LAEF were 0.89,0.90,0.90,0.80,0.82,0.80,0.76 and 0.78,respectively.However,DSCT slightly overestimated LAVmax,LAVmin,LAVp,LARV,LAPV,LAAV and LACV,and the deviation was 1.2,0.9,1.1,0.3,0.1,0.2 and 0.4 ml/m2,respectively.Compared with CMR,DSCT slightly underestimated LAEF of about 0.6％.Interobserver variation was lower in DSCT examination than CMR for the measurements of left atrial function.ConclusionDSCT provided accurateand reproducible measurements of left atrial volume and function.

To explore diagnostic acuity of helical CT colonscopic examination, simulated polyps were reproduced in 10 pig colons and 6 human colons obtained from colon resection. Helical CT colonoscopic scanning with different parameters was performed. The images were evaluated with Nav, Axial+MPR, SSD+Raysum. The diagnostic sensitivity of each method for the detection of simulated colonic polyps were assessed. The results indicated that the image quality of CT colonoscopy was improved with the decrease in collimation and pitch. The optimal angle of the colon lumen to the gantry was 90?. CT colonoscopy was superior to other imaging methods. Therefore, the performance of CTVC has a close relationship with the scanning parameters. The optimal scanning parameters were 5mm collimation, 1 5 pitch, and filling the colon with air. The combination of CTVC with other imaging methods would contribute to improving the diagnostic accuracy for the detection of colonic polyps.

0.05). The interobserver variability in DSCT measurements was lower than in RT-3DE measurements in indexed left atrial volume and function. Conclusion DSCT can provide not only the information of coronary artery,but also highly reliable measurements of left atrial phasic volume and function at the same time.