Objective To propose a novel method based on three-dimensional depthwise separable convolution network(3D DSN)for the separation of PET images with dual tracers of 18F-FDG and 18F-FAPI.Methods A total of 120 pairs of 18F-FDG and 18F-FAPI PET images of the same patient scanned separately at different time points were collected,and the dual-tracer PET image was generated through simulation.After the image registration of PET images of two tracers for ensuring spatial position matching,the registered PET images were forward-projected to generate sinogram data,and the sinogram data of two tracers were accumulated to obtain mixed sinogram data.Subsequently,the dual-tracer PET image was reconstructed using maximum likelihood expectation maximization and input into a 3D DSN based network for image separation,thereby obtaining PET images of two single tracers.Results Compared with 3D CNN method,the proposed method increased the structure similarity index measure(SSIM)of the separated 18F-FDG images to the real 18F-FDG images by 0.87%,increased the peak signal-to-noise ratio(PSNR)by 11.8%,and reduced the normalized root mean square error(NRMSE)by 52%.The SSIM of the separated 18F-FAPI images to the real 18F-FAPI images increased by 1.1%,PSNR increased by 17.0%,and NRMSE decreased by 51%.Conclusion The proposed method can be effectively applied to simultaneous PET imaging with dual PET tracers,reducing the number of scans and costs in time and money,and providing clinical doctors more accurate and abundant diagnostic information.

Objective To propose a novel method based on three-dimensional depthwise separable convolution network(3D DSN)for the separation of PET images with dual tracers of 18F-FDG and 18F-FAPI.Methods A total of 120 pairs of 18F-FDG and 18F-FAPI PET images of the same patient scanned separately at different time points were collected,and the dual-tracer PET image was generated through simulation.After the image registration of PET images of two tracers for ensuring spatial position matching,the registered PET images were forward-projected to generate sinogram data,and the sinogram data of two tracers were accumulated to obtain mixed sinogram data.Subsequently,the dual-tracer PET image was reconstructed using maximum likelihood expectation maximization and input into a 3D DSN based network for image separation,thereby obtaining PET images of two single tracers.Results Compared with 3D CNN method,the proposed method increased the structure similarity index measure(SSIM)of the separated 18F-FDG images to the real 18F-FDG images by 0.87%,increased the peak signal-to-noise ratio(PSNR)by 11.8%,and reduced the normalized root mean square error(NRMSE)by 52%.The SSIM of the separated 18F-FAPI images to the real 18F-FAPI images increased by 1.1%,PSNR increased by 17.0%,and NRMSE decreased by 51%.Conclusion The proposed method can be effectively applied to simultaneous PET imaging with dual PET tracers,reducing the number of scans and costs in time and money,and providing clinical doctors more accurate and abundant diagnostic information.

Objective The prediction of RR intervals in hypertensive patients can help clinicians to analyze and warn patients'heart condition.Methods Using 8 patients'data as samples,the RR intervals of patients were predicted by long short-term memory network(LSTM)and gradient lift tree(XGBoost),and the prediction results of the two models were combined by the inverse variance method to overcome the disadvantage of single model prediction.Results Compared with the single model,the proposed combined model had a different degree of improvement in the prediction of RR intervals in 8 patients.Conclusion LSTM-XGBoost model provides a method for predicting RR intervals in hypertensive patients,which has potential clinical feasibility.

Objective To evaluate the predictive value of T2-fluid attenuated inversion recovery (FLAIR)signal suppression rate for the short arm of chromosome 1 and long arm of chromosome 19 (1p/19q)molecular features in lower-grade gliomas (LGG),and to construct and verify the predictive model based on magnetic resonance imaging (MRI)tumor features and T2-FLAIR signal suppression rate.Methods Clincal and imaging data of the patients with pathologically confirmed supratentorial LGG (WHO grade 2～3)in our medical center from 2017 to 2021 were collected and retrospectively analyzed.According to the results of postoperative molecular pathology,they were divided into 1 p/19q-codeleted (1 p/19q-Codel)and 1 p/19q-noncodeleted (1 p/19q-Noncodel)groups.MRI tumor features were blindly assessed by 2 neuroradiologists.Five circular regions of interest were respectively delineated in the tumor area and the normal-appearing white matter in contralateral semioval center using the hot-spot method in order to calculate the T2-FLAIR signal suppression rate.The differences of clinical features,MRI tumor features and T2-FLAIR signal suppression rate were analyzed between the 2 groups.Univariate and multivariate logistic regression analyses were used to screen independent predictors and constructa predictive model and nomogram.Receiver operating characteristic (ROC)curve,calibration curve and Hosmer-Lemeshow test were applied to assess the model performance,and the model was internally validated by bootstrap method.Results A total of 146 supratentorial LGG patients were enrolled,including 68 being assigned into the 1 p/19q-Codel group and 78 into the 1 p/19q-Noncodel group.The T2-FLAIR signal suppression rate was 0.43 (0.28,0.62)in the 1 p/19q-Noncodel group,which was significantly higher than that in the 1 p/19q-Codel group[0.29 (0.24,0.35),P<0.001].Multivariate logistic regression analysis showed that T2-FLAIR signal suppression rate>0.374 (P<0.001),cortex infiltration (P=0.001) and calcification (P=0.004) were independent predictors for 1 p/19q status.The AUC value of T2-FLAIR signal suppression rate>0.374 in predicting 1 p/19q-Noncodel was 0.720,the sensitivity was 60.26％ and the specificity was 83.82％.DeLong test indicated that T2-FLAIR signal suppression rate>0.374 was more effective than T2-FLAIR mismatch sign in predicting 1 p/19q molecular features (P<0.001).ROC curve analysis suggested that the predictive model established by T2-FLAIR signal suppression rate>0.374 combined with cortex infiltration and calcification had good performance,with an AUC value of 0.808,and the AUC value verified internally by bootstrap method was 0.807.At the same time,the calibration and goodness of fit of the model were good.Conclusion T2-FLAIR signal suppression rate can be used as a quantitative imaging marker to predict 1 p/19q-Noncodel LGG.The predictive model with T2-FLAIR signal suppression rate>0.374 combined with cortex infiltration and calcification can effectively predict 1 p/19q molecular features.

Various types of software needed in radiomics studies come with the problems such as data incompatibility and hyperparameter tuning.Therefore,an artificial intelligence-based software is developed for radiomics studies,providing doctors and researchers a solution with image preprocessing,feature extraction,feature selection,modeling analysis and data visualization.The usability of the software is demonstrated using a public data set.Eight sets of feature selectors and classifiers are established for classification predication on test data set and key performance indicator output.Through hyperparameter tuning,the model is further optimized.Researchers will focus more on the research itself rather than unnecessary development efforts,and radiomics studies will become more convenient and efficient with the software addressed.

Various types of software needed in radiomics studies come with the problems such as data incompatibility and hyperparameter tuning.Therefore,an artificial intelligence-based software is developed for radiomics studies,providing doctors and researchers a solution with image preprocessing,feature extraction,feature selection,modeling analysis and data visualization.The usability of the software is demonstrated using a public data set.Eight sets of feature selectors and classifiers are established for classification predication on test data set and key performance indicator output.Through hyperparameter tuning,the model is further optimized.Researchers will focus more on the research itself rather than unnecessary development efforts,and radiomics studies will become more convenient and efficient with the software addressed.

Objective:To systematically evaluate the efficacy and safety of obinutuzumab-based regimen versus rituximab-based regimen in treatment of B-cell non-Hodgkin lymphoma (B-NHL).Methods:The Cochrane clinical controlled trials database, PubMed, Embase, American Society of Hematology meeting proceedings, American Society of Clinical Oncology annual meeting proceedings and ClinicalTrails database were searched for studies on the use of regimens containing obinutuzumab or rituximab for the treatment of B-NHL. Patients were divided into obinutuzumab group and rituximab group according to their medication status. Review Manager 5.3 software was used to compare the efficacy and safety of the two groups.Results:A total of 7 randomized controlled trials were selected, including 4 235 patients (1 430 cases of follicular lymphoma, 2 102 cases of diffuse large B-cell lymphoma, and 703 cases of other B-NHL); 2 121 cases were in the obinutuzumab group and 2 114 cases were in the rituximab group. Among 4 162 patients who could be evaluated, the objective response rate (ORR) in the obinutuzumab group was higher than that in the rituximab group [75.1% (1 565/2 083) vs. 72.7% (1 512/2 079); OR = 1.19, 95% CI 1.01-1.41, P = 0.03]. Progression-free survival (PFS) in the obinutuzumab group was better than that in the rituximab group ( HR = 0.86, 95% CI 0.75-0.99, P = 0.03). Among 3 542 patients who could be evaluated for adverse reactions, the incidence of grade 3-4 adverse reactions in the otuzumab group was higher than that in the rituximab group [61.8% (1 098/ 1 776) vs. 54.2% (958/1 766); OR = 1.50, 95% CI 1.29-1.74, P < 0.001], the incidence of grade 3-4 infusive-related adverse reactions [7.5% (158/1 776) vs. 3.1% (65/1 766); OR = 2.56, 95% CI 1.91-3.45, P < 0.001] and neutropenia [34.1% (597/1 749) vs. 29.4% (511/1 738); OR = 1.27, 95% CI 1.09-1.47, P = 0.002] in the obinutuzumab group were higher than those in the rituximab group. Conclusions:The ORR and PFS of B-NHL patients treated with obinutuzumab-based regimen are better than those treated with rituximab-based regimen, but the influence of adverse reactions should be considered when selecting the regimen.

In this article, a case for random signal interference in resolver (or encoder) of carousel on Varian VitalBeam medical linear accelerator was illustrated. This case was considered as a rare failure of the technology platform (including TrueBeam) by Chinese, European and American technical experts in Varian. In this article, the differences of the carousel in the structure and control system between VitalBeam and traditional accelerator were comparatively analyzed to enable the peers to have a deeper understanding of resolver. The logic and methods to solve the fault were summarized, providing reference experience for analyzing the problems related to carousel. It is found that the interlocking system is imperfect, which provides a factual and technological basis for Varian to optimize the system.

ObjectiveTo analyze the mental health status of non-psychiatric inpatients in a general hospital， and to explore the relevant influencing factors， so as to provide references for the screening of mental health problems and the construction of intervention models among non-psychiatric inpatients. MethodsA cross-sectional study was conducted among 916 non-psychiatric inpatients in a third grade class A general hospital in Guangzhou， and all the inpatients were assessed using Patient Health Questionnaire-9 item （PHQ-9）， Generalized Anxiety Disorder-7 item （GAD-7）， Athens Insomnia Scale （AIS） and Columbia-Suicide Severity Rating Scale （C-SSRS） to detect their depression， anxiety， insomnia and suicide risk status. Thereafter， univariate and multivariate Logistic regression analysis were used to screen the risk factors affecting the mental health of inpatients. ResultsA total of 339 （37.0%） inpatients with positive mental health problems were screened， and the screening results for each dimension revealed 218 cases （23.8%） of depression， 141 cases （15.4%） of anxiety， 257 cases （28.1%） of insomnia， 42 cases （4.6%） of suicidal ideation and 7 cases （0.8%） of suicidal behavior. Binary Logistic regression analysis showed that female （OR=1.379， P<0.05） was a risk factor for positive screening of mental health problems. Ordinal Logistic regression analysis denoted that age above 60 years old （OR=1.542， P<0.05） and singlehood （OR=2.055， P<0.05） were risk factors affecting the severity of depression， while senior high school to junior college education （OR=0.524， P<0.05） was a protective factor of depression， meantime， female （OR=1.472， P<0.05） was a risk factor affecting the severity of insomnia. ConclusionMental health problems are quite common among non-psychiatric inpatients in general hospitals， and are mainly affected by factors such as gender， age， marital status and educational background.

Objective To systematically explore the efficacy of four intervention regiments including desmopressin, alarm, desmopressin combined with alarm, and desmopressin combined with anticholinergic drugs in the treatment of monosymptomatic nocturnal enuresis in children by network meta-analysis. Methods The databases of PubMed, Cochrance Library, EMBase and Web of Science were systematically searched and retrieved upto August 1, 2017. Included were the randomized controlled trials (RCTs) which had any two or more of four intervention regiments (desmopressin, alarm, desmopressin combined with alarm, and desmopressin combined with anticholinergic drugs) for treatment of monosymptomatic nocturnal enuresis in children. The literature was screened according to the established inclusion and exclusion criteria, and the data extraction and quality evaluation were performed for the final inclusion of RCT. Software R 3.3.2 and STATA 14.0 were used for data analysis. Results Fifteen RCTs were included with a total of 1505 children. Network meta-analysis showed that the complete response rate and success rate of desmopressin combined with anticholinergic drugs were higher than those of desmopressin (complete reaction rate: OR=2.8, 95％ CI :1.5～5.4; success rate: OR=3.5, 95％ CI :1.7～7.5) and alarm (complete response rate: OR=2.7, 95％ CI :1.1～6.6; success rate: OR=3.8, 95％ CI: 1.6～9.0. The success rate of desmopressin combined with alarm was higher than that of alarm (OR=1.9, 95％CI: 1.1～3.4) . The recurrence rate of alarm after treatment was significantly lower than that of desmopressin (OR=0.15, 95％CI: 0.03～0.53) . The ranking results showed that the complete response rate and success rate of desmopressin combined with anticholinergic drugs were the best. The desmopressin combined with alarm can minimize the number of bed-wetting episodes per week and the recurrence rate of alarm was the lowest among the four regiments. Conclusion The effect of desmopressin combined with anticholinergic drugs is significantly better than that of alarm or desmopressin alone. The combination of desmopressin and alarm has a slight advantage or similar effect to that of single alarm or desmopressin treatment. The effect of desmopressin is similar to that of alarm. Alarm treatment has the lowest recurrence rate.