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.

[Purpose]To analyze the cost-effectiveness and cost-utility conducted on the lung can-cer screening project in urban areas of Anhui Province,and to provide suggestions for the formu-lation of lung cancer screening policies in Anhui Province.[Methods]A Markov decision model for low-dose computed tomography(LDCT)lung cancer screening intervention was established based on on-site survey data and literature data.The development of the population under different interventions was simulated,using saved life years(LYS)and quality-adjusted life years(QALY)as effectiveness indicators,to conduct cost-effectiveness and cost-utility analyses of different screening strategies.Cost data were discounted at a 3％discount rate.[Results]The screening schemes of once a year,once every two years,once every three years,and once every five years all meet the cost-effectiveness principle for saving one LYS or QALY.Among them,the best screening strategy in terms of cost-effectiveness and cost-utility was the LDCT lung cancer screening strategy once every two years,with costs of 72 441.54 CNY and 71 050.24 CNY,respectively.[Conclusion]The LDCT lung cancer screening program demonstrates good cost-effectiveness,with strategies of dif-ferent screening frequencies being viable options.The optimal screening strategy is screening once every two years.

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.

[Purpose]To analyze the cost-effectiveness and cost-utility conducted on the lung can-cer screening project in urban areas of Anhui Province,and to provide suggestions for the formu-lation of lung cancer screening policies in Anhui Province.[Methods]A Markov decision model for low-dose computed tomography(LDCT)lung cancer screening intervention was established based on on-site survey data and literature data.The development of the population under different interventions was simulated,using saved life years(LYS)and quality-adjusted life years(QALY)as effectiveness indicators,to conduct cost-effectiveness and cost-utility analyses of different screening strategies.Cost data were discounted at a 3％discount rate.[Results]The screening schemes of once a year,once every two years,once every three years,and once every five years all meet the cost-effectiveness principle for saving one LYS or QALY.Among them,the best screening strategy in terms of cost-effectiveness and cost-utility was the LDCT lung cancer screening strategy once every two years,with costs of 72 441.54 CNY and 71 050.24 CNY,respectively.[Conclusion]The LDCT lung cancer screening program demonstrates good cost-effectiveness,with strategies of dif-ferent screening frequencies being viable options.The optimal screening strategy is screening once every two years.

Objective:To investigate the clinical characteristics and drug resistance of Klebsiella pneumoniae infections at different systems, providing laboratory reference for the rational use of antibiotics in clinical practice.Methods:The clinical characteristics and drug resistance of patients with Klebsiella pneumoniae infections in respiratory, urinary, hematologic, and other systems who received treatment in Wuzhou Red Cross Hospital from January 2015 to December 2021 were analyzed.Results:From 2015 to 2021, there were 3 496 cases of Klebsiella pneumoniae infections in the hospital, among which the respiratory system was most affected with 2 250 strains (64.34%). The sex ratio of patients with Klebsiella pneumoniae infections at different systems was statistically significant ( χ2 = 266.77, P < 0.001). The respiratory system and hematological system were more commonly infected by Klebsiella pneumoniae in men, while the urinary system was more commonly infected in women. The sex ratio of patients with Klebsiella pneumoniae infections at other systems were similar. The age distribution of patients with Klebsiella pneumoniae infections at different systems was significantly different ( χ2 = 176.54, P < 0.001). Klebsiella pneumoniae infections of the respiratory, urinary, and hematological systems were the most common in people aged > 60-80 years, while Klebsiella pneumoniae infections in other systems were mainly found in people aged > 18-60 years. There were significant differences in the distribution of departments among different Klebsiella pneumoniae infection systems ( χ2 = 1 415.30, P < 0.001). The ICU had the highest incidence of Klebsiella pneumoniae infections in the respiratory system, while the department of internal medicine had the highest incidence of Klebsiella pneumoniae infections in the urinary and hematological systems, and the department of surgery had the highest incidence of Klebsiella pneumoniae infections in other parts of the body. The resistance rate of Klebsiella pneumoniae to common antibiotics for the hematologic system was lower than that of the other three infection systems. For infections in the respiratory system, urinary system, and other body parts, the resistance rates of Klebsiella pneumoniae to amikacin, meropenem, imipenem, and piperacillin/tazobactam were all below 10%, while the resistance rate to tobramycin was below 20%, and the resistance rate to cephalosporins was around 30%. Conclusion:The proportion of Klebsiella pneumoniae infections in different body parts varies by gender, age, and department. For Klebsiella pneumoniae infections in the hematological system, the resistance rate to commonly used antibiotics is lower than that for infections in the other three systems. In contrast, Klebsiella pneumoniae infections in the respiratory system, urinary system, and other systems have a particularly high resistance rate to third- and fourth-generation cephalosporins but are still sensitive to piperacillin/tazobactam and carbapenem antibiotics.

Objective:To explore the feasibility and application value of an automated method for generation of surgical records for resection of benign soft tissue tumor based on dense video descriptions.Methods:The Transformer deep learning model was used to establish an automated surgical record generation system to analyze the surgical videos of 30 patients with benign soft tissue tumor who had been admitted to Department of Orthopedics, Xijing Hospital, Air Force Military Medical University from September 2021 to August 2023. The patient data were randomly divided into training sets, validation sets, and test sets in a ratio of 8∶1∶1. In the test sets, 7 evaluation indexes, BLEU-1, BLEU-2, BLEU-3, BLEU-4, Meteor, Rouge, and CIDEr, were used to evaluate the text quality of surgical records generated by the model. The text of surgical records was compared with the classical algorithm, dense video captioning with paralled decoding (PDVC) in the field of video-intensive description.Results:The automated surgical record generation system running in the test sets showed the following: BLEU-1, BLEU-2, BLEU-3, BLEU-4, Rouge, Meteor, and CIDEr were 16.80, 15.23, 13.01, 11.68, 16.01, 12.67 and 62.30, respectively. The operation of the classical algorithm PDVC showed the following: BLEU-1, BLEU-2, BLEU-3, BLEU-4, Rouge, Meteor, and CIDEr were 15.63, 14.17, 11.90, 10.45, 12.97, 11.99 and 53.64, respectively. The automated surgical record generation system resulted in significant improvements compared with PDVC in all evaluation indexes. The BLEU-4, Rouge, Meteor, and CIDEr were improved by 1.23, 3.04, 0.68 and 8.66, respectively, demonstrating that the system proposed can better capture the key data in the video to help generate more effective text records.Conclusion:As the automated surgical record generation system shows good performance in generating surgical records for resection of benign soft tissue tumor based on intensive video descriptions, it can be applied in clinical practice.

Objective To summarize the best evidence for perioperative exercise in renal transplant patients and provide evidence-based evidence for clinical staff to perform exercise in renal transplant patients.Methods Evidence-based questions were identified according to the PIPOST model,and computerized searches were conducted on BMJ Best Practice,UpToDate,the World Health Organization,the US National Guidelines,the website of the Chinese Society of Nephrology,the website of the British Renal Association,the website of the American Society of Nephrology,CNKI,the knowledge service platform of Wanfang Data,the Wipo database and other databases for all evidence on perioperative exercise in renal transplant recipients,including clinical guidelines,clinical decision-making,systematic evaluations,evidence summaries,and expert consensus,with a timeframe for searching from the establishment of the database to August 2023.Quality assessment and evidence extraction of the literature were performed independently by 2 nursing graduate students.Results A total of 13 publications were included,including 1 clinical decision,1 guideline,3 expert consensus,and 8 systematic evaluations.A total of 24 pieces of best evidence were summarized in 7 areas:exercise benefits,exercise assessment,preoperative exercise strategies,postoperative exercise strategies,precautions,exercise instruction monitoring,and exercise support.Conclusions This study summarizes the best evidence about perioperative exercise exercise in renal transplantation and provides a reference for standardizing perioperative exercise exercise in renal transplantation.Clinical staff should fully identify the impediments and facilitators of exercise exercise in renal transplant patients,and develop personalized exercise exercise programs based on medical scenarios,patient conditions,and combined with patients'exercise wishes.

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 explore the clinical features and genetic etiology of a child with Char syndrome.Methods:A child who was presented at the Department of Child Health, Henan Children′s Hospital in February 2022 was selected as the study subject. Clinical data of the child was collected, and peripheral blood samples of the child and her parents were collected for the extraction of genomic DNA. Whole exome sequencing was carried out, and candidate variants were verified by Sanger sequencing and bioinformatic analysis.Results:The child had mainly manifested facial dysmorphism, patent ductus arteriosus, growth retardation, curving of fifth fingers and middle toes. Whole exome sequencing revealed that she has harbored a heterozygous c. 944A>C (p.Glu315Ala) variant of the TFAP2B gene, which was verified to be de novo by Sanger sequencing. Based on the guidelines from the American College of Medical Genetics and Genomics (ACMG), the variant was rated to be likely pathogenic (PM1+ PM2_Supporting+ PM6+ PP3). Conclusion:The heterozygous c. 944A>C (p.Glu315Ala) variant of the TFAP2B gene probably underlay the Char syndrome in this child. Above finding has expanded the mutational and phenotypic spectra of the TFAP2B gene, which has facilitated early identification and diagnosis of Char syndrome.

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.