Objective To explore the prediction efficiency of Ki-67 expression status in pituitary adenoma(PA)based on a joint model of siamese network and transfer learning.Methods The preoperative MR T1WI enhanced sequence images of 370 patients with PA diagnosed by surgery and pathology were retrospectively collected.According to the results of immunohistochemical,all patients were divided into high proliferation index group(Ki-67≥3,n=97)and low proliferation index group(Ki-67＜3,n=273),and all the sample data were randomly divided into training set and test set according to the ratio of 7∶3.Two single predictive models,ResNet-50 and VGGNet-16 and combined them with the siamese network and transfer learning were built.The prediction efficiency of different models were evaluated via accuracy rate,precision rate,recall rate,F1 score and receiver operating characteristic(ROC)curve as the main criteria.Results Compared with a single predictive model,the model combined with siamese network and transfer learning showed a better performance for predicting the Ki-67 of PA.Additionally,the ResNet-50 joint model exhibited the superior predictive performance.The accuracy rate was 0.872 7,the precision rate was 0.812 5,the recall rate was 0.764 7,the F1 score was 0.787 9,and the area under the curve(AUC)was 0.841 6.Conclusion The joint model based on siamese network and transfer learning exhibits a higher efficiency for predicting the Ki-67 expression status in PA,which can help the clinicians to formulate more personalized treatment for the patients.

Turning to critical illness is a common stage of various diseases and injuries before death. Patients usually have complex health conditions, while the treatment process involves a wide range of content, along with high requirements for doctor′s professionalism and multi-specialty teamwork, as well as a great demand for time-sensitive treatments. However, this is not matched with critical care professionals and the current state of medical care in China. Telemedicine, which shortens the distance of medical professionals and the gap of disease diagnosis and treatments in various regions through electronic information, can effectively solve the current problem. Therefore, there is an urgent need to develop a standardized, high-quality visualization telemedicine round system .Therefore, experts have been organized to search domestic and foreign literature on telemedicine round for critically ill patients and to form this consensus based on clinical experiences so as to further improve the level of critical care treatments in regions.

Turning to critical illness is a common stage of various diseases and injuries before death. Patients usually have complex health conditions, while the treatment process involves a wide range of content, along with high requirements for doctor′s professionalism and multi-specialty teamwork, as well as a great demand for time-sensitive treatments. However, this is not matched with critical care professionals and the current state of medical care in China. Telemedicine, which shortens the distance of medical professionals and the gap of disease diagnosis and treatments in various regions through electronic information, can effectively solve the current problem. Therefore, there is an urgent need to develop a standardized, high-quality visualization telemedicine round system .Therefore, experts have been organized to search domestic and foreign literature on telemedicine round for critically ill patients and to form this consensus based on clinical experiences so as to further improve the level of critical care treatments in regions.

Objective To explore the prediction efficiency of Ki-67 expression status in pituitary adenoma(PA)based on a joint model of siamese network and transfer learning.Methods The preoperative MR T1WI enhanced sequence images of 370 patients with PA diagnosed by surgery and pathology were retrospectively collected.According to the results of immunohistochemical,all patients were divided into high proliferation index group(Ki-67≥3,n=97)and low proliferation index group(Ki-67＜3,n=273),and all the sample data were randomly divided into training set and test set according to the ratio of 7∶3.Two single predictive models,ResNet-50 and VGGNet-16 and combined them with the siamese network and transfer learning were built.The prediction efficiency of different models were evaluated via accuracy rate,precision rate,recall rate,F1 score and receiver operating characteristic(ROC)curve as the main criteria.Results Compared with a single predictive model,the model combined with siamese network and transfer learning showed a better performance for predicting the Ki-67 of PA.Additionally,the ResNet-50 joint model exhibited the superior predictive performance.The accuracy rate was 0.872 7,the precision rate was 0.812 5,the recall rate was 0.764 7,the F1 score was 0.787 9,and the area under the curve(AUC)was 0.841 6.Conclusion The joint model based on siamese network and transfer learning exhibits a higher efficiency for predicting the Ki-67 expression status in PA,which can help the clinicians to formulate more personalized treatment for the patients.

Depression, as a complex affective mental disorder, brings a considerable burden to patients and society. At present, pharmacotherapy, psychotherapy, and traditional physical therapy methods cannot fully meet clinical needs. Therefore, seeking new treatment methods has become an urgent matter. In recent years, transcranial direct current stimulation, as a non-invasive neuromodulation technique, has attracted widespread attention and research in the field of depression treatment. This article briefly reviews the research progress of transcranial direct current stimulation in treating depression.

Depression, as a complex affective mental disorder, brings a considerable burden to patients and society. At present, pharmacotherapy, psychotherapy, and traditional physical therapy methods cannot fully meet clinical needs. Therefore, seeking new treatment methods has become an urgent matter. In recent years, transcranial direct current stimulation, as a non-invasive neuromodulation technique, has attracted widespread attention and research in the field of depression treatment. This article briefly reviews the research progress of transcranial direct current stimulation in treating depression.

Objective:To analyze the trend of late-diagnosis of HIV-infected men who have sex with men (MSM) before and after the AIDS Conquering Project in Guangxi Zhuang Autonomous Region (Guangxi) and its influencing factors, in order to find out the population groups that need priority intervention at the present stage.Methods:The HIV-infected MSM in Guangxi from 2005-2021 were selected from the National Integrated HIV/AIDS Control and Prevention Data System. The Joinpoint 4.9.1.0 software was used to test the time trend of late-diagnosis and non-late-diagnosis cases, and logistic regression was applied to analyze the factors influencing the proportion of late-diagnosis at each stage.Results:From 2005 to 2021, 5 764 HIV-infected MSM were reported in Guangxi from 2005 to 2021, with an overall late-diagnosis of 28.45% (1 640 cases). Under the 2015 baseline data as the boundary, the proportion of late-diagnosis cases showed a trend of sharp decline followed by stabilization from 2005 to 2015, average annual percent change= -6.90% ( P<0.001). The effect of factors such as resident population, occupation as a farmer or worker, and sample originating from medical consultation on late-diagnosis changed considerably before and after the implementation of the project, and the factors influencing late-diagnosis at this stage were age, resident population, occupation as a farmer, worker or student. The factors influencing late-diagnosis at this stage are age, resident population, and occupation as a farmer, worker and a student. Conclusions:The proportion of late diagnosis cases of HIV-infected MSM in Guangxi decreased significantly before and after the project. However, late-diagnosis should not be neglected and precise prevention and control should be carried out for the resident population, farmers, workers or students.

Objective To conduct a retrospective study on the clinical efficacy with endoscopic linea alba plication (ELAP) in the treatment of postpartum diastasis recti abdominis muscles. Methods Clinical data was collected to study the patients with postpartum diastasis recti abdominis muscles treated by ELAP in our hospital from January 2018 to December 2021. The operation was performed successfully in 48 cases. One case was lost follow-up and 47 cases were included in this study. Mean age was (34.9±4.2) years with body mass index (BMI) (20.1±2.0) kg/m2. The index of patients included general data, intraoperative data and postoperative recovery. Follow-up was done through out-patient examination and B-mode ultrasonography until to March 2022. Results The inter-rectus distance (IRD) in umbilical area (M3) shown by ultrasound examination was (41.6±8.2) mm. There were 10 cases combined with umbilical hernia and 2 cases with linea alba hernia. ELAP was performed under general anesthesia. All hernia rings were closed by suturing. The operative time was (130.9±36.0) min. Visual analog scale was (1.2±0.6) on the 1st postoperative day with postoperative hospital stay (1.5±0.9) d. Two cases had mild seroma postoperatively with puncture and absorption under B-ultrasound guiding. Remaining cases were without operative complications such as bleeding and infection of incision. Followed up of 47 cases was completed in the period of median 15(12, 26) months. One case had mild pain in the operative site and cured after non-operative treatment. Ultrasound examination in the other case showed 57.0 mm of IRD in M3 area preoperative and normal in the follow-up of 1 month postoperative. However, there was mild recurrence on 3 months of follow-up showing IRD 21.0 mm. Conclusions ELAP could be considered safe and effective in the treatment of postpartum diastasis recti abdominis muscle.

Objective:To explore the relationship between semi-quantitative parameters of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and long-term prognosis of locally advanced nasopharyngeal carcinoma, and to find prognostic indicators from non-invasive images of locally advanced nasopharyngeal carcinoma.Methods:Data were collected from January 2011 to January 2012 via a prospective clinical trial with locally advanced nasopharyngeal carcinoma. Clinical information was from 71 patients who completed the treatment plan with long-term follow-ups and UICC 2010 stage Ⅲ, Ⅳ A, Ⅳ B. The patients received three cycles of Taxotere-Platinol-Fluorouracil (TPF) regimen chrono-chemotherapy, followed by two cycles of concurrent paclitaxel chemotherapy with intensity-modulated radiotherapy (IMRT). DCE-MRI examination was performed before induction chemotherapy to obtain DCE-MRI related semi-quantitative parameters. Correlation analysis was conducted between DCE-MRI related semi-quantitative parameters and short-term efficacy of nasopharyngeal lesions after concurrent radiotherapy and chemotherapy. Results:Of all 77 patients, 71 completed treatment and were followed up from 9 to 86 months, with a median follow-up of 77 months, with 80.2% and 67.6% in 3- and 5-year OS, 73.2% and 60.5% in 3- and 5-year PFS, respectively. Evaluation of short-term efficacy of nasopharyngeal lesions after concurrent chemoradiotherapy: the difference in tissue arrival time of contrast agent between complete response (CR) group and partial response (PR) group was statistically significant ( t=0.537, P<0.05). Univariate survival analysis found that OS ( χ2=3.982, P<0.05) and PFS ( χ2=4.019, P<0.05) in the group with short contrast arrival time were significantly higher than those in the group with long contrast arrival time. OS ( χ2=7.593, P<0.05) and PFS ( χ2=5.624, P<0.05) of patients aged over 45 years were significantly lower than those aged less than 45 years. Cox multivariate regression model showed that advanced clinical stage (stage Ⅳ A, Ⅳ B) ( P=0.048) and age≥45 years ( P=0.031) were independent prognostic factors of OS in patients with nasopharyngeal carcinoma. Long arrival time of contrast agent ( P=0.018), age≥45 years ( P=0.004), advanced N(2-3) stage ( P=0.032) and enhancement peak<3 000 ( P=0.005) were independent prognostic factors of PFS in patients with nasopharyngeal carcinoma. Conclusions:The arrival time of the contrast agent in DCE-MRI may be a reliable prognostic factor for locally advanced nasopharyngeal carcinoma.

Objective:To understand the characteristics and associated factors of newly reported HIV/AIDS cases with non-marital or non-commercial heterosexual transmission, in Guangxi Zhuang Autonomous Region (Guangxi), 2015-2018.Methods:Information of newly reported HIV/AIDS cases aged ≥18 years in Guangxi between 2015 and 2018 was collected from the National Comprehensive HIV/AIDS Information System. Unconditional logistic regression model was used to access those factors that were associated with HIV infections through non-marital or non-commercial heterosexual contact.Results:Between 2015 and 2018, a total number of 35 497 HIV/AIDS cases, aged ≥18 years were newly reported in Guangxi. Among them, 32 648 (92.0 %) were infected heterosexually while 10 500 were infected through non-marital or non-commercial heterosexual behavior. Non-marital or non-commercial heterosexual transmission accounted for 29.6 % (10 500/35 497) of the newly reported HIV/AIDS cases, and 32.2 % (10 500/32 648) of those with heterosexual transmission. Males counted for 53.5 % (5 617/10 500) of non-marital or non-commercial heterosexual transmission and males to females ratio was 1.2∶1 (5 617∶4 883). Those married or had regular sexual partners counted for 55.9 % (5 873/10 500). Commercial heterosexual transmission appeared the main mode of HIV transmission for males (64.4 %,16 516/25 633) while main mode for females was non-marital or non-commercial heterosexual transmission and counted for 49.5 % (4 883/9 864). Results from the multivariate logistic regression analysis showed that adjusted OR of female HIV/AIDS infected HIV via non-marital or non-commercial heterosexual transmission, was 3.98 times (95 %CI: 3.78-4.20) hight than that of males. Among the group aged<50 years and the aged 50-59 years, the adjusted ORs were 1.35 times (95 %CI: 1.27-1.44) and 1.13 times (95 %CI: 1.05-1.21) hight than that of aged ≥60 years. Those who were single/divorced/widowed, the adjusted OR was 1.53 times (95 %CI: 1.45-1.61) hight than that of those married/regular partners. Those with junior high school education, high school education and above the adjusted ORs were 1.22 times (95 %CI: 1.16-1.29) and 1.18 times (95 %CI: 1.10-1.27), compared to those only with education levels of primary school or below. Conclusions:The number of HIV/AIDS cases via non-marital or non-commercial heterosexual transmission accounted for nearly 30.0 % of all the routes of HIV transmission in Guangxi, 2015-2018. Female, aged<60 years old, single/divorced/widowed and having had junior and above high school education etc., appeared as risk factors on non-marital or non-commercial heterosexual transmission, among newly reported HIV/AIDS in Guangxi.