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.

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.

This article reports a case of prenatal diagnosis of fetal Costello syndrome. At 11 weeks of gestation, the fetal nuchal translucency thickness was 2.5 mm. At 26 +1 weeks of gestation, ultrasound indicated that the fetal abdominal circumference was significantly enlarged, suggesting fetal overgrowth. Subsequent regular ultrasound follow-ups revealed polyhydramnios, enlarged fetal kidneys, and macroglossia after 30 +5 weeks of gestation. Whole-exome sequencing of the family detected a c.34G>A(p.Gly12Ser) mutation in the fetal HRAS gene, which was pathogenic and not present in either parent. Based on clinical manifestations, the fetus was diagnosed with Costello syndrome. After genetic counseling, the pregnant woman opted for termination of the pregnancy.

Objective:To analyze the clinical characteristics of anti-cyclic citrullinated peptide (CCP) antibody-negative rheumatoid arthritis (RA) patients.Methods:To retrospectively analyze the medical records of RA patients hospitalized in the department of rheumatology and immunity of Peking University Third Hospital from January 2013 to December 2018, we collected the baseline characteristics, joint manifestations, extra-articular manifestations, and laboratory parameters of RA patients, and compared the differences between anti-CCP antibody-negative patients and anti-CCP antibody-positive patients by U test and chi-square test. Results:A total of 486 RA patients were included in this study, including 153 anti-CCP antibody-negative patients (31.5%) and 333 anti-CCP antibody-positive patients (68.5%). Compared with anti-CCP antibody-positive group, anti-CCP antibody-negative group had shorter disease course ( U=-4.750, P<0.01) and the pro-portion of morning stiffness, shoulder or elbow joint involvement, and hand arthritis ( P<0.05) was lower, while the incidence of phlebothrombosis of leg ( χ2=4.100, P=0.043) was higher, as well as thrombocytosis ( U=-2.179, P=0.029) and elevation of CRP ( U=-2.154, P=0.03). Subgroup analysis based on RF showed that CCP RF + group had higher percentage of women ( P=0.042) and higher incidence of interstitial lung disease ( χ2=5.652, P=0.017) and secondary Sj?gren's syndrome ( χ2=11.211, P=0.001), compared with CCP RF - group. Conclusion:anti-CCP antibody-negative-patients have similar clinical char-acteristics with anti-CCP antibody-positive group, but the involvement of shoulder or elbow joint and hand arthritis are less common in anti-CCP antibody-negative group. Meanwhile the incidence of phlebothrombosis of leg is higher, and the level of platelet(PLT) and C-reactive protein (CRP) is higher, suggesting that anti-CCP antibody-negative RA may have more vident inflammatory response.

Objective: To analyze the epidemiological history, clinical manifestations, treatment and the short-term prognosis of 31 cases of 2019 novel coronavirus(2019-nCoV) infection in children from six provinces (autonomous region) in northern China. Methods: A retrospective analysis of the epidemiological history, clinical symptoms, signs, laboratory examinations, chest imaging, treatment and the short-term prognosis of 31 cases of 2019-nCoV was conducted. The patients were diagnosed between January 25th, 2020 and February 21st, 2020 in 21 hospitals in 17 cities of six provinces(autonomous region) of Shaanxi, Gansu, Ningxia, Hebei, Henan and Shandong. Results: The age of the 31 children with 2019-nCoV infection was 7 years and 1 month (6 months -17 years). Nine cases (29%) were imported cases. Other 21 cases (68%) had contact with confirmed infected adults. One case (3%) had contact with asymptomatic returnees from Wuhan. Among the 31 children, 28 patients (90%) were family cluster cases. The clinical types were asymptomatic type in 4 cases (13%), mild type in 13 cases (42%), and common type in 14 cases (45%). No severe or critical type existed. The most common symptom was fever (n=20, 65%), including 1 case of high fever, 9 cases of moderate fever, 10 cases of low fever. Fever lasted from 1 day to 9 days. The fever of fifteen cases lasted for ≤3 d, while in other 5 cases lasted > 3 d. Other symptoms included cough (n=14, 45%), fatigue (n=3, 10%) and diarrhea (n=3, 9%). Pharyngalgia, runny nose, dizziness, headache and vomiting were rare. In the early stage, the total leukocytes count in peripheral blood decreased in 2 cases (6%), the lymphocytes count decreased in 2 cases (6%), and the platelet count increased in 2 cases (6%).Elevation of C-reactive protein (10%, 3/30), erythrocyte sedimentation rate(19%,4/21), procalcitonin(4%,1/28), liver enzyme(22%, 6/27) and muscle enzyme (15%, 4/27) occurred in different proportions. Renal function and blood glucose were normal. There were abnormal chest CT changes in 14 cases, including 9 cases with patchy ground glass opacities and nodules, mostly located in the lower lobe of both lungs near the pleural area. After receiving supportive treatment, the viral nucleic acid turned negative in 25 cases within 7-23 days. Among them, 24 children (77%) recovered and were discharged from hospital. No death occurred. Conclusions In this case series, 2019-nCoV infections in children from six provinces (autonomous region) in northern China are mainly caused by close family contact. Clinical types are asymptomatic, mild and common types. Clinical manifestations and laboratory examination results are nonspecific. Close contact history of epidemiology, nucleic acid detection and chest imaging are important bases for diagnosis. After general treatment, the short-term prognosis is good.

Objective To investigate the relationship between prognostic nutritional index (PNI) and neutropenia after adjuvant chemotherapy in patients with colorectal cancer. Methods The clinical data of 44 patients with colorectal cancer performed adjuvant chemotherapy in Shunyi District Hospital from December 2014 to January 2018 were retrospectively analyzed, and the patients were divided into group A (grade 0-2 neutropenia) and group B (grade3-4 neutropenia) according to the degree of neutropenia. The serum albumin, peripheral lymphocyte counts, and neutrophil counts within 1 week before chemotherapy were collected, and the PNI was calculated. The chi-square test and rank sum test were used to compare the clinical data, body mass index (BMI), baseline neutrophil count, and PNI between the two groups. Logistic regression analysis was used to analyze the risk factors for neutropenia after chemotherapy. Results The baseline median neutrophil counts and median PNI in group A were 3.17×109/L [(1.38-7.79)×109/L] and 50.40 (37.40-57.05), and in group B were 2.54 ×109/L [(1.22-3.87) ×109/L] and 45.50 (37.95-50.95). The baseline neutrophil counts and PNI in group A were significantly higher than those in group B, the differences between the two groups were statistically significant (Z= -2.085, P= 0.037; Z= -2.615, P= 0.009). Logistic regression analysis showed that PNI was an independent risk factor for neutropenia after chemotherapy (HR=0.803, 95％CI 0.646-0.998, P= 0.048). Conclusion PNI has a certain role in predicting neutropenia after adjuvant chemotherapy in patients with colorectal cancer.

Critical ultrasonography(CUS) is different from the traditional diagnostic ultrasound,the examiner and interpreter of the image are critical care medicine physicians.The core content of CUS is to evaluate the pathophysiological changes of organs and systems and etiology changes.With the idea of critical care medicine as the soul,it can integrate the above information and clinical information,bedside real-time diagnosis and titration treatment,and evaluate the therapeutic effect so as to improve the outcome.CUS is a traditional technique which is applied as a new application method.The consensus of experts on critical ultrasonography in China released in 2016 put forward consensus suggestions on the concept,implementation and application of CUS.It should be further emphasized that the accurate and objective assessment and implementation of CUS requires the standardization of ultrasound image acquisition and the need to establish a CUS procedure.At the same time,the standardized training for CUS accepted by critical care medicine physicians requires the application of technical specifications,and the establishment of technical specifications is the basis for the quality control and continuous improvement of CUS.Chinese Critical Ultrasound Study Group and Critical Hemodynamic Therapy Collabration Group,based on the rich experience of clinical practice in critical care and research,combined with the essence of CUS,to learn the traditional ultrasonic essence,established the clinical application technical specifications of CUS,including in five parts:basic view and relevant indicators to obtain in CUS;basic norms for viscera organ assessment and special assessment;standardized processes and systematic inspection programs;examples of CUS applications;CUS training and the application of qualification certification.The establishment of applied technology standard is helpful for standardized training and clinical correct implementation.It is helpful for clinical evaluation and correct guidance treatment,and is also helpful for quality control and continuous improvement of CUS application.

Objective To investigate the effects of HLA-B27 in disease activity and the clinical features of axial spondyloarthritis(SpA). Methods Clinical data of 112 patients with axial SpA was collected and studied prospectively. Clinical manifestations and laboratory examination results of 82 HLA-B27 positive and 30 HLA-B27 negative patients with axial SpA were analyzed. Data source was from Chinese Rheumatism Data Center. Results (1)The average age of onset of HLA-B27 negative patients was significantly later than that of the positive patients , and there was no significant difference in the course of disease and the proportion of male and female patients. (2)The ratio of severe lesion of hip ,peripheral arthritis ,attachment inflammation and systemic symptoms of HLA-B27 negative group were significantly lower than those of HLA-B27 positive group. Familial aggregation phenomenon,uveitis and spine radiology changes in two groups had no significant difference.(3)The changes of disease activity index including erythrocyte sedimentation rate and C-reactive protein increased in HLA-B 27 negative group was significantly lower than those in HLA-B27 positive group. Conclusion There is strong correlation between axial SpA and HLA-B27. The average age of onset of HLA-B27 negative patients was significantly later than that of the positive patients. HLA-B27 negative patients manifested severe symptoms and worse prognosis.

Objective Discussing the role of Yunnan baiyao in the newborn umbilical cord.Methods 120 cases newborns were selected and randomly divided into the control group of 60cases and the observation group of 60 cases according to birth order.The two kinds of newborns were both used single valve care,and were disinfected with 75%alcohol twice a day,Newborns of the observation group were dipped in Yunnan baiyao cream which was taken 75%alcohol to apply the root of umbilical and around after each nursing time.Observed the umbilical cord healing of two groups of newborns and take notes.Results In the observation group newborns,umbilical cord on the drying time [(3.1 ±1.1)d]and off time[(6.6 ±1.8)d]were better than the control group[(3.1 ±1.1)d,(8.0 ±3.2)d](t =7.8,2.95,all P <0.05);6 cases occurred redness and swelling around the belly button,2 cases occurred hemor-rhage,17 cases occurred secretions.which were better than that in control group(18 cases,6 cases,35 cases).The statistical analysis showed significant difference in the data of the two groups.Conclusion Yunnan baiyao can promote healing of umbilical cord,it should be popularize in clinical use.

OBJECTIVE To find the infla mmation bio markers induced by coke oven e missions (COE),we investigated the changes of T helper 17 (Th17 )cytokines in hu man bronchial epithelial (16HBE)cells.METHODS 16HBE cells were exposed to organic extracts of COE collected fro m co-king plant at the concentrations of 5,10 and 20 mg·L -1 for 24 h or 5 d to establish short-term and long-term cell models,respectively.Cell viability was measured by MTT assay and infla mmatory da mage was assessed by lactate dehydrogenase assay (LDH).The cytokines in culture supernatant sa mples was detected by co mmercial hu man Th17 cytokine panel kit.RESULTS COE Can induce infla mmation in COE 20 mg·L -1 group and no expression on IL-17 F and IL-1 β.The concentration of IL-10 was 1 .25 ± 0.54,1 .39 ±0.13 and (1 .90 ±0.73)pg·mL -1 in COE 5,10 and 20 mg·L -1 group showing good con-centration-effect relationship (r=0.98,P <0.05 ).IL-23 expression was found only higher at 10 and 20 mg·L -1 and the concentrations were 3.38 ±3.90 and (1 .74 ±2.00 )pg·mL -1 ,respectively.In 16HBE cells treated by COE for 5 d,elevated expression of IL-17A was found in COE 5 and 10 mg·L -1 group,and there was statistically sigificant difference between COE 10 mg·L -1 and DMSO group (P<0.05).Elevated concentration of IL-17F of 10.2 ±1 1 .78 and (6.79 ±7.84)pg·mL -1 was found in COE 5 and 10 mg·L -1 group.The concentration of IL-10 was 1 .71 ±0.02,1 .49 ±0.25 and (2.82 ± 0.33)pg·mL -1 in COE 5,10 and 20 mg·L -1 group,respectively.We found increased IL-1 βexpression with concentration of 2.72 ±0.62,2.25 ±0.33 and (0.93 ±0.21 )pg·mL -1 in COE 5,10 and 20 mg·L -1 group with negative dose-response relationship.We also found more elevated TNF-αlevels in the 5 d than in the 24 h model with no COE specific relationship.CONCLUSION COE induces expression changes of Th17 cytokines profile in 16HBE cells,including IL-23 and IL-1 βfor early and long-term infla mmation,respectively.IL-10 may be a candidate marker for population study on COE induced infla mmatory injury.