Objective To observe the value of machine learning model based on MR T2WI and diffusion weighted imaging(DWI)radiomics for predicting perineural invasion(PNI)of rectal cancer.Methods Totally 343 patients with rectal cancer were retrospectively collected and divided into training set(n=275,92 PNI[+]and 183 PNI[-])and test set(n=68,23 PNI[+]and 45 PNI[-])at the ratio of 8∶2.Univariate and multivariate logistic regression(LR)were used to analyze clinical data and screen the independent predictors of PNI in rectal cancer,so as to construct a clinical model.The best radiomics features were extracted and screened based on preoperative T2WI and DWI.Then extremely randomized trees,multilayer perceptron,light gradient boosting machine,extreme gradient boosting,support vector machine(SVM),LR,K-nearest neighbor and random forest algorithms were used to construct ML models,respectively,and the optimal ML model was selected to establish a clinical-radiomics ML model combined with clinical relevant independent predictors.The predictive efficacy and clinical value of each model were evaluated.Results Patients' age was the independent predictor of PNI of rectal cancer(OR=0.988,P＜0.001),and the area under the curve(AUC)of the clinical model constructed based on it was 0.435 and 0.458 in training and test sets,respectively.SVM model was the best one among 8 ML models,with AUC in training and test set of 0.887 and 0.854,respectively.The AUC of clinical-radiomics ML model in training and test sets was 0.887 and 0.860,respectively,not different with AUC of SVM model(both P＞0.05).Decision curve analysis showed that when the threshold value was 0.20-0.45,clinical net benefit of SVM model was higher than that of other models.Conclusion SVM model based on T2WI and DWI radiomics could effectively predict PNI of rectal cancer.

Objective To observe the value of machine learning model based on MR T2WI and diffusion weighted imaging(DWI)radiomics for predicting perineural invasion(PNI)of rectal cancer.Methods Totally 343 patients with rectal cancer were retrospectively collected and divided into training set(n=275,92 PNI[+]and 183 PNI[-])and test set(n=68,23 PNI[+]and 45 PNI[-])at the ratio of 8∶2.Univariate and multivariate logistic regression(LR)were used to analyze clinical data and screen the independent predictors of PNI in rectal cancer,so as to construct a clinical model.The best radiomics features were extracted and screened based on preoperative T2WI and DWI.Then extremely randomized trees,multilayer perceptron,light gradient boosting machine,extreme gradient boosting,support vector machine(SVM),LR,K-nearest neighbor and random forest algorithms were used to construct ML models,respectively,and the optimal ML model was selected to establish a clinical-radiomics ML model combined with clinical relevant independent predictors.The predictive efficacy and clinical value of each model were evaluated.Results Patients' age was the independent predictor of PNI of rectal cancer(OR=0.988,P＜0.001),and the area under the curve(AUC)of the clinical model constructed based on it was 0.435 and 0.458 in training and test sets,respectively.SVM model was the best one among 8 ML models,with AUC in training and test set of 0.887 and 0.854,respectively.The AUC of clinical-radiomics ML model in training and test sets was 0.887 and 0.860,respectively,not different with AUC of SVM model(both P＞0.05).Decision curve analysis showed that when the threshold value was 0.20-0.45,clinical net benefit of SVM model was higher than that of other models.Conclusion SVM model based on T2WI and DWI radiomics could effectively predict PNI of rectal cancer.

Chronic prostatitis is a common and frequently occurring disease in male clinics. Due to the diverse symptoms， complex etiology， unclear mechanisms， and recurrent episodes of chronic prostatitis， Western medicine often faces the challenge of limited treatment options and unsatisfactory outcomes. In order to fully leverage the unique advantages of traditional Chinese medicine （TCM） in the treatment of chronic prostatitis， the China Association of Chinese Medicine organized a discussion among experts from the fields of TCM urology， Western urology， and related pharmacy. The experts focused on the advancements in the understanding of chronic prostatitis in modern medicine， various theories on the etiology， pathogenesis， and treatment of chronic prostatitis in TCM， entry points from interdisciplinary fields， the role and advantages of TCM in the comprehensive management of chronic prostatitis， and research into mechanisms related to chronic prostatitis. After discussions， the experts concluded that chronic prostatitis is one of the diseases where TCM has a distinct advantage. TCM can effectively improve the clinical syndromes of chronic prostatitis， including urinary issues， social psychology， organ specificity， infection， nervous system problems， pain and discomfort， sexual dysfunction， etc.， and can enhance the quality of life. For patients with chronic prostatitis who cannot tolerate or may not accept the adverse effects of Western medicine， as well as for those with non-inflammatory chronic prostatitis/chronic pelvic pain syndrome （CP/CPPS）， those with pain as the primary symptom， those with urinary tract symptoms， those with coexisting anxiety and depression， and those with abnormal semen liquefaction， TCM-based treatment can be the main approach. Currently， the optimal diagnosis and treatment strategy for chronic prostatitis has not yet been established， and further research from perspectives such as clinical epidemiology， evidence-based medicine， and molecular biology is needed. Both TCM and Western medicine should integrate their respective strengths， clarify the role and advantages of TCM interventions based on mutual reference， and improve the diagnosis and treatment standards for chronic prostatitis in China.

Objective To evaluate the visual improvement of therapeutic plasma exchange (TPE) for refractory optic neuritis (ON) patients in acute phase.Methods Seventy-five affected eyes from 44 refractory ON patients with severe visual defect or resistance to high-dose intravenous methylprednisolone (IVMP) therapy,who were admitted to The Chinese PLA General Hospital between January 2015 and August 2016,were recruited and received TPE therapy.Among these patients,11 were male and 33 were female;the average age was 39.1 ± 13.9;31 patients had two affected eyes,13 patients had one affected eye.The course of the disease on the group of patients were more than 2 weeks,and the visual acuity worsened for more than 10 days and continued to deteriorate.TPE treatment was performed on all of the patients.BCVA was recorded before and 24 h after treatment,and the visual function was scored using visual outcome scale (VOS).At the same time,the adverse reactions of TPE treatment were observed.The paired t-test was used to compare the VOS before and after treatment.The correlation between VOS before and after treatment was analyzed by Linear-by-Linear correlation analysis.Results Among 75 affected eyes,the post-therapy VOS 3.89 ±2.13 was significantly improved from pre-therapy VOS 5.56± 1.69 (t=6.77,P＜0.001).Forty-eight of 75 eyes were improved at lease 1 score of VOS,the overall rate of visual improvement was 64.0％.Especially among the eyes with initial vision of light perception,an improved rate of 82.4％ was presented.75.0％ in those eyes with initial vision of count fingers and 67.7％ in no light perception.Linear-by-Linear correlation analysis showed a significant linear correlation between the scores of VOS before and after TPE treatment (r=0.398,P=0.01).During the course of TPE treatment,5 patients had mild adverse reactions such as low calcium reaction and allergic reaction and were well controlled after treatment.Conclusion Using TPE to treat refractory ON in acute phased can improve the visual function of patients.

BACKGROUND:It is important to prepare a mal eable putty to repair irregular bone defects because the preformed bone substitute material cannot suit to bone defects.
OBJECTIVE:To prepare mal eable demineralized bone matrix/hyaluronic acid putty and to screen out the optimal composite ratio, as wel as to evaluate its cellcompatibility.
METHODS:Demineralized bone matrix was prepared from the cortical bone of healthy donors. The hyaluronic acid was dissolved at concentrations of 0.75%, 1.5%, 3%, 4.5%, and the viscosity of them was measured. Then 450 mg demineralized bone matrix was compounded with 1 mL hyaluronic acid solution to prepare the demineralized bone matrix/hyaluronic acid putty, and the optimal ratio of demineralized bone matrix/hyaluronic acid was screened by the disintegrated time of the putty at 37 ℃. L-929 mouse fibroblasts were cultured in the leaching liquor of demineralized bone matrix/hyaluronic acid, and the cytotoxicity was tested by cellcount kit-8 assay at days 1, 4 and 7.
RESULTS AND CONCLUSION:With the increase of hyaluronic acid concentration, the viscosity of hyaluronic acid solution was increased;the demineralized bone matrix/hyaluronic acid putty was strengthened and the disintegrated time was prolonged gradual y. When the ratio of demineralized bone matrix/hyaluronic acid was 15/1, demineralized bone matrix/hyaluronic acid was molded easily, and the disintegrated time was 8 hours in 7 ℃ PBS. The results of cytotoxicity showed that cellproliferation rates were 93.72%, 101.65%and 97.68%at days 1, 4 and 7 respectively, while the cytotoxicity was in grade 0 or 1. These findings indicate that demineralized bone matrix/hyaluronic acid putty at a compound ratio of 15:1 can be molded easily and difficult to disintegrate, with low cytotoxicity.