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.

Emerging and re-emerging RNA viruses occasionally cause epidemics and pandemics worldwide, such as the on-going outbreak of the novel coronavirus SARS-CoV-2. Herein, we identified two potent inhibitors of human DHODH, S312 and S416, with favorable drug-likeness and pharmacokinetic profiles, which all showed broad-spectrum antiviral effects against various RNA viruses, including influenza A virus, Zika virus, Ebola virus, and particularly against SARS-CoV-2. Notably, S416 is reported to be the most potent inhibitor so far with an EC of 17 nmol/L and an SI value of 10,505.88 in infected cells. Our results are the first to validate that DHODH is an attractive host target through high antiviral efficacy in vivo and low virus replication in DHODH knock-out cells. This work demonstrates that both S312/S416 and old drugs (Leflunomide/Teriflunomide) with dual actions of antiviral and immuno-regulation may have clinical potentials to cure SARS-CoV-2 or other RNA viruses circulating worldwide, no matter such viruses are mutated or not.
Animals ; Antiviral Agents ; pharmacology ; therapeutic use ; Betacoronavirus ; drug effects ; physiology ; Binding Sites ; drug effects ; Cell Line ; Coronavirus Infections ; drug therapy ; virology ; Crotonates ; pharmacology ; Cytokine Release Syndrome ; drug therapy ; Drug Evaluation, Preclinical ; Gene Knockout Techniques ; Humans ; Influenza A virus ; drug effects ; Leflunomide ; pharmacology ; Mice ; Mice, Inbred BALB C ; Orthomyxoviridae Infections ; drug therapy ; Oseltamivir ; therapeutic use ; Oxidoreductases ; antagonists & inhibitors ; metabolism ; Pandemics ; Pneumonia, Viral ; drug therapy ; virology ; Protein Binding ; drug effects ; Pyrimidines ; biosynthesis ; RNA Viruses ; drug effects ; physiology ; Structure-Activity Relationship ; Toluidines ; pharmacology ; Ubiquinone ; metabolism ; Virus Replication ; drug effects

Objective To evaluate the value of interstitial magnetic resonance lymphography (MRL) to identify the sentinel lymph node (SLN) of breast cancer.Methods Totally 58 patients with invasive breast cancer were consecutive collected.15 mL of Gd-DTPA and 2 mL of mepivacain hydrochloride 2% were mixed and 0.5 mL of them was injected into the outside of the subareolar breast tissue.MRI was performed with Siemens 3.0 T Magnetom Trio MRI instrument using volumetric interpolated breath-hold examination sequence.Axillary lymph flow was tracked on maximum intensity projection (MIP) and sentinel lymph nodes were identified by interstitial MRL as M-SLN.All M-SLN were marked by a method of surface capsule localization.During surgery, methylene blue was used as tracer and SLNs stained by it were detected and excised by following the blue lymphatic vessels,these were designated as D-SLN.The numbers of SLNs detected by interstitial MRL and stained by methylene blue during operation were compared by paired samples rank-sum test and the correlation was analyzed by Spearman rank correlation test.Assessing the sensitivity, specificity and accuracy of interstitial MRL for diagnosing M-SLN.Results A total of 75 M-SLNs (average 1.60 ± 0.52) were identified by interstitial MRL.During operation, all M-SLNs were easily resected under the guidance of skin marker.91 D-SLNs (average 1.94±0.63) were stained by methylene blue, which was significant more than those of the M-SLNs.There was a strong correlation (Spearman's rank correlation coefficient 0.69,P<0.001) between the SLNs identified by these two methods.Interstitial MRL in diagnosing D-SLN metastasis of breast cancer had a sensitivity of 95.8%,specificity of 88.9%,and accuracy of 93.3%.Conclusion Interstitial MRL can accurately identify the axillary sentinel lymph node and guide the biopsy.It may have great clinical value in the future.