Objective:This study aimed to evaluate the value of CT-based radiomics machine learning models in predicting spread through air spaces(STAS)in lung adenocarcinoma(LUAD)and to determine the optimal peritumoral analysis region.Methods:Data from 378 pa-tients who underwent non-small cell lung cancer surgery at Zhejiang Cancer Hospital between January 2013 to January 2017 were retro-spectively analyzed.Logistic regression,random forest,and XGBoost models were constructed using regions extending 0,3,6,9,and 12 mm outward from the tumor margin.Results:The XGBoost model using the 6 mm peritumoral region performed best on the test set,with an AUC-ROC of 0.855(95%CI:0.756-0.950),followed by the XGBoost model using the 9 mm region.Decision curve analysis(DCA)indicated that the XGBoost models for the 6 mm and 9 mm regions had higher net clinical benefits.Feature analysis revealed that some wavelet trans-form features significantly contributed to STAS prediction.Conclusions:This preliminary study suggests that CT-based radiomics machine learning models have predictive value for STAS.The XGBoost model based on the 6 mm peritumoral region demonstrated the best perform-ance,and holds promise in assisting preoperative assessment.

Objective:This study aimed to evaluate the value of CT-based radiomics machine learning models in predicting spread through air spaces(STAS)in lung adenocarcinoma(LUAD)and to determine the optimal peritumoral analysis region.Methods:Data from 378 pa-tients who underwent non-small cell lung cancer surgery at Zhejiang Cancer Hospital between January 2013 to January 2017 were retro-spectively analyzed.Logistic regression,random forest,and XGBoost models were constructed using regions extending 0,3,6,9,and 12 mm outward from the tumor margin.Results:The XGBoost model using the 6 mm peritumoral region performed best on the test set,with an AUC-ROC of 0.855(95%CI:0.756-0.950),followed by the XGBoost model using the 9 mm region.Decision curve analysis(DCA)indicated that the XGBoost models for the 6 mm and 9 mm regions had higher net clinical benefits.Feature analysis revealed that some wavelet trans-form features significantly contributed to STAS prediction.Conclusions:This preliminary study suggests that CT-based radiomics machine learning models have predictive value for STAS.The XGBoost model based on the 6 mm peritumoral region demonstrated the best perform-ance,and holds promise in assisting preoperative assessment.

Chalcone is a common scaffold in natural products with optimal properties and biological activities.In this study, we designed and prepared eight new coumarin-chalcone derivatives (5a-5h), and confirmed their structures by 1H NMR and 13C NMR. Their in vitro antifungal activity combined with fluconazole (FLC) against drug-resistant Candida albicans was tested by microdilution method.The results indicated that most chalcone derivatives showed good antifungal activity against drug resistant Candida albicans with FLC, particularly with compound 5g displaying better antifungal activity (MIC50 = 5.60 μg/mL) than FLC (MIC50 = 200 μg/mL) when combined with FLC, so, these derivatives could be used as synergists of antifungal drugs.