Combining machine and deep transfer learning for mediastinal lymph node evaluation in patients with lung cancer

Background The prognosis and survival of patients with lung cancer are likely to deteriorate with metastasis.Using deep-learning in the detection of lymph node metastasis can facilitate the noninvasive calculation of the likelihood of such metastasis,thereby providing clinicians with crucial information to enhance diagnostic precision and ultimately improve patient survival and prognosis.Methods In total,623 eligible patients were recruited from two medical institutions.Seven deep learning models,namely Alex,GoogLeNet,Resnet18,Resnet101,Vgg16,Vgg19,and MobileNetv3(small),were utilized to extract deep image histological features.The dimensionality of the extracted features was then reduced using the Spearman correlation coefficient(r≥0.9)and Least Absolute Shrinkage and Selection Operator.Eleven machine learning methods,namely Support Vector Machine,K-nearest neighbor,Random Forest,Extra Trees,XGBoost,LightGBM,Naive Bayes,AdaBoost,Gradient Boosting Decision Tree,Linear Regression,and Multilayer Perceptron,were employed to construct classification prediction models for the filtered final features.The diagnostic performances of the models were assessed using various metrics,including accuracy,area under the receiver operating characteristic curve,sensitivity,specificity,positive predictive value,and negative predictive value.Calibration and decision-curve analyses were also performed.Results The present study demonstrated that using deep radiomic features extracted from Vgg16,in conjunction with a prediction model constructed via a linear regression algorithm,effectively distinguished the status of mediastinal lymph nodes in patients with lung cancer.The performance of the model was evaluated based on various metrics,including accuracy,area under the receiver operating characteristic curve,sensitivity,specificity,positive predictive value,and negative predictive value,which yielded values of 0.808,0.834,0.851,0.745,0.829,and 0.776,respectively.The validation set of the model was assessed using clinical decision curves,calibration curves,and confusion matrices,which collectively demonstrated the model's stability and accuracy.Conclusion In this study,information on the deep radiomics of Vgg16 was obtained from computed tomography images,and the linear regression method was able to accurately diagnose mediastinal lymph node metastases in patients with lung cancer.

Action modes of Aloe vera L. extracts against <i>Tetranychus cinnabarinus</i>Boisduval (Acarina: Tetranychidae)

Objective: This paper mainly determined the action modes of extract of Aloe vera L. against Tetranychus cinnabarinus Boisduval. Methods: The different action modes, contact action, repellent, fumigant, and oviposition inhibition property of the acetone extract of Aloe vera L. leaf against the carmine spider mite Tetranychus cinnabaribus (Boisduval) (Acarina: Tetranychidae) were investigated at 26°C ± 1°C, 75% - 80% relative humidity, and 14:10 light: day cycle in the laboratory. Results: Based on the established toxicity regression line of the Aloe vera L. acetone extract against female adult mites, the median lethal concentrations (LC50) were 0.836 and 0.167 mg/mL for 48 and 72 h, respectively. With processing time increased, the contact acaricidal activity increased and the repellent activity gradually decreased. The main modes of action of the extract against female adult mites were contact and repellent, and preferable effects were observed on adult mites. These results indicate that A. vera L. extract contains acaricidal and repellent bioactive components that may be useful in future control of the phytophagous mites.

Fabrication and Properties of SiC Nanofiber Paper/Nonwoven Fabric

SiC nanofibers were synthesized by the sol-gel and carbothermal reduction method.The morphologies,microstructure and composition of the product were characterized by XRD,FESEM,and TEM.The product was ultralong β-SiC nanofibers with diame-

Industrial Pollution Governance in Beijing-Tianjin-Hebei Based on Industrial Relocation

Industrial relocation and ecological subsidy are viewed as effective ways to overcome transboundary industrial pollution. In this paper, we study the transboundary industrial pollution control problem in the Beijing-Tianjin-Hebei region in the context of industrial relocation. Firstly, we construct an economic model of pollution control with relevant variables such as environmental tax and environmental damage coefficient. Secondly, we solve the economic contributions by using the proportional split-off solution. Finally, we compare the optimal relocation quantity and welfare functions in both cooperative and non-cooperative cases. Our research finds that: 1) The optimal strategy is closely related to utility coefficient, environmental loss coefficient and incentive intensity coefficient.2) The welfare function and the optimal relocation quantity in the cooperative case are significantly greater than those in the non-cooperative case. Based on the analysis, some suggestions are provided for transboundary industrial pollution management.