Prediction of Pathological Subtypes of Lung Adenocarcinoma with Pure Ground Glass Nodules by Deep Learning Model / 中国医学科学院学报

To make a preliminary pathological classification of lung adenocarcinoma with pure ground glass nodules(pGGN)on CT by using a deep learning model. CT images and pathological data of 219 patients(240 lesions in total)with pGGN on CT and pathologically confirmed adenocarcinoma were collected.According to pathological subtypes,the lesions were divided into non-invasive lung adenocarcinoma group(which included atypical adenomatous hyperplasia and adenocarcinoma in situ and micro-invasive adenocarcinoma)and invasive lung adenocarcinoma group.First,the lesions were outlined and labeled by two young radiologists,and then the labeled data were randomly divided into two datasets:the training set(80%)and the test set(20%).The prediction Results of deep learning were compared with those of two experienced radiologists by using the test dataset. The deep learning model achieved high performance in predicting the pathological types(non-invasive and invasive)of pGGN lung adenocarcinoma.The accuracy rate in pGGN diagnosis was 0.8330(95% =0.7016-0.9157)for of deep learning model,0.5000(95% =0.3639-0.6361)for expert 1,0.5625(95% =0.4227-0.6931)for expert 2,and 0.5417(95% =0.4029-0.6743)for both two experts.Thus,the accuracy of the deep learning model was significantly higher than those of the experienced radiologists(=0.002).The intra-observer agreements were good(Kappa values:0.939 and 0.799,respectively).The inter-observer agreement was general(Kappa value:0.667)(=0.000). The deep learning model showed better performance in predicting the pathological types of pGGN lung adenocarcinoma compared with experienced radiologists.

Overview of Experimental Methods for Antimicrobial Activity of Natural Drugs / 中国实验方剂学杂志

The antibiotics have obvious antibacterial and anti-inflammatory effects, but their toxic side effect, secondary infection and bacterial resistance have become a global problem. Traditional Chinese medicine(TCM) has always been the treasure of traditional culture and national characteristics in China since ancient times. It also has remarkable effect on inhibiting the growth of bacteria and killing pathogenic bacteria. The research on bacteriostatic experiment of TCM has gradually become a hot topic. Sensitivity experiments for such natural medicines have gradually become a research hotspot, but the complexity and particularity of natural medicines will vary with different methods. Therefore, different methods of drug sensitivity experiments should be matched with different natural drugs. By collecting and sorting out the relevant literature at home and abroad, this paper systematically summarizes the commonly used in vitro, in vivo and their combination bacteriostasis experimental methods of natural medicine activity, analyses the advantages and disadvantages of each method in the process of application, finds that different kinds of natural drugs have different applicable methods, and puts forward suggestions for the operation of each experimental method, in order to provide ideas for the selection of antibacterial susceptibility research experiments of natural medicines. It also provides a reliable reference method for solving the problem of antibiotic abuse and the development and utilization of natural medicines.