The Value Of CT Soft Tissue Window Radiomics In Assessing The Efficacy Of Pulmonary Adenocarcinoma Chemotherapy

Background Lung cancer is the leading cause of death in the world of cancer.Primary lung cancer mostly occurs in middle-aged men.Most patients are already in the middle and advanced stage when diagnosed,and about 60% of patients are inoperable.Chemotherapy is the main choice for patients with advanced stage.CT examination has become an important means to evaluate the curative effect and prognosis of chemotherapy for lung cancer.However,the efficacy of tumor chemotherapy cannot be accurately reflected in a timely manner.Therefore,the applied research of image omics has attracted more and more people's attention.Objective Radiomics is a new research field in medical science,its generation is inseparable with the good performance of radio-genomics in disease study and the great potential of medical imaging in the disease diagnosis and treatment,Radiomics is the extraction of a large number of multidimensional data from images and quantitative analysis of them to evaluate the heterogeneity of tumors,thus providing important information for the judgment and evaluation of tumor efficacy.In this paper,a series of imaging data were obtained based on soft window CT images before treatment to establish a predictive model to evaluate the efficacy of chemotherapy for lung cancer patients.Help to choose and adjust the treatment plan in the later period.Methods Images and case materials of 105 patients pathologically diagnosed with pulmonary adenocarcinoma were retrospectively collected in our hospital from December 2015 to December 2018.After half-year chemotherapy,the patients were assigned to the response group(35 cases)and non-response group(70 cases)according to RECIST where the non-response group was further divided into the stable group(35 cases)and progression group(35 cases).For all patients,their CT soft tissue images before chemotherapy were obtained,The lesions were manually segmented using ITK-SNAP software,and then focal features of those CT soft tissue images by AK analysis software of GE company were extracted using radiomics methods and then subjected to LASSO dimensionality reduction and modeling.The model for comparison between the response group and the non-response group was calculated using The Receiver Operating Characteristic Curve(ROC)and image omics model to assess the diagnostic capability of chemotherapy response.Results For images based on the response group and the non-response group,12 significant texture features were extracted,including 5 co-occurrence matrices(GLCM)and 7 run-length matrices(RLM),the training group's AUC,diagnosis sensitivity and specificity were 0.80,0.68 and 0.80;Validation group's AUC,diagnosis sensitivity and specificity were 0.74,0.70 and 0.81,The AUC values of both groups are between 0.7~0.9,which also achieved good diagnostic value.Decision curve of image omics model have a good clinical practicability in a larger threshold range of 0.18-0.76.Conclusion Radiomics based on the CT images before chemotherapy may help exactly assess the efficacy of pulmonary adenocarcinoma chemotherapy before treatment,It is expected to provide some guidance for improving the prognosis of patients.