Font Size: a A A

CT-based Radiomics Analysis For Evaluating The Differentiation Degree Of Esophageal Squamous Carcinoma

Posted on:2020-03-29Degree:MasterType:Thesis
Country:ChinaCandidate:L S ChengFull Text:PDF
GTID:2404330590460805Subject:Clinical medicine
Abstract/Summary:PDF Full Text Request
Purpose: To create a CT-based radiomics predictive mode aimed to evaluate the Differentiation Degree of the Esophageal Squamous Carcinoma.Materials and Methods: 160 patients from January 2008 to August 2016 in Gaungdong General Hospital with surgical pathology,complete clinical data and chest CT scanning before operation was retrospectively collected.All patients in this study were classified into primary dataset and independent validation in random.Texture analysis was performed on CT images,while the carcinomas were performed by manual segmentation in order to extract the radiomics features.Radiomics features were extracted and 9 radiomics signatures were finally selected after dimension reduction.Radiomics features were extracted and established via the software Matlab.In order to build the predictive model,Multivariable logistic regression analysis was performed.10-fold cross-validation was used for tuning parameter selection in the LASSO model by minimum criteria.The receiver operating characteristic curves(ROC)and areas under ROC curve(AUC)were used to compare the model performance in the primary validation and the independent validation for evaluating the Differentiation Degree of Esophageal Squamous Carcinoma.Results: Radiomics signature showed great effect in discriminating primary dataset and independent validation.The predictive model has a good performance in primary dataset.The areas under ROC curve equals to 0.791,and the sensitivity is 81.6%,while the specificity equals to 72.3%.In the independent validation,the predictive model also does well,where the areas under ROC curve equals to 0.757,the sensitivity is 70.0%,and the specificity equals to 73.0%(AUC=0.757;sensitivity=70.0%,specificity=73.0%).Conclusions: The predictive model can be used for evaluating the differentiation degree of Esophageal squamous carcinoma efficiently.The model can provide help for clinicians in diagnosis and choice of treatment when dealing with the patients with Esophageal Squamous Carcinoma.
Keywords/Search Tags:Esophageal Squamous Carcinoma, Differentiation Degree, Radiomics
PDF Full Text Request
Related items