Predicting the degree of pathological differentiation of hepatic carcinomas based on enhanced CT radiomics
Objective To investigate the value of predicting the degree of pathological differentiation of hepatocellular carcinoma based on portal phase CT radiomics before surgery. Methods A retrospective collection of 206 patients confirmed by postoperative pathology in the First Affiliated Hospital of Bengbu Medical University with clinical data and complete preoperative CT enhanced scan images, they were divided into low differentiation group and non low differentiation group based on pathological results, the patients were randomly divided into training group (n=145) and test group (n=61) at a ratio of 7∶3. The ITK-SNAP software was used to manually segment tumors from the portal phase,the radiomics features of the tumor tissues were extracted using the Pyradiomics package of Python software.The minimum redundancy maximum redundancy and the least absolute shrinkage and selection operator methods were used to reduce the dimensionality of radiomics features and establish radiomics labels. Logistic regression analysis was used to establish clinical model, radiomics model and combined model, and 100 leave-group-out cross validation was used to verify the reliability of the model. The ROC curve, calibration curve and decision curve were used to evaluate the diagnostic efficacy and clinical application value of the model. Results 9 optimal radiomics features were obtained. In the training group, the area under the curve of clinical model, radiomics model, and combined model was 0.641, 0.740, 0.784, respectively, and the area under the curve was 0.644, 0.692, 0.724 in the test group, respectively. Conclusion The radiomics model based on portal phase CT has certain value in predicting the degree of pathological differentiation of hepatocellular carcinoma before surgery.
radiomicshepatocellular carcinomapathologydegree of differentiation
国家科技期刊平台
NSTL
万方数据
