Objective:To establish a radiomics signature based on CT images of non-small cell lung cancer (NSCLC) to predict the expression of molecular marker P63.Methods:A total of 245 NSCLC patients who underwent CT scans were retrospectively included.All patients were confirmed by histopathological examinations and P63 expression were examined within 2 weeks after CT examination.Radiomics features were extracted by MaZda software and subjective image features were defined from original non-enhanced CT images.The Lasso-logistic regression model was used to select features and develop radiomics signature,subjective image features model,and combined diagnostic model.The predictive performance of each model was evaluated by the receiver operating characteristic (ROC) curve,and compared with Delong test.Results:Of the 245 patients,96 were P63 positive and 149 were P63 negative.The subjective image feature model consisted of 6 image features.Through feature selection,the radiomics signature consisted of 8 radiomics features.The area under the ROC curves of the subjective image feature model and the radiomics signature in predicting P63 expression statue were 0.700 and 0.755,respectively,without a significant difference (P＞0.05).The combined diagnostic model showed the best predictive power (AUC=0.817,P＜0.01).Conclusion:The radiomics-based CT scan images can predict the expression status of NSCLC molecular marker P63.The combination of the radiomics features and subjective image features can significantly improve the predictive performance of the predictive model,which may be helpful to provide a non-invasive way for understanding the molecular information for lung cancer cells.

To develop a radiomics signature based on CT image features to estimate the expression level of Ki-67 in non-small cell lung cancer (NSCLC).
 Methods: A total of 108 NSCLC patients, who underwent non-enhanced and contrast-enhanced CT scan in our hospital from January 2014 to November 2017, were retrospectively analyzed. They were confirmed by histopathological examination and undergone Ki-67 expression level test within 2 weeks after CT examination. The non-enhanced and contrast-enhanced CT three-dimensional structural images of the lesions were manually delineated by MaZda software, and the texture features of the region of interest were extracted. Combination of feature selection and classification methods were used to build radiomics signatures, and the classification were assessed using misclassification rates. The MaZda software provides texture feature selection methods including mutual information (MI), Fisher coefficients (Fisher), classification error probability combined with average correlation coefficients (POE+ACC), and Fisher+POE+ACC+MI (FPM), and texture feature analysis including raw data analysis (RDA), principal component analysis (PCA), linear classification analysis (LDA) and nonlinear classification analysis (NDA).
 Results: Among the 108 patients, 50 cases were at high levels of Ki-67 expression and 58 cases were at low levels of Ki-67 expression, respectively. The differences of gender, age and pathological type between the two groups were statistically significant (P<0.05). The radiomics signature built by FPM feature selection combined with NDA feature analysis based on non-enhanced CT images achieved the best performance for predicting the level of Ki-67 with a misclassification rate of 14.81%. However, radiomics signature based on contrast-enhanced CT images did not reduce the misclassification rate.
 Conclusion: The radiomics signature based on conventional CT image texture features is helpful to predict the expression of Ki-67 in NSCLC lesions, which can provide a non-invasive technique for assessing the invasiveness and prognosis for NSCLC.
Carcinoma, Non-Small-Cell Lung ; diagnostic imaging ; Gene Expression Regulation, Neoplastic ; Humans ; Ki-67 Antigen ; genetics ; Lung Neoplasms ; diagnostic imaging ; Prognosis ; Retrospective Studies ; Tomography, X-Ray Computed

To explore the feasibility of CT-based image radiomics signature in identification of primary gastric lymphoma and Borrmann type IV gastric cancer.
 Methods: A retrospective analysis of 71 patients with primary gastric lymphoma or Borrmann type IV gastric cancer confirmed by pathology in our Hospital from January 2009 to April 2017 was performed. There were 28 patients with primary gastric lymphoma and 43 patients with Borrmann type IV gastric cancer. The feature extraction algorithm based on Matlab 2017a software was used to extract the features of image, and the logistic regression model was used to screen the features to establish radiomics signature. The CT sign diagnosis model was established, which included the periplasmic fat infiltration, softness of the stomach wall, abdominal lymph node and peripheral organ metastasis, ascites, mucosal white line sign and lesion thickness. The classification of the two models was evaluated by receiver operating characteristic curve.
 Results: A total of 32 3D features were extracted from CT image for each patients. Two features were found to be the most important differential diagnosis factors, and the radiomics signature was established. The CT sign diagnosis model consisted of ascites, periplasmic fat infiltration, stomach wall softness and mucosal white line. For the radiomics signature and the CT subjective finding model, the AUCs were 0.964 and 0.867 with the accuracy at 94.4% and 80.2%, the sensitivity at 93.0% and 74.4%, the specificity at 96.4% and 89.3%, respectively. After Delong test, the diagnostic efficacy of the radiomics signature was higher than the CT sign diagnosis model (P<0.001).
 Conclusion: CT-based image radiomics signature can accurately identify primary gastric lymphoma and Borrmann type IV gastric cancer, and can potentially provide important assistance in clinical diagnosis for the two diseases.
Humans ; Lymphoma, Non-Hodgkin ; Neoplasm Staging ; Retrospective Studies ; Stomach Neoplasms ; Tomography, X-Ray Computed