RESUMEN
Objective:To evaluate the value of preoperative prediction of vessel invasion (VI) of locally advanced gastric cancer by machine learning model based on the venous phase enhanced CT radiomics features.Methods:A retrospective analysis of 296 patients with locally advanced gastric cancer confirmed by pathology in the First Affiliated Hospital of Zhengzhou University from July 2011 to December 2020 was performed. The patients were divided into VI positive group ( n=213) and VI negative group ( n=83) based on pathological results. The data were divided into training set ( n=207) and test set ( n=89) according to the ratio of 7∶3 with stratification sampling. The clinical characteristics of patients were recorded, and the independent risk factors of gastric cancer VI were screened by multivariate logistic regression. Pyradiomics software was used to extract radiomic features from the venous phase enhanced CT images, and the minimum absolute shrinkage and selection algorithm (LASSO) was used to screen the features, obtain the optimal feature subset, and establish the radiomics signature. Four machine learning algorithms, including extreme gradient boosting (XGBoost), logistic, naive Bayes (GNB), and support vector machine (SVM) models, were used to build prediction models for the radiomics signature and the screened clinical independent risk factors. The efficacy of the model in predicting gastric cancer VI was evaluated by the receiver operating characteristic curve. Results:The degree of differentiation (OR=13.651, 95%CI 7.265-25.650, P=0.003), Lauren′s classification (OR=1.349, 95%CI 1.011-1.799, P=0.042) and CA199 (OR=1.796, 95%CI 1.406-2.186, P=0.044) were independent risk factors for predicting the VI of locally advanced gastric cancer. Based on the venous phase enhanced CT images, 864 quantitative features were extracted, and 18 best constructed radiomics signature were selected by LASSO. In the training set, the area under the curve (AUC) of XGBoost, logistic, GNB and SVM models for predicting gastric cancer VI were 0.914 (95%CI 0.875-0.953), 0.897 (95%CI 0.853-0.940), 0.880 (95%CI 0.832-0.928) and 0.814 (95%CI 0.755-0.873), respectively, and in the test set were 0.870 (95%CI 0.769-0.971), 0.877 (95%CI 0.788-0.964), 0.859 (95%CI 0.755-0.961) and 0.773 (95%CI 0.647-0.898). The logistic model had the largest AUC in the test set. Conclusions:The machine learning model based on the venous phase enhanced CT radiomics features has high efficacy in predicting the VI of locally advanced gastric cancer before the operation, and the logistic model demonstrates the best diagnostic efficacy.
RESUMEN
Objective To prepare the 99Tcm-labeled human epidermal growth factor receptor type 2 (HER2) affibody molecule ZHER2:342 and evaluate its receptor binding specificity in vitro.Methods The molecular ZHERa:342 was labeled with 99Tcm using the ligand exchange method.The labeling efficiency and radiochemical purity were measured by HPLC.The major factors,such as the mass of SnC12 and NaOH and reaction time were analyzed,and the optimal method was summarized.Cell binding kinetics and cellular retention of the probe were investigated in HER2-expressing SKOV-3 cells and MDA-MB-231 cells with low HER2 expression respectively.HER2 binding specificity of 99Tcm-ZHER2:342 was analyzed by a pre-injection of excess unlabeled ZHER2:342 to saturate HER2 receptors.One-way analysis of variance and two-sample t test were used.Results The optimal labeling procedure was as follows:5 μg (1 g/L) of ZHER2:342 was mixed with 5 μg of NaOH (1 g/L),then 8.8 μg SnC12(1 g/L,solution) was added,followed by 150 μl (37 MBq) 99TcmO4-solution,and finally the mixture was slightly vortexed and incubated for 1 h at room temperature.99TcmZHER2:342 was stable in vitro with a high labeling efficiency of (98.10± 1.73)％.The radiochemical purity was ＞ 98％,and was more than 85％ after the incubation for 24 h in saline and fresh human serum.The cell binding of 99Tcm-ZHER2:342 with HER2-expressing SKOV-3 cells gradually increased over time with a peak of (9.95± 1.02)％ at 6 h.The binding of 99Tcm-ZHER2:342 in SKOV-3 cells was significantly higher than that in MDA-MB-231 cells at every time point (5.68-9.88 vs 0.56-2.11 ; t:from-34.50 to-13.14,all P＜0.01).The labeled molecular probe retained the capacity to bind specifically to HER2-expressing SKOV-3 cells since the cell binding decreased from (9.95 ± 1.02) ％ to (2.11 ±0.27) ％ after receptor saturation (t =-13.14,P＜0.01).Conclusions 99Tcm-ZHER2:342 has a high labeling efficiency,good stability and optimal binding specificity.These characteristics enable it to be a promising molecular probe for HER2-targeting imaging.