Objective:To investigate the predictive value of radiomics features derived from dynamic contrast-enhanced MRI (DCE-MRI) based on habitat imaging technology for pathological complete response after neoadjuvant therapy (NAT) for breast cancer.Methods:All patients were female, aged 25-67 years. Patients were stratified into training ( n=83) and validation ( n=36) sets via stratified random sampling (7∶3 ratio). Pathological complete remission (pCR) and non-pathological complete remission (non-pCR) were defined using the Miller-Payne grading system. All patients underwent DCE-MRI before NAT. ITK-Snap software was used to outline the region of interest (ROI), the imaging histological features of the entire tumor region were extracted and screened, a traditional imaging histological model for predicting post-NAT pCR (ROI overall model) was constructed; the tumor region was divided into three subregions using habitat imaging technology, and the imaging histological features within ROI subregion 1, ROI subregion 2, and ROI subregion 3 were extracted and screened, and the habitat imaging model for predicting post-NAT pCR were constructed (ROI subregion 1 model, ROI subregion 2 model, ROI subregion 3 model). Univariate logistic regression identified clinical predictors of pCR for clinical model construction. Combined models integrating clinical predictors and habitat imaging features were established. The efficacy of each model in predicting pCR after NAT in breast cancer was evaluated using receiver operating characteristic curves and area under the curve (AUC), and the efficacy of clinical application of the models was evaluated using decision curve analysis (DCA). Results:Of the 119 patients, 74 were pCR patients, with 52 in the training set and 22 in the validation set, and 45 were non-pCR patients, with 31 in the training set and 14 in the validation set. Logistic regression analysis showed that human epidermal growth factor receptor 2 status ( OR=0.254, 95% CI 0.093-0.697, P=0.008) was an independent predictor of pCR after NAT, and this was used to construct a clinical prediction model. The predictive efficacy of ROI subregion 1 model and ROI subregion 2 model in the habitat model was higher than that of the traditional imaging histology model (ROI overall model), with AUCs of 0.805, 0.748,0.728 for the training set and 0.776,0.718,0.708 for the validation set, respectively. The combined clinical prediction model for predicting pCR after NAT in breast cancer had AUCs of 0.877 and 0.818 for the training and validation sets, respectively. DCA showed a higher net benefit for the combined model than for the traditional imaging histology model and the habitat imaging histology model. Conclusion:Compared with the traditional method of extracting the entire tumor region, extracting radiomics features from DCE-MRI subregions based on habitat imaging technology can improve the predictive performance of NAT efficacy in breast cancer.

Objective:To investigate the predictive value of radiomics features derived from dynamic contrast-enhanced MRI (DCE-MRI) based on habitat imaging technology for pathological complete response after neoadjuvant therapy (NAT) for breast cancer.Methods:All patients were female, aged 25-67 years. Patients were stratified into training ( n=83) and validation ( n=36) sets via stratified random sampling (7∶3 ratio). Pathological complete remission (pCR) and non-pathological complete remission (non-pCR) were defined using the Miller-Payne grading system. All patients underwent DCE-MRI before NAT. ITK-Snap software was used to outline the region of interest (ROI), the imaging histological features of the entire tumor region were extracted and screened, a traditional imaging histological model for predicting post-NAT pCR (ROI overall model) was constructed; the tumor region was divided into three subregions using habitat imaging technology, and the imaging histological features within ROI subregion 1, ROI subregion 2, and ROI subregion 3 were extracted and screened, and the habitat imaging model for predicting post-NAT pCR were constructed (ROI subregion 1 model, ROI subregion 2 model, ROI subregion 3 model). Univariate logistic regression identified clinical predictors of pCR for clinical model construction. Combined models integrating clinical predictors and habitat imaging features were established. The efficacy of each model in predicting pCR after NAT in breast cancer was evaluated using receiver operating characteristic curves and area under the curve (AUC), and the efficacy of clinical application of the models was evaluated using decision curve analysis (DCA). Results:Of the 119 patients, 74 were pCR patients, with 52 in the training set and 22 in the validation set, and 45 were non-pCR patients, with 31 in the training set and 14 in the validation set. Logistic regression analysis showed that human epidermal growth factor receptor 2 status ( OR=0.254, 95% CI 0.093-0.697, P=0.008) was an independent predictor of pCR after NAT, and this was used to construct a clinical prediction model. The predictive efficacy of ROI subregion 1 model and ROI subregion 2 model in the habitat model was higher than that of the traditional imaging histology model (ROI overall model), with AUCs of 0.805, 0.748,0.728 for the training set and 0.776,0.718,0.708 for the validation set, respectively. The combined clinical prediction model for predicting pCR after NAT in breast cancer had AUCs of 0.877 and 0.818 for the training and validation sets, respectively. DCA showed a higher net benefit for the combined model than for the traditional imaging histology model and the habitat imaging histology model. Conclusion:Compared with the traditional method of extracting the entire tumor region, extracting radiomics features from DCE-MRI subregions based on habitat imaging technology can improve the predictive performance of NAT efficacy in breast cancer.

Objective To compare the difference of entrance dose between CR and amorphous silocon DR system in chest imaging, and to discuss their optimum exposure dose. Methods For CR and DR, different entrance dose was measured by dosimeter in chest phantom. The value of IQFinv was analyzed by CDRAD2. 0 software. Image quality difference between CR and DR was assessed by group t-test. The relationship between image quality and entrance dose was tested by using Pearson correlation analysis. The best IQFinv values in CR and DR system were achieved via ROC curve analysis, and the exposure dose was then calculated. Results There were direct correlation values between entrance dose and the value of IQFinv in CR and DR system, respectively( r =0. 893 ,0. 848 ,P < 0. 01 ) . The linear regression equation for DR was IQFinv =0. 0050 +3. 359, and for CR was IQFinv =0. 005D + I. 651 , where D was entrance dose. The difference of IQFinv value between CR and DR was significant(t = 5. 455 ,P < 0. 05). The best IQFinv value of the two groups from ROC analysis was 3.55. Conclusions With the entrance dose increased, the detection ability of contrast-detail was elevated in the two digital radiography systems. With equal entrance dose, the detection ability of DR in contrast-detail was superior to CR. With equal image quality, DR obviously decreased the radiation dose to the patients.