RESUMO
Objective To develop and validate a radiomics predictive model based on mammogram for preoperative predicting triple-negative breast cancer (TNBC) or non-triple-negative breast cancer (NTNBC). Methods We retrospectively analyzed 459 Chinese women who were diagnosed with invasive breast cancer (confirmed by pathology) during August 2015 to November 2015. Our cohort included 34 TNBC and random selected 102 NTNBC cases. Regions of interest (ROIs) were manually selected from craniocaudal and mediolateral oblique mammograms by radiologists through manual lesion segmentation, and 43 radiomics features were evaluated. Craniocaudal (CC) single-view, mediolateral oblique (MLO) single-view and CC and MLO double-view classification model were constructed respectively. Classification performance was evaluated by the area under receiver operating characteristic curve (AUC), accuracy, sensitivity and specificity. Kruskal-Walls U test and t test were used to compare the radiomics features between TNBC and UTNBC. Results The model that used the combination of both the CC and MLO view images achieved the overall best performance than using either of the two views alone, yielding an AUC of 0.791, accuracy of 0.798, sensitivity of 0.776 and specificity of 0.806 for TNBC comparing with NTNBC. Three features were selected by the model (gray scale span and inverse different moment for CC, roundness for MLO) showed a statistical significance (P<0.05) and AUC>0.6 in the subtype classification. Conclusion This research constructed model based on mammograms classification model can effectively distinguish between TNBC and NTNBC. This model has potential value for breast cancer molecular subtype classification and clinical treatment.
RESUMO
Objective To characterize the imaging features of fibroblastic and (or) myofibroblastic benign tumors. Methods The imaging manifestations were analyzed in fourteen patients with fibroblastic and (or) myofibroblastic benign tumors of the breast area confirmed by histopathology from July, 2010 to July, 2017. Independent-samples t test was performed to compare ADC values between lesions and normal breast tissue. Results Thirteen cases were adhered to superficial facia of breasts and 1 case was located in the pectoralis. Five lesions were presented as a mass on MRI, 9 lesions were presented as a non-mass. Twelve cases showed low signal intensity on T1WI, 8 cases showed high signal intensity and 4 cases showed moderately or slightly high signal intensity on T2WI. TIC analysis showed that 10 cases had typeⅠenhancement and 4 cases had typeⅢenhancement. There was no difference between mean ADC values of lesions and normal breast tissue (P>0.05). All the cases showed hypoechoic and spiculated margins on ultrasound. Twelve cases were hypovascular ones. Twelve cases underwent mammography. Five cases were presented as a mass and 7 cases were presented as asymmetric. These cases showed equal density without suspicious calcifications. Conclusion The location, MRI, ultrasound and mammography manifestations of fibroblastic and (or) myofibroblastic benign tumors have some characteristics and these imaging findings may help to establish an accurate preoperative diagnosis.