Heterogeneity of Tumor and its Surrounding Stroma on DCE-MRI and Diffusion Weighted Imaging in Predicting Histological Grade and Lymph Node Status of Breast Cancer

摘要

Breast cancer histological grade and lymph node status are important in evaluating the prognosis of patients. This studyaim to predict these factors by analyzing the heterogeneity of tumor and its adjacent stroma based on dynamic contrastenhancement magnetic resonance imaging (DCE-MRI) and diffusion-weighted imaging (DWI). A dataset of 172 patientswith surgically verified lymph node status (positive lymph nodes, n=62; negative lymph nodes, n=110) who underwentpreoperative DCE-MRI and DWI examination was collected. Among them, 144 cases had available histological gradeinformation, including 56 cases of low-grade (grade 1 and 2), and 88 samples of high-grade (grade 3). To this end, weidentified six tumor subregions on DCE-MRI as well as the corresponding subregions on ADC according to their distancesto the tumor boundary. The statistical and Haralick texture features were extracted in each subregion, based on whichpredictive models were built to predict histological grade and lymph node status in breast cancer. An area under a receiveroperating characteristic curve (AUC) was computed with a leave-one-out cross-validation (LOOCV) method to assesseach classifier’s performance. For histological grade prediction, the classifier using DCE-MRI features in the inner tumorachieved best performance among all the subregions with AUC of 0.859. For lymph node status, classifier based onDCE-MRI features from tumor subregion of proximal peritumoral stromal shell obtained highest AUC of 0.882 among allthe regions. Furthermore, the predictions from DCE-MRI and DWI were fused, and the AUC value was increased to 0.895for discriminating histological grade. Our results demonstrate that DCE-MRI and ADC imaging features arecomplementary in predicting histological grade in breast cancer.