Evaluation And Prediction Of Neoadjuvant Chemotherapy Response For Breast Cancer Based On DCE-MRI Breast Imaging And Pathological Information

Breast cancer is one of the most malignancies among women worldwide,in the clinical application,the Neoadjuvant Chemotherapy(NACT)of breast cancer has also gradually become a standard model for treatment of breast cancer.The clinical studies have shown that pathologic complete response after NACT,its five-year disease-free survival rate can reach 85% and complete remission of pathology indicates a good prognosis.But the patient in the preoperative neoadjuvant chemotherapy may not be able to obtain the desired effect,therefore,it is necessary to find a reliable non-invasive assessment and prediction method which can evaluate and predict the response of NACT,so that doctors can optimize the chemotherapy regimen and choice of the operation time.All the same time,Dynamic Contrast Enhanced Magnetic Resonance Imaging(DCE-MRI)stands out in all types of breast imaging diagnostic tools by virtue of its high-resolution soft tissue and dynamic characteristics has been widely used.The research of this paper has highlighted the use of dynamic contrast enhanced magnetic resonance imaging to evaluate and predict the response neoadjuvant chemotherapy.In addition,the pathological examination of breast cancer,including molecular subtypes,could provide the supplementary information of prognosis to the breast cancer patients.In this study,a dataset with fifty-seven breast cancer patients were included,all of whom received preoperative MRI examination.Among them,45 patients had complete response(CR),2 patients had partial response(PR)and 10 had stable disease(SD)to chemotherapy based on the Response Evaluation Criteria In Solid Tumors(RECIST)criterion.A total of 297 imaging features including statistical characteristics,morphology,texture and dynamic enhancement were extracted from DCE-MRI and immunohistochemistry(IHC)determined molecular subtypes.This thesis innovative imaging features will be grouped and fuse the molecular subtypings of breast cancer,to explore the significance of molecular subtypes of breast cancer in the prediction of the response of neoadjuvant chemotherapy.The main contents include the following fields:(1)Images pre-processing and molecular subtype judgment: 57 cases of malignant breast cancer were retrospectively analyzed whose immunohistochemistry pathology and DCE-MRI was checked before surgery and chemotherapy.First,breast and lesion regions divided from the DCE-MRI images and acquire the two areas as the lesion region and background region.Second,according to immunohistochemistry Estrogen Receptor(ER),Progesterone Receptor(PR),Human epidermal growth factor receptor(HER-2)and Ki-67 expression result,breast cancer were divided into four molecular subtypes.The distribution of four molecular subtypes was statistically analyzed and the chi-square test was performed.(2)Feature extraction and curative effect prediction: A total of 297 imaging features were extracted in the corresponding regions,in the lesion region including statistical characteristics,morphology,texture and dynamic enhancement and background parenchymal enhancement features in the background region,to explore the predictive properties of neoadjuvant chemotherapy for breast cancer after fused imaging features and molecular features.Area under the receiver operating characteristic curve(AUC)and the cross validation were used to evaluate the model.It is shown that the performance of the classifier can be improved by the fusion of the molecular features.(3)Evaluation of neoadjuvant chemotherapy: The mission and ratio of image features before and after chemotherapy in breast cancer patients were calculated.To explore the feasibility of the new method to evaluated neoadjuvant chemotherapy between the change of before and after chemotherapy images and the molecular subtypes of breast cancer.The results showed that the conformity of the two methods with Pathology were 94.7% and 93% respectively.This thesis carried on objective quantitative research of the role of DCE-MRI imaging features and molecular subtypes of Breast cancer in the prediction of the response of neoadjuvant chemotherapy.The results showed that certain correlation exists between the imaging features and molecular subtypes and the response of neoadjuvant chemotherapy,it also showed that the imaging features and molecular subtypes have better classification of the predictive power.The results further proved the value of imaging diagnosis in the Clinical treatment of breast cancer.