AUTHOR=Zhu Yadi , Yang Ling , Shen Hailin TITLE=Value of the Application of CE-MRI Radiomics and Machine Learning in Preoperative Prediction of Sentinel Lymph Node Metastasis in Breast Cancer JOURNAL=Frontiers in Oncology VOLUME=Volume 11 - 2021 YEAR=2021 URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.757111 DOI=10.3389/fonc.2021.757111 ISSN=2234-943X ABSTRACT=Purpose: To explore the value of machine learning model based on DCE-MRI radiomic features in preoperative prediction of sentinel lymph node (SLN) metastasis of breast cancer. Methods: The clinical、 pathological and MRI data of 177patients with pathologically confirmed breast cancer (81with SLN positive and 96with SLN negative) and underwent conventional DCE-MRI before surgery in the First Affiliated Hospital of Soochow University from January 2015 to May 2021 were analyzed retrospectively. The samples were randomly divided into the training set (n=123) and validation verification set (n= 54) according to the ratio of 7:3,the radiomic features were derived from DCE-MRI phase 2 images, 1316 original eigenvectors are normalized by maximum and minimum normalization, the optimal feature filter and selection operator (LASSO) algorithm were used to obtain the optimal features. Six Five machine learning models of Support Vector Machine, Random Forest, Logistic Regression, Gradient Boosting Decision Tree, Nomogram and Decision Tree were constructed based on the selected features. Radiomics signature and independent risk factors were incorporated to build a combined model. The receiver Receiver operating characteristic curve and area under the curve were was used to evaluate the performance of the above models, and the accuracy, sensitivity, and specificity were calculated. Results: There is no significant difference between all clinical and histopathological variables in breast cancer patients with and without SLN metastasis (P >0.05), except tumor size and BI-RADS classification (P< 0.01). Thirteen features were obtained as optimal features for machine learning models construction. In the validation set, the AUC (0.86) of SVM was the highest among the six five machine learning models. Meanwhile, the combined model showed better performance in sentinel lymph node metastasis (SLNM) prediction and achieved a higher AUC (0.88) in the validation set. Conclusions: We revealed the clinical value of machine learning models established based on DCE-MRI radiomic features, providing a highly accurate, non-invasive, and convenient method to for preoperative prediction of SLNM in breast cancer patients.