Prediction of pathologic complete response of neoadjuvant chemotherapy for early triple negative breast cancer using pre-therapeutic MRI

International audienceA total of 76 patients were enrolled in this retrospective monocentric study. All patients had a non-metastatic triple negative breast cancer and underwent a pre-therapeutic MRI protocol (T1-weighted, T2-weigthed, diffusion-weighted and dynamic-contrast-enhanced imaging) before a neoadjuvant chemotherapy. Results of radiomic analyses based on multiple contrast images and using 3 classifiers (support vector machine, Random forest and multilayer perceptron) were leading to a relative interest of using a combination of features extracted from DCE-MRI, T1W and T2W in the aim to predict responders and non-responders