Breast Cancer Res Treat. 2018 Oct 16. [Epub ahead of print]
Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set.
Elizabeth Hope Cain, Ashirbani Saha, Michael R. Harowicz, Jeffrey R. Marks, P. Kelly Marcom, Maciej A. Mazurowski.
Duke University School of Medicine, Durham, USA; Johns Hopkins University, Baltimore, USA; Duke University, Durham, USA.
PURPOSE: To determine whether a multivariate machine learning-based model using computer-extracted features of pre-treatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can predict pathologic complete response (pCR) to neoadjuvant therapy (NAT) in breast cancer patients.
METHODS: Institutional review board approval was obtained for this retrospective study of 288 breast cancer patients at our institution who received NAT and had a pre-treatment breast MRI. A comprehensive set of 529 radiomic features was extracted from each patient's pre-treatment MRI. The patients were divided into equal groups to form a training set and an independent test set. Two multivariate machine learning models (logistic regression and a support vector machine) based on imaging features were trained to predict pCR in (a) all patients with NAT, (b) patients with neoadjuvant chemotherapy (NACT), and (c) triple-negative or human epidermal growth factor receptor 2-positive (TN/HER2+) patients who had NAT. The multivariate models were tested using the independent test set, and the area under the receiver operating characteristics (ROC) curve (AUC) was calculated.
RESULTS: Out of the 288 patients, 64 achieved pCR. The AUC values for predicting pCR in TN/HER+ patients who received NAT were significant (0.707, 95% CI 0.582-0.833, p
CONCLUSIONS: The multivariate models based on pre-treatment MRI features were able to predict pCR in TN/HER2+ patients.
KEYWORDS: Pathologic complete response Neoadjuvant therapy Breast cancer Breast cancer MRI MRI radiomics Machine learning Logistic regression Support vector machines