A new class of dynamic contrast-enhanced MRI features for breast lesion classification

We propose an ensemble learning approach to classify malignant versus benign breast lesions leveraging morphological and dynamic features derived from Magnetic Resonance Images (MRI). The analysis has been performed on 164 breast lesions of the publicly available “Advanced MRI Breast Lesions” dataset from The Cancer Imaging Archive, containing T2-weighted and Dynamic Contrast-Enhanced (DCE)-MRI sequences, along with the segmentation masks of suspicious lesions. After extracting radiomic features using Pyradiomics Python package, we computed dynamic features from DCE-MRI kinetic curves, which describe the contrast agent wash-in and wash-out. These features have been defined as the derivatives of image intensity measures, like mean and standard deviation, computed inside the lesion masks on the 5 DCE-MRI time steps. We trained and evaluated an eXtreme Gradient Boosting (XGBoost) classifier, experimenting with different feature combinations in a stratified 5-fold cross-validation scheme. The best model trained on T2-weighted MRI morphological features achieved an Area Under the Curve (AUC) score of 0.83±0.04 on the independent test set consisting of 20 lesions, while the model using only dynamic features performed an AUC of 0.91±0.03. Despite being obtained on a limited size test sample, these results show the great potential of features derived from DCE images in breast lesions classification.