Task‐based assessment of a convolutional neural network for segmenting breast lesions for radiomic analysis

Purpose Radiomics allows for powerful data‐mining and feature extraction techniques to guide clinical decision making. Image segmentation is a necessary step in such pipelines and different techniques can significantly affect results. We demonstrate that a convolutional neural network (CNN) segmentation method performs comparably to expert manual segmentations in an established radiomics pipeline. Methods Using the manual regions of interest (ROIs) of an expert radiologist (R1), a CNN was trained to segment breast lesions from dynamic contrast‐enhanced MRI (DCE‐MRI). Following network training, we segmented lesions for the testing set of a previously established radiomics pipeline for predicting lymph node metastases using DCE‐MRI of breast cancer. Prediction accuracy of CNN segmentations relative to manual segmentations by R1 from the original study, a resident (R2), and another expert radiologist (R3) were determined. We then retrained the CNN and radiomics model using R3’s manual segmentations to determine the effects of different expert observers on end‐to‐end prediction. Results Using R1’s ROIs, the CNN achieved a mean Dice coefficient of 0.71 ± 0.16 in the testing set. When input to our previously published radiomics pipeline, these CNN segmentations achieved comparable prediction performance to R1’s manual ROIs, and superior performance to those of the other radiologists. Similar results were seen when training the CNN and radiomics model using R3’s ROIs. Conclusion A CNN architecture is able to provide DCE‐MRI breast lesion segmentations which are suitable for input to our radiomics model. Moreover, the previously established radiomics model and CNN can be accurately trained end‐to‐end using ground truth data provided by distinct experts.