Radiologist-Level Performance by Using Deep Learning for Segmentation of Breast Cancers on MRI Scans

Abstract

When trained on a sufficiently large dataset, the developed 3D U-Net performed as well as fellowship-trained radiologists in detailed 2D segmentation of breast cancers at routine clinical MRI.<b>Keywords:</b> MRI, Breast, Segmentation, Supervised Learning, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning AlgorithmsPublished under a CC BY 4.0 license. <i>Supplemental material is available for this article.</i>