Multiple sclerosis (MS), a demyelinating disease of the central nervous system, affects more than two million people worldwide. Contrast enhancing lesions are thought to reflect active disease state and play a key role in MS management. Deep learning (DL) based on convolutional neural networks has reached state-of-art performance on semantic segmentation tasks. Using annotated images for 398 MS patients, we evaluated DL performance on segmentation of enhancing lesions. Our approach yielded Dice similarity coefficient of 0.78, true positive rate of 0.91, and false positive rate of 0.28 for test data. Network performance was excellent for enhancement volumes ≥70 µl.