Abstract

Motivation: To automate rim lesion segmentation in multiple sclerosisGoal(s): To compare deep learning and conventional methods for rim lesion segmentation in multiple sclerosisApproach: We compare Unet with chan-vese and Grabcut segmention of MR rim positive lesions. Results: Deep learning achieve the highest Dice score among the compared methods. Impact: Automate rim lesion segmentation in Multiple Sclerosis may allow determine those patient with persistent inflammation.