Skin lesion segmentation using U-Net and good training strategies

11/27/2018

∙

by   Fred Guth, et al.

∙

0

∙

share

In this paper we approach the problem of skin lesion segmentation using a convolutional neural network based on the U-Net architecture. We present a set of training strategies that had a significant impact on the performance of this model. We evaluated this method on the ISIC Challenge 2018 - Skin Lesion Analysis Towards Melanoma Detection, obtaining threshold Jaccard index of 77.5