Skin lesion segmentation using U-Net and good training strategies

2018/11/27 by Guth, Fred, deCampos, Teofilo E.
#68T45 #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #I.2.10

paper · doi:10.48550/arxiv.1811.11314

Abstract

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%.

Related

• Lesion segmentation using U-Net network
• Skin Lesion Segmentation: U-Nets versus Clustering
• Semantic Segmentation of Skin Lesions using a Small Data Set
• Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks
• U-Net-based Models for Skin Lesion Segmentation: More Attention and Augmentation