English

Automatic segmentation of skin lesions using deep learning

Computer Vision and Pattern Recognition 2018-07-16 v1

Abstract

This paper summarizes the method used in our submission to Task 1 of the International Skin Imaging Collaboration's (ISIC) Skin Lesion Analysis Towards Melanoma Detection challenge held in 2018. We used a fully automated method to accurately segment lesion boundaries from dermoscopic images. A U-net deep learning network is trained on publicly available data from ISIC. We introduce the use of intensity, color, and texture enhancement operations as pre-processing steps and morphological operations and contour identification as post-processing steps.

Keywords

Cite

@article{arxiv.1807.04893,
  title  = {Automatic segmentation of skin lesions using deep learning},
  author = {Joshua Peter Ebenezer and Jagath C. Rajapakse},
  journal= {arXiv preprint arXiv:1807.04893},
  year   = {2018}
}

Comments

4 pages, 1 figure, extended abstract of submission to ISIC 2018 skin analysis challenge

R2 v1 2026-06-23T02:59:50.582Z