Automatic segmentation of skin lesions using deep learning

TL;DR

This paper presents an automated deep learning approach for skin lesion segmentation in dermoscopic images, utilizing U-net architecture with enhanced preprocessing and post-processing techniques to improve accuracy.

Contribution

The study introduces a novel combination of intensity, color, and texture enhancement with morphological post-processing in a U-net framework for improved lesion segmentation.

Findings

Achieved accurate lesion boundary segmentation on ISIC data

Enhanced segmentation performance with preprocessing techniques

Demonstrated effectiveness of combined pre- and post-processing methods

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.