Segmentation of skin lesions and their attributes using Generative Adversarial Networks

TL;DR

This paper presents a method using Conditional Generative Adversarial Networks to perform detailed segmentation of skin lesions and their attributes, aiding early melanoma detection with high accuracy on dermoscopic images.

Contribution

It introduces a modified Pix2Pix network tailored for multi-channel skin lesion segmentation, reducing annotation effort and improving segmentation accuracy.

Findings

Achieved high Jaccard indices for all segmentation attributes.

Utilized 2018 ISIC dataset with 500 images for training and testing.

Demonstrated effectiveness of the modified GAN in medical image segmentation.

Abstract

This work is about the semantic segmentation of skin lesion boundary and their attributes using Image-to-Image Translation with Conditional Adversarial Nets. Melanoma is a type of skin cancer that can be cured if detected in time. Segmentation into dermoscopic images is an essential procedure for computer-assisted diagnosis due to its existing artifacts typical of skin images. To alleviate the image annotation process, we propose to use a modified Pix2Pix network. The discriminator network learns the mapping from a dermal image as an input and a mask image of six channels as an output. Likewise, the discriminative network output called PatchGAN is varied for one channel and six output channels. The photos used come from the 2018 ISIC Challenge, where 500 photographs are used with their respective semantic map, divided into 75% for training and 35% for testing. Obtaining for 100 training epochs high Jaccard indices for all attributes of the segmentation map.