ISIC 2017 Skin Lesion Segmentation Using Deep Encoder-Decoder Network

TL;DR

This paper presents a deep encoder-decoder network with novel data augmentation and multi-model testing strategies for skin lesion segmentation, demonstrating improved performance in the ISBI Challenge 2018.

Contribution

It introduces a novel combination of deep learning architecture, data augmentation, and multi-model testing for skin lesion segmentation.

Findings

Effective segmentation results on ISBI Challenge 2018 data

Improved accuracy through data augmentation and model comparison

Validated approach with competitive performance

Abstract

This paper summarizes our method and validation results for part 1 of the ISBI Challenge 2018. Our algorithm makes use of deep encoder-decoder network and novel skin lesion data augmentation to segment the challenge objective. Besides, we also propose an effective testing strategy by applying multi-model comparison.