# Automatic skin lesion segmentation with fully convolutional-deconvolutional networks

## TL;DR

This paper presents a fully convolutional-deconvolutional neural network approach for automatic skin lesion segmentation, validated on the ISBI 2017 challenge dataset to improve melanoma detection accuracy.

## Contribution

The paper introduces a novel fully convolutional-deconvolutional network architecture specifically designed for skin lesion segmentation tasks.

## Key findings

- Achieved high segmentation accuracy on ISBI 2017 dataset
- Demonstrated effectiveness of the proposed network architecture
- Validated method's potential for aiding melanoma diagnosis

## Abstract

This paper summarizes our method and validation results for the ISBI Challenge 2017 - Skin Lesion Analysis Towards Melanoma Detection - Part I: Lesion Segmentation