Improving Dermoscopic Image Segmentation with Enhanced Convolutional-Deconvolutional Networks

TL;DR

This paper presents an improved convolutional-deconvolutional network architecture that incorporates multi-color space information and deeper layers to enhance automatic skin lesion segmentation in dermoscopic images, achieving top performance on a major challenge dataset.

Contribution

The authors developed a deeper network with smaller kernels and multi-color space features, significantly improving segmentation accuracy over previous methods.

Findings

Achieved an average Jaccard Index of 0.765 on the ISBI 2017 challenge

Ranked first in the challenge with top segmentation performance

Demonstrated the effectiveness of multi-color space features in segmentation

Abstract

Automatic skin lesion segmentation on dermoscopic images is an essential step in computer-aided diagnosis of melanoma. However, this task is challenging due to significant variations of lesion appearances across different patients. This challenge is further exacerbated when dealing with a large amount of image data. In this paper, we extended our previous work by developing a deeper network architecture with smaller kernels to enhance its discriminant capacity. In addition, we explicitly included color information from multiple color spaces to facilitate network training and thus to further improve the segmentation performance. We extensively evaluated our method on the ISBI 2017 skin lesion segmentation challenge. By training with the 2000 challenge training images, our method achieved an average Jaccard Index (JA) of 0.765 on the 600 challenge testing images, which ranked itself in the first place in the challenge