Fully Convolutional Network based on Contrast Information Integration for Dermoscopic Image Segmentation

Abstract

Melanoma is one of the most common human lethal cancers. Because the lesions have different shapes, sizes, colors, and low contrast, extracting powerful features for fine-grained skin lesion segmentation is still a challenging task today. In this paper, we propose a novel fully convolutional network based on contrast information integration for skin lesion segmentation, which effectively utilizes contrast information from each convolutional block in our network framework. Compared with existing skin lesion segmentation approaches, a new integration module is designed by combining the contrast information for extracting richer feature representation. Finally, we evaluate our method on the public ISIC 2017 challenge dataset and obtain the outstanding performance with the Jaccard Index (JA) of 79.9%, which is higher than other state-of-the-art methods for skin lesion segmentation.