Cascaded context enhancement network for automatic skin lesion segmentation

作者：

Highlights：

• Propose a cascaded context enhancement neural network for skin lesion segmentation.

• The cascaded context aggregation module generates richer long-range context.

• The context-guided local affinity module extracts fine feature with global context.

• Achieving state-of-the-art performances on four dermoscopy image datasets.

摘要

•Propose a cascaded context enhancement neural network for skin lesion segmentation.•The cascaded context aggregation module generates richer long-range context.•The context-guided local affinity module extracts fine feature with global context.•Achieving state-of-the-art performances on four dermoscopy image datasets.

论文关键词：Convolutional neural network,Deep learning,Dermoscopy image,Skin lesion segmentation

论文评审过程：Received 15 July 2021, Revised 6 January 2022, Accepted 28 March 2022, Available online 2 April 2022, Version of Record 14 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117069