Skin Lesion Segmentation with Codec Structure Based Upper and Lower Layer Feature Fusion Mechanism

• Cheng Yang,
• GuanMing Lu,

Vol. 16, No. 1, January 31, 2022
10.3837/tiis.2022.01.004, Download Paper (Free):

• Semantic segmentation
• skin lesion segmentation
• Deep Learning
• Convolutional Neural Network (CNN)
• atrous spatial pyramid pooling.

Abstract

The U-Net architecture-based segmentation models attained remarkable performance in numerous medical image segmentation missions like skin lesion segmentation. Nevertheless, the resolution gradually decreases and the loss of spatial information increases with deeper network. The fusion of adjacent layers is not enough to make up for the lost spatial information, thus resulting in errors of segmentation boundary so as to decline the accuracy of segmentation. To tackle the issue, we propose a new deep learning-based segmentation model. In the decoding stage, the feature channels of each decoding unit are concatenated with all the feature channels of the upper coding unit. Which is done in order to ensure the segmentation effect by integrating spatial and semantic information, and promotes the robustness and generalization of our model by combining the atrous spatial pyramid pooling (ASPP) module and channel attentionmodule (CAM). Extensive experiments on ISIC2016 and ISIC2017 common datasets proved that our model implements well and outperforms compared segmentation models for skin lesion segmentation.

Statistics

Cite this article