Skin lesion segmentation using high-resolution convolutional neural network. (April 2020)

• Record Type: Journal Article
• Authors: Xie, Fengying; Yang, Jiawen; Liu, Jie; Jiang, Zhiguo; Zheng, Yushan; Wang, Yukun
• Is Part Of: Computer methods and programs in biomedicine. Volume 186(2020)
• Publication Date: 2020-04
• Subjects: Skin lesion segmentation -- Convolutional neural network -- High-resolution feature -- Attention mechanism; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2019.105241
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: A novel convolutional neural network is proposed, which can generate high-resolution feature maps to preserve spatial details. The spatial and channel-wise attention mechanisms are adopted to enhance representative features while suppressing noise. The proposed network can accurately extract skin lesion boundaries, and is robust to hair fibers and artifacts in the images. Abstract: Background and Objective: Skin lesion segmentation is an important but challenging task in computer-aided diagnosis of dermoscopy images. Many segmentation methods based on convolutional neural networks often fail to extract accurate lesion boundaries because the spatial size of feature maps decreases as the maps are processed throughout the network layers. We propose skin lesion segmentation in dermoscopy images based on a convolutional neural network with an attention mechanism, which can preserve edge details. Methods: We devised a high-resolution feature block containing three branches, namely, main, spatial attention, and channel-wise attention branches. The main branch takes high-resolution feature maps as input to extract spatial details around boundaries. The other two attention branches boost the discriminative features in the main branch regarding the spatial and channel-wise dimensions. By fusing the branch outputs, robust features with detailed spatial information can be extracted, and accurate skin lesion boundaries can be obtained. Results: Experiments on datasets from the International Symposium on Biomedical Imaging in 2016 and 2017 and the PH2 dataset retrieved Jaccard indices of 0.783, 0.858, and 0.857, respectively, for the proposed method. Hence, our method can accurately extract skin lesion boundaries and is robust to hair fibers and artifacts in the images. Overall, our method outperforms two typical segmentation networks (FCN-8 s and U-Net) and other state-of-the-art skin lesion segmentation methods. Conclusions: The proposed network endowed with high-resolution feature blocks preserves spatial details during feature extraction, and its attention mechanism enhances representative features while suppressing noise. Hence, the proposed approach provides high-performance skin lesion segmentation.