OAU-net: Outlined Attention U-net for biomedical image segmentation. (January 2023)

• Record Type: Journal Article
• Authors: Song, Haojie; Wang, Yuefei; Zeng, Shijie; Guo, Xiaoyan; Li, Zheheng
• Is Part Of: Biomedical signal processing and control. Volume 79(2023)Part 1
• Publication Date: 2023-01
• Subjects: Biomedical image segmentation -- Bypass branching strategy -- Outlined filter kernel -- Hybrid attention module; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104038
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Different processing methods should be used for different encoding and decoding depths. An edge detection operator sensitive to semantic segmentation is introduced to obtain more edge information. The proposed attention mechanism can simultaneously emphasize the independence between channel and location. Statistical analysis and comparative experiments have proved the superiority of the proposed network. Abstract: In this paper, we propose an Outlined Attention U-network (OAU-net) with bypass branching strategy to solve biomedical image segmentation tasks, which is capable of sensing shallow and deep features. Unlike previous studies, we use residual convolution and res2convolution as encoders. In particular, the outline filter and attention module are embedded in the skip connection part, respectively. Shallow features will enhance the edge information after being processed by the outline filter. Meanwhile, in the depths of the network, to better realize feature fusion, our attention module will simultaneously emphasize the independence between feature map channels (channel attention module) and each position information (spatial attention module), that is, the hybrid domain attention module. Finally, we conducted ablation experiments and comparative experiments according to three public data sets (pulmonary CT lesions, Kaggle 2018 data science bowl, skin lesions), and analyzed them with classical evaluation indexes. Experimental results show that our proposed method improves segmentation accuracy effectively. Our code is public at https://github.com/YF-W/OAU-net.