Triplet attention fusion module: A concise and efficient channel attention module for medical image segmentation. (April 2023)

• Record Type: Journal Article
• Authors: Wu, Yanlin; Wang, Guanglei; Wang, Zhongyang; Wang, Hongrui; Li, Yan
• Is Part Of: Biomedical signal processing and control. Volume 82(2023)
• Publication Date: 2023-04
• Subjects: Medical image -- Semantic segmentation -- Channel attention -- Lightweight; 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.2022.104515
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: In this paper, we propose the triplet attention fusion (TAF) module, which realizes the effective fusion of global and local interactions and indirect and direct mapping in channel dimension while ensuring low computational complexity and computational cost. Because of its lightweight and convenient advantages, the TAF module can be integrated into the existing semantic segmentation networks. Tested on ISIC-2018 and LiTS datasets, the experimental results show that TAF can greatly improve the performance of the network compared with other attention modules when a small number of parameters are introduced. The performance of UNet with only TAF module is close to or even surpasses that of the other state-of-the-art network models. Abstract: Concise segmentation of medical images is vital for diagnosing and treating diseases. In recent years, convolutional neural networks (CNNs) have yielded satisfactory results in the field of medical image segmentation, and researchers are striving to improve the segmentation performance of CNNs by using the channel attention mechanism. However, most existing channel attention modules have numerous parameters and use a single compression and activation function in the process of attention realization. This limits the effect of attention promotion. To solve this problem, in this paper, we propose the triplet attention fusion (TAF) module. It combines direct and indirect mapping to achieve effective fusion of global-local information. In addition, this method has low computational complexity. Because of its lightweight and convenient advantages, the TAF module can be integrated into the existing semantic segmentation networks. The experimental results on ISIC-2018 and LiTS datasets show that TAF can greatly improve the performance of the network. Compared with other attention modules, it introduces fewer parameters. In addition, the performance of UNet with TAF module is close to or even surpasses that of the other state-of-the-art network models. It proves the superiority and effectiveness of our proposed module in medical image segmentation.