DSU-Net: Distraction-Sensitive U-Net for 3D lung tumor segmentation. (March 2022)

• Record Type: Journal Article
• Authors: Zhao, Junting; Dang, Meng; Chen, Zhihao; Wan, Liang
• Is Part Of: Engineering applications of artificial intelligence. Volume 109(2022)
• Publication Date: 2022-03
• Subjects: Lung tumor -- 3D-segmentation -- CT volumes -- U-Net -- Distraction attention; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2021.104649
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Automatic segmentation of lung tumors is a crucial and challenging problem. Many existing methods suffer from ambiguity of tissue regions and tumor regions, which occur with similar appearance. To address this problem, we propose a new cascaded two-stage U-net model, Distraction-Sensitive U-Net (DSU-Net), to explicitly take the ambiguous region information (referred as distraction region) into account. Stage-I generates a global segmentation for the whole input CT volume and predicts latent distraction regions, which contain both false negative areas and false positive areas, against the segmentation ground truth. Stage-II embeds the distraction region information into local segmentation for volume patches to further discriminate the tumor regions. To this end, a Distraction Attention Module (DAM) is proposed and applied in each level of U-Net in Stage-II, to improve the discrimination of features. We evaluate our network on a lung cancer dataset from Gross Target Volume segmentation of MICCAI2019 challenge. Experimental results show that the proposed DSU-Net outperforms existing U-like networks. Highlights: Propose the Distraction-Sensitive U-Net (DSU-Net) for 3D lung tumor segmentation. Embed distraction-region information in the cascaded DSU-Net model. Design a Distraction Attention Module (DAM) to enhance the discrimination of features. Achieve performance superior over those U-like methods for lung tumor segmentation.