DSU-Net: Distraction-Sensitive U-Net for 3D lung tumor segmentation

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.

Automated summary

The proposed DSU-Net model addresses the problem of automatic segmentation of lung tumors by incorporating distraction region information in a two-stage U-net model. Stage-I focuses on generating global segmentation and predicting distraction regions, while Stage-II further integrates distraction region information to improve the discrimination of tumor regions.