文献类型：期刊文献

英文题名：TD-Net: Trans-Deformer network for automatic pancreas segmentation

作者：Dai, Shunbo[1];Zhu, Yu[1,3];Jiang, Xiaoben[1];Yu, Fuli[1];Lin, Jiajun[1];Yang, Dawei[1,2,3]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Fudan Univ, Zhongshan Hosp, Dept Pulm & Crit Care Med, Shanghai 200032, Peoples R China;[3]Shanghai Engn Res Ctr Internet Things Resp Med, Shanghai, Peoples R China

年份：2023

卷号：517

起止页码：279

外文期刊名：NEUROCOMPUTING

收录：;EI(收录号：20224513094487);WOS:【SCI-EXPANDED(收录号:WOS:000944860500002)】；

基金：Acknowledgments This work was supported in part by the Science and Technology Commission of Shanghai Municipality (20DZ2254400, 21DZ2200600, 20DZ2261200) , National Scientific Foundation of China (82170110) , Fujian Province Department of Science and Technology (2022D014) .

语种：英文

外文关键词：Pancreas segmentation; Deformable convolution; Vision transformer; Wavelet decomposition; Deep supervision

摘要：Accurate and efficient pancreas segmentation is the basis for subsequent diagnosis and qualitative treat-ment of pancreatic cancer. Segmenting the pancreas from abdominal CT images is a challenging task because the morphology of the pancreas varies greatly among different individuals and may be affected by problems such as the unbalanced category and blurred boundaries. This paper proposes a two-stage Trans-Deformer network to solve these problems of pancreas segmentation. To be specific, we first use 2D Unet for coarse segmentation to generate candidate regions of the pancreas. In the fine segmentation stage, we propose to integrate deformable convolution into Vision Transformer (VIT) for solving the deformation problem of the pancreas. For the problem of blurred boundaries caused by low contrast in the pancreas, a multi-input module based on wavelet decomposition is proposed to make our network pay more attention to high-frequency texture information. In addition, we propose using the Scale Inter-active Fusion (SIF) module to merge local features and global features. Our method was evaluated on the public NIH dataset including 82 abdominal contrast-enhanced CT volumes and the public MSD dataset including 281 abdominal contrast-enhanced CT volumes via fourfold cross-validation. We have achieved the average Dice Similarity Coefficient (DSC) values of 89.89 +/- 1.82 % on the NIH dataset, and 91.22 +/- 1.37 % on the MSD dataset, outperforming other exiting state-of-the-art pancreas segmentation methods.(c) 2022 Elsevier B.V. All rights reserved.