融入双注意力模块的U-Net肺结节图像分割方法
A U-Net Lung Nodule Image Segmentation Method Incorporating a Dual Attention Module
DOI: 10.12677/CSA.2022.127177, PDF,  被引量   
作者: 侯英竹：河北地质大学信息工程学院，河北 石家庄;智能传感物联网技术河北省工程研究中心，河北 石家庄
关键词: 肺结节；图像分割；U-Net；空间注意力模块；通道注意力模块；Pulmonary Nodules； Image Segmentation； U-Net； Spatial Attention Module； Channel Attention Module
摘要: 对肺部医学图像进行分析可以用来肺癌诊断，为了解决肺结节分割的任务中特征提取复杂和分割困难等问题，本文提出了一种融入双注意力模块的U-Net肺结节图像分割方法。该方法在U-Net网络的基础上融入空间注意力模块和通道注意力模块，改善分割网络对复杂环境的感知能力，克服复杂环境对分割结果的干扰从而提高分割效果。在肺结节公开数据集(LUNA16)上进行实验结果表明，本文提出的分割方法能够准确地分割出肺结节区域，能够较为有效地实现肺结节图像分割。
Abstract: The analysis of lung medical images can be used for lung cancer diagnosis. In order to solve the problems of complex feature extraction and difficult segmentation in the task of lung nodule segmentation, a U-Net lung nodule image segmentation network method incorporating a dual attention module was proposed in this paper. The method used to incorporate spatial attention module and channel attention module on the basis of U-Net network to improve the segmentation network's ability to perceive complex environment and overcome the interference of complex environment on segmentation results so as to improve the segmentation effect. Experimental results on the public dataset of lung nodules (LUNA16) show that the proposed segmentation method can accurately segment lung nodule regions and can achieve lung nodule image segmentation more effectively.
文章引用：侯英竹. 融入双注意力模块的U-Net肺结节图像分割方法[J]. 计算机科学与应用, 2022, 12(7): 1756-1764. https://doi.org/10.12677/CSA.2022.127177

参考文献

[1] 陈万青, 张思维, 邹小农. 中国肺癌发病死亡的估计和流行趋势研究[J]. 中国肺癌杂志, 2010, 13(5): 488-493.
[2] Wei, Y., Chang, C.X., Jia, T. and Xu, X.H. (2009) Segmentation of Regions of Interest in Lung CT Im-ages Based on 2-D OTSU Optimized by Genetic Algorithm. Proceedings of 2009 Chinese Control and Decision Con-ference, Guilin, 17-19 June 2009, 5185-5189.
[3] Parveen, S.S. and Kavitha, C. (2013) Detection of Lung Cancer Nodules Using Automatic Region Growing Method. Proceedings of the 4th International Conference on Computing, Communications and Networking Technologies, Tiruchengode, 4-6 July 2013, 1-6. [Google Scholar] [CrossRef] 
[4] Kanitkar, S.S., Thombare, N.D. and Lokhande, S.S. (2015) Detection of Lung Cancer Using Marker-Controlled Watershed Transform. Proceedings of 2015 International Confer-ence on Pervasive Computing, Pune, 8-10 January 2015, 1-6. [Google Scholar] [CrossRef] 
[5] Mirderikvand, N., Naderan, M. and Jamshidnezhad, A. (2016) Accurate Automatic Localisation of Lungnodules Using Graph Cut and Snakes Algorithms. Proceedings of the 6th International Conference on Computer and Knowledge Engineering, Mashhad, 20-21 October 2016, 194-199. [Google Scholar] [CrossRef] 
[6] Farag, A.A., El Munim, H.E.A., Graham, J.H. and Farag, A.A. (2013) A Novel Approach for Lung Nodules Segmentation in Chest CT Using Level Sets. IEEE Transactions on Image Processing, 22, 5202-5213. [Google Scholar] [CrossRef] 
[7] Lo, S.C.B., Chan, H.P., Lin, J.S., Li, H., Freedman, M.T. and Mun, S.K. (1995) Artificial Convolution Neural Network for Medical Image Pattern Recognition. Neural Networks, 8, 1201-1214. [Google Scholar] [CrossRef] 
[8] Long, J., Shelhamer, E. and Darrell, T. (2015) Fully Convolu-tional Networks for Semantic Segmentation. Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, 7-12 June 2015, 3431-3440. [Google Scholar] [CrossRef] 
[9] Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Con-volutional Networks for Biomedical Image Segmentation. Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, 5-9 October 2015, 234-241. [Google Scholar] [CrossRef] 
[10] Cicek, O., Abdulkadir, A., Lienkamp, S.S. (2016) 3D-UNet: Learning Dense Volumetric Segmentation from Sparse Annotation. In: Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Berlin, 221-236. [Google Scholar] [CrossRef] 
[11] 魏颖, 雷志浩, 齐林. 基于注意力机制的3D U-Net婴幼儿脑组织MR图像分割[J]. 东北大学学报(自然科学版), 2021, 42(5): 616-623.
[12] 郝晓宇, 熊俊峰, 薛旭东, 等. 融合双注意力机制3D U-Net的肺肿瘤分割[J]. 中国图象图形学报, 2020, 25(10): 2119-2127.
[13] 王磐, 强彦, 杨晓棠, 等. 基于双注意力3D-UNet的肺结节分割网络模型[J]. 计算机工程, 2021, 47(2): 307-313. [Google Scholar] [CrossRef] 
[14] Oktay, O., Schlemper, J., Le Folgoc, L., Lee, M., Hein-rich, P.M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., Kainz, B., Glocker, B. and Rueckert, D. (2018) At-tention U-Net: Learning Where to Look for the Pancreas.
[15] Fu, J., Liu, J., Tian, H.J., Li, Y., Bao, Y.J., Fang, Z.W. and Lu, H.Q. (2019) Dual Attention Network for Scene Segmentation. Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, 16-20 June 2019, 3146-3154. [Google Scholar] [CrossRef] 
[16] Zhou, Z.W., Siddiquee, M.M.R., Tajbakhsh, N. and Liang, J.M. (2019) UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation.