改进的卷积神经网络在肺部图像上的分割应用

doi:10.3778/j.issn.1673-9418.2001042

摘要/Abstract

摘要：

CT成像技术是辅助医生诊断肺部疾病的重要手段。针对肺部各组织结构复杂，难以准确地对肺部CT图像中肺实质进行分割和提取的问题，提出了一种编/解码模式的肺分割算法。为了获得图像的多尺度信息，首先向网络模型中输入多尺度图像，使用残差网络结构作为编码模块，在扩展网络深度的同时不造成网络退化问题；此外，在编码和解码之间利用空洞空间金字塔池化（ASPP）充分提取上文多尺度信息；最后利用级联操作，将捕捉到的信息与编码层信息级联，结合注意力机制从而提高分割精度。通过对LUNA16数据集中89位患者的13 465张CT图像进行测试，以相似性系数和精确度作为主要评判标准，实验精度分别达到了99.56%和99.33%。实验结果表明，该方法能有效分割出肺实质区域，与其他网络相比分割效果更好。

关键词: CT图像, 肺实质, 医学图像分割, 深度学习

Abstract:

CT imaging technology is an important means to assist doctors in diagnosing lung diseases. In order to solve the problem that the lung parenchyma is difficult to be segmented and extracted accurately from the CT images of the lung due to the complex structure of the lung tissues, an algorithm of lung segmentation with encoding/decoding mode is proposed. In order to obtain the multi-scale information of the image, the multi-scale image is firstly input into the network model, and the residual network structure is used as the coding module to expand the depth of the network without causing network degradation. In addition, the multi-scale information is fully extracted by using atrous spatial pyramid pooling (ASPP) between encoding and decoding. Finally, the cascade operation is used to cascade the captured information with the information of the coding layer, and the attention mechanism is combined to improve the segmentation accuracy. By testing 13465 CT images of 89 patients in the LUNA16 data set, the experimental accuracy reaches 99.56% and 99.33%, respectively, with the similarity coefficient and accuracy as the main evaluation criteria. Experimental results show that the method can effectively segment the lung parenchyma area, and the segmentation effect is better than other networks.

Key words: CT image, lung parenchyma, medical image segmentation, deep learning

钱宝鑫，肖志勇，宋威. 改进的卷积神经网络在肺部图像上的分割应用[J]. 计算机科学与探索, 2020, 14(8): 1358-1367.

QIAN Baoxin, XIAO Zhiyong, SONG Wei. Application of Improved Convolutional Neural Network in Lung Image Segmentation[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(8): 1358-1367.

参考文献

[1] Pulagam A R, Kande G B, Ede V K R, et al. Automated lung segmentation from HRCT scans with diffuse parenchymal lung diseases[J]. Digit Imaging, 2016, 29: 507-519.
[2] Mansoor A, Bagci U, Foster B, et al. Segmentation and image analysis of abnormal lungs at CT: current approaces, chal-lenges, and future trends[J]. Radiographics, 2015, 35(4): 1056-1076.
[3] Hu S, Hoffman E A, Reinhardt J M. Automatic lung segmen-tation for accurate quantitation of volumetric X-ray CT ima-ges[J]. IEEE Transactions on Medical Imaging, 2001, 20(6): 490-498.
[4] Adams R, Bischof L. Seeded region growing[J]. IEEE Tran-sactions on Pattern Analysis and Machine Intelligence, 1994, 16(6): 641-647.
[5] Xiao G, Yun X, Wu J M. A multi-cue mean-shift target trac-king approach based on fuzzified region dynamic image fusion[J]. Science China (Information Sciences), 2012, 55(3): 577-589.
[6] Long J, Shelhamer E, Darrell T, et al. Fully convolutional networks for semantic segmentation[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, Jun 7-13, 2015. Piscataway: IEEE, 2015: 3434-3440.
[7] Ronneberger O, Fischer P, Brox T, et al. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedings of the 18th International Conference on Medical Image Com-puting and Computer-Assisted Intervention, Munich, Oct 5-9, 2015. Cham: Springer, 2015: 234-241.
[8] Milletari F, Navab N, Ahmadi S A. V-Net: fully convolu-tional neural networks for volumetric medical image segmen-tation[C]//Proceedings of the 4th International Conference on 3D Vision, Stanford, Oct 25-28, 2016. Washington: IEEE Computer Society, 2016: 565-571.
[9] Zhao H S, Shi J P, Qi X J, et al. Pyramid scene parsing net-work[C]//Proceedings of the 30th IEEE Conference on Com-puter Vision and Pattern Recogntion. Washington: IEEE Com-puter Society, 2017: 6230-6239.
[10] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Com-puter Society Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2016: 770-778.
[11] Glorot X, Bordes A, Bengio Y. Deep sparse rectifier neural networks[J]. Journal of Machine Learning Research, 2011, 15: 315-323.
[12] Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions[J]. arXiv:1511.07122, 2015.
[13] Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]//Pro-ceedings of the 32nd International Conference on Machine Learning, Lille, Jul 6-11, 2015: 448-456.
[14] He K M, Zhang X Y, Ren S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[C]//LNCS 8691: Proceedings of the 2014 European Conference on Computer Vision. Cham: Springer, 2014: 346-361.
[15] Yang M K, Yu K, Zhang C, et al. DenseASPP for semantic segmentation in street scenes[C]//Proceedings of the 2018 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2018: 3684-3692.
[16] Chollet F. Xception: deep learning with depthwise separable convolutions[C]//Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2017: 1800-1808.
[17] Luong T, Pham H, Manning C D. Effective approaches to attention-based neural machine translation[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2015: 1412-1421.
[18] Abraham N, Khan N M. A novel focal Tversky loss function with improved attention U-net for lesion segmentation[C]//Proceedings of the IEEE 16th International Symposium on Biomedical Imaging. Piscataway: IEEE, 2019: 683-687.
[19] Chung H, Ko H, Jeon S J. Automatic lung segmentation with juxta-pleural nodule identification using active contour model and Bayesian approach[J]. IEEE Journal of Translational Engineering in Health and Medicine, 2018, 6: 1800513.
[20] Geng L, Zhang S Q, Tong J, et al. Lung segmentation method with dilated convolution based on VGG-16 network[J]. Com-puter Assisted Surgery, 2019, 24: 27-33.
[21] Chen L C, Papandreou G, Schroff F, et al. Rethinking atrous convolution for semantic image segmentation[J]. arXiv:1706. 05587, 2017.
[22] Oktay O, Schlemper J, Le Folgoc L, et al. Attention U-net: learning where to look for the pancreas[J]. arXiv:1804.03999, 2018.
[23] Gu Z W, Cheng J, Fu H Z, et al. CE-Net: context encoder network for 2D medical image segmentation[J]. IEEE Tran-sactions on Medical Imaging, 2019, 30(10): 2281-2292.