基于Concat-UNet的食管癌肿瘤医学影像分割研究

doi:10.19678/j.issn.1000-3428.0062625

摘要/Abstract

摘要： 食管癌肿瘤的诊断方式主要是医生对胸部计算机断层扫描（CT）影像进行阅片。由于医生的主观判断易受外界环境的干扰，因此诊断结果与实际结果存在偏差。基于深度学习的图像分割网络对辅助诊断食管癌肿瘤具有重要意义。因食管在整体胸部CT影像中所占的区域较小且对比度较低，传统的图像分割网络难以准确地确定食管癌肿瘤的区域。为精准分割医学CT影像中的食管癌肿瘤，提出图像分割网络Concat-UNet。基于U-Net网络，采用编码解码模式的U型对称架构对网络中的卷积模块进行改进，并引入跳跃连接和批量归一化层，将卷积模块的原始输入与提取特征后的输出进行特征融合，以增强网络的特征提取能力。在此基础上，采用BCEWithLogits与Dice损失函数相结合的方式联合训练网络。实验结果表明，相比SegNet、ERFNet、U-Net等网络，Concat-UNet在食管癌数据集上的检测精确率为91.87%，相比基准网络U-Net提升了11.64个百分点，具有较优的分割效果。

关键词: 食管癌, 语义分割, U-Net网络, Concat-UNet网络, 跳跃连接

Abstract: The diagnosis of esophageal cancer tumors mainly depends on the observation of chest images by doctors based on Computed Tomography(CT) scan.Because the doctor's subjective judgment is easily influenced by environmental factors, a deviation may exist between the diagnosis and actual results.The image segmentation network based on deep learning is crucial for the auxiliary diagnosis of esophageal cancer.Because of the small area and low contrast of the esophagus in the entire chest CT image, it is difficult to accurately determine the area of esophageal cancer tumor based on the traditional image segmentation network.This paper proposes an image segmentation network Concat-UNet to accurately segment esophageal cancer tumors in medical CT images.Based on the U-Net network, the convolution module in the network is improved using the U-shaped symmetric architecture of encoding and decoding mode.The skip connection and Batch Normalization(BN) layer are introduced to fuse the original input of the convolution module with the output after feature extraction to enhance the feature extraction capability of the network. On this basis, the combination of BCEWithLogits and Dice loss functions is used to jointly guide the network training to stabilize the network training.The experimental results show that compared with SegNet, ERFNet, U-Net, and other networks, Concat-UNet has a detection accuracy of 91.87% for the esophageal cancer dataset and exhibits an improved segmentation effect.Specifically, Concat-UNet is improved by 11.64 percentage points over the baseline U-Net network.

Key words: esophageal cancer, semantic segmentation, U-Net network, Concat-UNet network, skip connection

中图分类号:

TP391

刘文, 亓文霞, 仲国强, 王佳佳, 王大寒. 基于Concat-UNet的食管癌肿瘤医学影像分割研究[J]. 计算机工程, 2022, 48(12): 312-320.

LIU Wen, QI Wenxia, ZHONG Guoqiang, WANG Jiajia, WANG Dahan. Research on Medical Image Segmentation for Esophageal Cancer Tumors Based on Concat-UNet[J]. Computer Engineering, 2022, 48(12): 312-320.

https://www.ecice06.com/CN/Y2022/V48/I12/312

图/表 9

20230112184215

20230112184218

20230112184222

20230112184225

20230112184229

20230112184232

20230112184235

20230112184239

20230112184243

参考文献

[1] ARNOLD M, SOERJOMATARAM I, FERLAY J, et al.Global incidence of oesophageal cancer by histological subtype in 2012[J].Gut, 2015, 64(3):381-387.
[2] CHEN W Q, ZHENG R S, BAADE P D, et al.Cancer statistics in China, 2015[J].CA:A Cancer Journal for Clinicians, 2016, 66(2):115-132.
[3] 李鹏, 王拥军, 陈光勇, 等.中国巴雷特食管及其早期腺癌筛查与诊治共识(2017万宁)[J].中国实用内科杂志, 2017, 37(9):798-809. LI P, WANG Y J, CHEN G Y, et al.Chinese consensus:screening, diagnosis and management of Barrett's esophagus and adenocarcinoma(2017 Wanning)[J].Chinese Journal of Medicine, 2017, 37(9):798-809.(in Chinese)
[4] 丘文峰.基于Python的医学图像处理框架及其应用[D].广州:华南师范大学, 2010. QIU W F.Python-based medical image processing framework and its application[D].Guangzhou:South China Normal University, 2010.(in Chinese)
[5] 俞益洲, 马杰超, 石德君, 等.深度学习在医学影像分析中的应用综述[J].数据与计算发展前沿, 2019, 1(6):37-52. YU Y Z, MA J C, SHI D J, et al.Application of deep learning in medical imaging analysis:a survey[J].Frontiers of Data & Computing, 2019, 1(6):37-52.(in Chinese)
[6] 王弈, 李传富.人工智能方法在医学图像处理中的研究新进展[J].中国医学物理学杂志, 2013, 30(3):4138-4143. WANG Y, LI C F.The new research progress of artificial intelligent methods in medical image processing[J].Chinese Journal of Medical Physics, 2013, 30(3):4138-4143.(in Chinese)
[7] IOFFE S, SZEGEDY C.Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on Machine Learning.New York, USA:ACM Press, 2015:448-456.
[8] MUTHUKRISHNAN R, RADHA M.Edge detection techniques for image segmentation[J].International Journal of Computer Science & Information Technology, 2012, 3(6):250-254.
[9] KAGANAMI H G, ZOU B J.Region-based segmentation versus edge detection[C]//Proceedings of the 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing.Washington D.C., USA:IEEE Press, 2009:1217-1221.
[10] SHI J B, MALIK J.Normalized cuts and image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8):888-905.
[11] BOYKOV Y, FUNKA-LEA G.Graph cuts and efficient N-D image segmentation[J].International Journal of Computer Vision, 2006, 70(2):109-131.
[12] ROTHER C."GrabCut":Interactive foreground extraction using iterated graph cuts[J].Proceedings of Siggraph, 2004, 23(3):309-314.
[13] COATES A, ANDREW Y.Learning feature representations with K-means[EB/OL].[2021-08-01].https://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=17E81A9ECB385E299D5CC6021E8F3871?doi=10.1.1.269.5607&rep=rep1&type=pdf.
[14] LUXBURG U.A tutorial on spectral clustering[J].Statistics and Computing, 2007, 17(4):395-416.
[15] COMANICIU D, RAMESH V, MEER P.Real-time tracking of non-rigid objects using mean shift[C]//Proceedings of Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2003:142-149.
[16] ACHANTA R, SHAJI A, SMITH K, et al.SLIC superpixels compared to state-of-the-art superpixel methods[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11):2274-2282.
[17] 吴永芳, 杨鑫, 徐敏, 等.基于K均值聚类的图割医学图像分割算法[J].计算机工程, 2011, 37(5):232-234. WU Y F, YANG X, XU M, et al.Graph cuts medical image segmentation algorithm based on K-means clustering[J].Computer Engineering, 2011, 37(5):232-234.(in Chinese)
[18] 杨柳, 陈永林, 王翊, 等.基于核图割模型的肝脏CT图像肿瘤分割[J].计算机工程, 2014, 40(3):238-243. YANG L, CHEN Y L, WANG Y, et al.Tumor segmentation for liver CT images based on kernel graph cut model[J].Computer Engineering, 2014, 40(3):238-243.(in Chinese)
[19] SHELHAMER E, LONG J, DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4):640-651.
[20] TONG N, GOU S P, YANG S Y, et al.Fully automatic multi-organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks[J].Medical Physics, 2018, 45(10):4558-4567.
[21] RONNEBERGER O, FISCHER P, BROX T.U-Net:convolutional networks for biomedical image segmentation[C]//Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention.Berlin, Germany:Springer, 2015:234-241.
[22] DROZDZAL M, VORONTSOV E, CHARTRAND G, et al.The importance of skip connections in biomedical image segmentation[C]//Proceedings of Deep Learning and Data Labeling for Medical Applications.New York, USA:Springer, 2016:179-187.
[23] BROSCH T, TANG L Y W, YOO Y, et al.Deep 3D convolutional encoder networks with shortcuts for multiscale feature integration applied to multiple sclerosis lesion segmentation[J].IEEE Transactions on Medical Imaging, 2016, 35(5):1229-1239.
[24] 林志洁, 郑秋岚, 梁涌, 等.基于内卷U-Net的医学图像分割模型[J].计算机工程, 2022, 48(8):180-186. LIN Z J, ZHENG Q L, LIANG Y, et al.Medical image segmentation model based on involution U-Net[J].Computer Engineering, 2022, 48(8):180-186.(in Chinese)
[25] 仵晨阳, 何瑶.基于U-Net网络的食管癌病灶的分割研究[J].计算机与数字工程, 2020, 48(11):2734-2738. WU C Y, HE Y.Segmentation of esophageal cancer lesions based on U-Net network[J].Computer & Digital Engineering, 2020, 48(11):2734-2738.(in Chinese)
[26] KRÄHENBÜHL P, KOLTUN V.Efficient inference in fully connected CRFs with Gaussian edge potentials[C]//Proceedings of the 24th International Conference on Neural Information Processing Systems.New York, USA:ACM Press, 2011:109-117.
[27] CHEN L C, PAPANDREOU G, KOKKINOS I, et al.DeepLab:semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4):834-848.
[28] CHEN L C, PAPANDREOU G, SCHROFF F, et al.Rethinking atrous convolution for semantic image segmentation[EB/OL].[2021-08-01].https://arxiv.org/pdf/1706.05587.pdf.
[29] LIU W, RABINOVICH A, BERG A C.ParseNet:looking wider to see better[EB/OL].[2021-08-01].https://arxiv.org/pdf/1506.04579.pdf.
[30] BADRINARAYANAN V, KENDALL A, CIPOLLA R.SegNet:a deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12):2481-2495.
[31] ROMERA E, ÁLVAREZ J M, BERGASA L M, et al.ERFNet:efficient residual factorized ConvNet for real-time semantic segmentation[J].IEEE Transactions on Intelligent Transportation Systems, 2018, 19(1):263-272.
[32] HE K M, ZHANG X Y, REN S Q, et al.Deep residual learning for image recognition[C]//Proceedings of Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:770-778.
[33] GLOROT X, BORDES A, BENGIO Y.Deep sparse rectifier neural networks[C]//Proceedings of the 14th International Conference on Artificial Intelligence and statistics.New York, USA:ACM Press, 2011:315-323.

选择文件类型/文献管理软件名称

选择包含的内容