基于内卷U-Net的医学图像分割模型

doi:10.19678/j.issn.1000-3428.0062023

摘要/Abstract

摘要： 图像分割技术的主要对象为自然图像和医学图像，相对于自然图像而言，医学图像的语义分割通常需要较高的精度以进行下一步的临床分析、诊断和规划治疗。目前用于医学图像语义分割的深度神经网络模型由于仅考虑位置的平移不变性，存在局部感受野较小、无法表达长范围依赖关系的问题。设计一种面向医学图像的分割模型，基于内卷U-Net网络，使用内卷操作代替传统的卷积操作，并将内卷结构作为基本的网络结构，提升模型对医学图像局部特征的学习能力。在模型的瓶颈层引入注意力机制模块来学习图像长范围的依赖关系，以提高医学图像语义分割的精度。在肺部CT数据集上的实验结果表明，该模型的Dice系数为0.998，较基于卷积神经网络的分割模型约提高5%，并且大幅缩短Hausdorff距离，具有更高的分割准确度以及较好的稳健性。

关键词: 图像分割, 内卷网络, 图像处理, 注意力机制, U-Net网络

Abstract: The main objects of image segmentation technology are natural images and medical images.Compared with that of natural images, semantic segmentation of medical images usually requires high accuracy for the subsequent steps of clinical analysis, diagnosis, and treatment planning.At present, the depth neural network model used to semantically segment medical images only considers the translation invariance of position, which features an insufficiently large local receptive field, leaving no way to express long-range dependence.Therefore, medical image segmentation model is proposed in this paper.Based on the Involution U-Net network, the involution operation replaces the traditional convolution operation, and the involution structure is adopted as the basic network structure to tailor the model's learning ability to the local features of medical images.To improve the model's learning ability, Besides, the attention mechanism module is introduced into the bottleneck layer to learn the long-range dependency of images.Experimental results on the lung CT dataset show that the model's Dice coefficient is 0.998, which is approximately 5% higher than that of the current segmentation model based on a convolutional neural network.In addition, this model greatly cuts the Hausdorff distance, apart from achieving higher segmentation accuracy and better robustness.

Key words: image segmentation, involution network, image processing, attention mechanism, U-Net network

中图分类号:

TP391

林志洁, 郑秋岚, 梁涌, 邢卫. 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 Zhijie, ZHENG Qiulan, LIANG Yong, XING Wei. Medical Image Segmentation Model Based on Involution U-Net[J]. Computer Engineering, 2022, 48(8): 180-186.

https://www.ecice06.com/CN/Y2022/V48/I8/180

图/表 6

20220825092515

20220825092523

20220825092527

20220825092531

20220825092534

20220825092538

参考文献

[1] DALCA A V, GUTTAG J, SABUNCU M R.Anatomical priors in convolutional networks for unsupervised biomedical segmentation[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:9290-9299.
[2] 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.
[3] LITJENS G, KOOI T, EHTESHAMI B B, et al.A survey on deep learning in medical image analysis[J].Medical Image Analysis, 2017, 42:60-88.
[4] GIRSHICK R.Fast R-CNN[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2015:1440-1448.
[5] ZHOU X Y, SHEN M, RIGA C, et al.Focal FCN:towards small object segmentation with limited training data.[EB/OL].[2021-06-06].https://arxiv.org/abs/1711.01506v2.
[6] JÉGOU S, DROZDZAL M, VAZQUEZ D, et al.The one hundred layers tiramisu:fully convolutional DenseNets for semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops.Washington D.C., USA:IEEE Press, 2017:1175-1183.
[7] 周岩, 周苑, 王旭辉.基于有限离散剪切波变换的灰度图像融合[J].计算机工程, 2016, 42(12):222-227. ZHOU Y, ZHOU Y, WANG X H.Grayscale image fusion based on finite discrete shearlet transform[J].Computer Engineering, 2016, 42(12):222-227.(in Chinese)
[8] 范九伦, 赵凤.灰度图像的二维Otsu曲线阈值分割法[J].电子学报, 2007, 35(4):751-755. FAN J L, ZHAO F.Two-dimensional Otsu's curve thresholding segmentation method for gray-level images[J].Acta Electronica Sinica, 2007, 35(4):751-755.(in Chinese)
[9] CHAN T, VESE L.An active contour model without edges[C]//Proceedings of Conference on Scale-Space Theories in Computer Vision.Berlin, Germany:Springer, 1999:141-151.
[10] MUMFORD D, SHAH J.Optimal approximations by piecewise smooth functions and associated variational problems[J].Communications on Pure and Applied Mathematics, 1989, 42(5):577-685.
[11] ZHENG Y L, CHEN K.A hierarchical algorithm for multiphase texture image segmentation[J].ISRN Signal Processing, 2012, 12:53-62.
[12] VESE L A, CHAN T F.A multiphase level set framework for image segmentation using the Mumford and shah model[J].International Journal of Computer Vision, 2002, 50(3):271-293.
[13] MORAR A, MOLDOVEANU F, GRÖLLER E.Image segmentation based on active contours without edges[C]//Proceedings of the 8th International Conference on Intelligent Computer Communication and Processing.Washington D.C., USA:IEEE Press, 2012:213-220.
[14] KRIZHEVSKY A, SUTSKEVER I, HINTON G E.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM, 2012, 60:84-90.
[15] SIMONYAN K, ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL].[2021-06-06].https://arxiv.org/abs/1409.1556.
[16] SZEGEDY C, LIU W, JIA Y Q, et al.Going deeper with convolutions[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2015:1-9.
[17] HUANG G, LIU Z, VAN DER MAATEN L, et al.Densely connected convolutional networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:2261-2269.
[18] COUPÉP, MANJÓN J V, FONOV V, et al.Patch-based segmentation using expert priors:application to hippocampus and ventricle segmentation[J].NeuroImage, 2011, 54(2):940-954.
[19] LI H M, YANG X, LIANG J M, et al.Contrastive rendering for ultrasound image segmentation[EB/OL].[2021-06-06].https://arxiv.org/abs/2010.04928.
[20] PÉREZ-GARCÍA F, RODIONOV R, ALIM-MARVASTI A, et al.Simulation of brain resection for cavity segmentation using self-supervised and semi-supervised learning[EB/OL].[2021-06-06].https://arxiv.org/abs/2006.15693.
[21] DING W B, LI L, ZHUANG X H, et al.Cross-modality multi-atlas segmentation using deep neural networks[C]//Proceedings of Medical Image Computing and Computer Assisted Intervention.Berlin, Germany:Springer, 2020:233-242.
[22] ALARIFS M M R, KNAPP K, SLABAUGH G.Shape-aware deep convolutional neural network for vertebrae segmentation[C]//Proceedings of Computational Methods and Clinical Applications in Musculoskeletal Imaging.Berlin, Germany:Springer, 2018:12-24.
[23] LIN T Y, GOYAL P, GIRSHICK R, et al.Focal loss for dense object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2):318-327.
[24] LI D, HU J, WANG C H, et al.Involution:inverting the inherence of convolution for visual recognition[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2021:12316-12325.
[25] CHEN X, WILLIAMS B M, VALLABHANENI S R, et al.Learning active contour models for medical image segmentation[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:11624-11632.
[26] BRESSON X, ESEDOḠLU S, VANDERGHEYNST P, et al.Fast global minimization of the active contour/snake model[J].Journal of Mathematical Imaging and Vision, 2007, 28(2):151-167.
[27] FANG S, LI K Y, LI Z.Salient positions based attention network for image classification[EB/OL].[2021-06-06].https://arxiv.org/abs/2106.04996.
[28] PEREIRA S, PINTO A, ALVES V, et al.Brain tumor segmentation using convolutional neural networks in MRI images[J].IEEE Transactions on Medical Imaging, 2016, 35(5):1240-1251.
[29] ZHENG Y L, CHEN K.A general model for multiphase texture segmentation and its applications to retinal image analysis[J].Biomedical Signal Processing and Control, 2013, 8(4):374-381.
[30] WOLTERINK J M, LEINER T, VIERGEVER M A, et al.Automatic segmentation and disease classification using cardiac cine MR images[EB/OL].[2021-06-06].https://link.springer.com/chapter/10.1007/978-3-319-75541-0_11.
[31] BAUMGARTNER C F, KOCH L M, POLLEFEYS M, et al.An exploration of 2D and 3D deep learning techniques for cardiac MR image segmentation[EB/OL].[2021-06-06].https://www.semanticscholar.org/paper/An-Exploration-of-2D-and-3D-Deep-Learning-for-MR-Baumgartner-Koch/68353b0cfa6cd44b5ff97ce957084b72bc84934c.
[32] YEONGGUL J, YOONMI H, SEONGMIN H, et al.Automatic segmentation of LV and RV in cardiac MRI[EB/OL].[2021-06-06].https://link.springer.com/chapter/10.1007/978-3-319-75541-0_17.
[33] FABIAN I, PAUL F J, PETER M F, etal.Automatic cardiac disease assessment on cine-mri via time-series segmentation and domain specific features[EB/OL].[2021-06-06].https://www.xueshufan.com/publication/2727040849.

选择文件类型/文献管理软件名称

选择包含的内容