基于深度学习的医学图像分割技术研究进展

doi:10.16180/j.cnki.issn1007-7820.2021.02.002

摘要/Abstract

摘要：

医学图像分割在临床诊断中发挥着重要作用,也是其他医学图像处理方法的基础。随着计算机硬件性能的提高,基于深度学习的图像分割技术已成为处理医学图像的有力工具,被广泛应用于各种医学图像分割任务中。文中介绍了常见的医学图像种类及其特点,对近些年涌现出的图像分割算法进行了分析和对比,部分算法已经成功应用到脑组织、肺部和血管等部位图像分割任务之中。文中还针对目前基于深度学习的医学图像分割技术在发展过程中所面临的问题给出了应对策略,并对今后的发展方向进行了展望。

关键词: 深度学习, 医学图像, 神经网络, 卷积运算, 分割算法, 图像处理

Abstract:

Medical image segmentation plays an important role in clinical diagnosis and is the basis of other medical image processing methods. With the improvement of computer hardware performance, image segmentation technology based on deep learning has already become a powerful tool for processing medical images and is widely used in various medical image segmentation tasks. This paper introduces several types of common medical images and their characteristics, analyzes and compares the image segmentation algorithms that have emerged in recent years. Some algorithms have been successfully applied to segmentation tasks such as brain tissue, lungs and blood vessels. In response to the current problems in the development of medical image segmentation technology based on deep learning, corresponding strategies are proposed, and the future development direction is also prospected.

Key words: deep learning, medical image, neural network, convolution operation, segmentation algorithm, image processing

中图分类号:

TP391.41

闫超,孙占全,田恩刚,赵杨洋,范小燕. 基于深度学习的医学图像分割技术研究进展[J]. 电子科技, 2021, 34(2): 7-11.

YAN Chao,SUN Zhanquan,TIAN Engang,ZHAO Yangyang,FAN Xiaoyan. Research Progress of Medical Image Segmentation Based on Deep Learning[J]. Electronic Science and Technology, 2021, 34(2): 7-11.

图/表 1

参考文献 32

[1]	康晓东. 医学影像图像处理[M]. 北京: 人民卫生出版社, 2009.
	Kang Xiaodong. Medical image processing[M]. Beijing: People's Medical Publishing House, 2009.
[2]	Mohammad H H, Jia W J, He X J, et al. Deep learning techniques for medical image segmentation: achievements and challenges[J]. Journal of Digital Imaging, 2019,32(4):582-596. doi: 10.1007/s10278-019-00227-x pmid: 31144149
[3]	刘宇, 陈胜. 医学图像分割方法综述[J]. 电子科技, 2017,30(8):169-172.
	Liu Yu, Chen Sheng. Review of medical image segmentation method[J]. Electronic Science and Technology, 2017,30(8):169-172.
[4]	Zhang L, Zhang Y. Big data analysis by infinite deep neural networks[J]. Journal of Computer Research and Development, 2016,53(1):68-79.
[5]	Shen D G, Wu G R, Suk H I. Deep learning in medical image analysis[J]. Annual Review of Biomedical Engineering, 2017,19(5):221-248.
[6]	He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition [C].Las Vegas: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016.
[7]	Prathiba M, Jose D, Saranya R, et al. Automated M-elanoma recognition in dermoscopy images via very deep residual networks [C].Coimbatore:Proceedings of the First International Conference on Materials Science and Manufacturing Technology, 2019.
[8]	Litjens G, Kooi T, Bejnordi B E, et al. A survey on deep learning in medical image analysis[J]. Medical Image Analysis, 2017,42(9):60-88. doi: 10.1016/j.media.2017.07.005
[9]	崔宝成. 浅析医学影像技术学-CT[J]. 世界最新医学信息文摘, 2015,15(72):111-112.
	Cui Baocheng. Analysis of medical imaging technology-CT[J]. World Latest Medical Information, 2015,15(72):111-112.
[10]	Niessen W J. MR brain image analysis in dementia: from quantitative imaging biomarkers to ageing brain models and imaging genetics[J]. Medical Image Analysis, 2016,33(12):107-113. doi: 10.1016/j.media.2016.06.029
[11]	Shi J, Zhou S C, Liu X, et al. Stacked deep polynomial network based representation learning for tumor classification with small ultrasound image dataset[J]. Neurocomputing, 2016,194(23):87-94. doi: 10.1016/j.neucom.2016.01.074
[12]	Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation [C].Boston:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015.
[13]	Krizhevsky A, Sutskever I, Hinton G E. ImageNet C-lassification with deep convolutional neural networks [C]. Lake Tahoe:Proceedings of the International Conference on Neural Information Processing Systems, 2012.
[14]	Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation[J]. Medical Image Computing and Computer-Assisted Intervention,, 2015,9351(65):234-241.
[15]	Milletari F, Navab N, Ahmadi S A. V-Net:fully convolutional neural networks for volumetric medical image segmentation [C].Palo Alto:Proceedings of the Fourth International Conference on 3D Vision, 2016.
[16]	Zhou Z W, Tajbakhsh N, Liang J M. U-Net plus plus:a nested U-Net architecture for medical image segmentation[C].Granada:The Eighth International Workshop on Multimodal Learning for Clinical Decision Support (ML-CDS), 2018.
[17]	Gu Z W, Cheng J, Fu H Z, et al. CE-Net:context encoder network for 2D medical image segmentation[J]. IEEE Transactions on Medical Imaging, 2019,38(10):2281-2292. doi: 10.1109/TMI.2019.2903562 pmid: 30843824
[18]	Noh H, Hong S, Han B. Learning deconvolution network for semantic segmentation [C].Santiago:IEEE International Conference on Computer Vision, 2015.
[19]	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(12):834-848.
[20]	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(18):2481-2495.
[21]	He K M, Zhang X Y, Ren S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015,37(9):1904-1916. doi: 10.1109/TPAMI.2015.2389824 pmid: 26353135
[22]	Cui Z P, Yang J, Qiao Y. Brain MRI segmentation with patch-based CNN approach [C].Chengdu: Proceedings of the Thirty-fifth Chinese Control Conference, 2016.
[23]	Moeskops P, Viergever M A, Mendrik A M, et al. Automatic segmentation of MR brain images with a convolutional neural network[J]. IEEE Transactions on Medical Imaging, 2016,35(5):1252-1262. doi: 10.1109/TMI.2016.2548501 pmid: 27046893
[24]	Zhang W L, Li R J, Deng H T, et al. Deep convolutional neural networks for multi-modality isointense infant brain image segmentation[J]. Neuro Image, 2015,108(25):214-224.
[25]	Nie D, Wang L, Lao C J, et al. 3-D fully convolutional networks for multimodal isointense infant brain image segmentation[J]. IEEE Transactions on Cybernetics, 2018,49(3):1123-1136. doi: 10.1109/TCYB.2018.2797905 pmid: 29994385
[26]	Cheng J Z, Ni D, Chou Y H, et al. Computer-aided diagnosis with deep learning architecture: applications to breast lesions in US images and pulmonary nodules in CT scans[J]. Scientific Reports, 2016,6(11):244-254.
[27]	Liauchuk V, Kovalev V, Kalinovsky A, et al. Examining the ability of convolutional neural networks to detect lesions in lung CT images [C].Barcelona:Medical Imaging and Augmented Reality:Computer Assisted Radiology and Surgery, 2017.
[28]	Zhou J H, Ginsberg M S, Metaxas D N, et al. Automatic detection and segmentation of ground glass opacity nodules [C].Heidelberg:Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention, 2006.
[29]	Nasr E E, Samavi S, Karimi N, et al. Vessel extraction in X-ray angiograms using deep learning[C].Orlando: Proceedings of the Thirty-eighth International Conference of the Engineering in Medicine and Biology Society(EMBC), 2016.
[30]	Wu A, Xu Z Y, Gao M C, et al. Deep vessel tracking: a generalized probabilistic approach via deep learning[C]. Prague:Proceedings of the Thirteenth International Symposium on Biomedical Imaging (ISBI), 2016.
[31]	Madabhushi A, Lee G. Image analysis and machine learning in digital pathology: challenges and opportunities[J]. Medical Image Analysis, 2016,33(6):170-175. doi: 10.1016/j.media.2016.06.037
[32]	Wang S L, Yin Y L, Cao G B, et al. Hierarchical retinal blood vessel segmentation based on feature and ensemble learning[J]. Neurocomputing, 2015,149(18):708-717. doi: 10.1016/j.neucom.2014.07.059

网络结构	功能特点	备注
FCN^[12]	密集性预测, 像素级分割	避免了因图像块重叠而导致的重复卷积计算
DeconvNet^[18]	设计了多个反卷积层和反池化层网络	解决了原始FCN网络中的尺寸问题,使物体的细节信息更为详尽
DeepLab^[19]	把卷积神经网络与传统概率图模型融合,并使用了空洞卷积。	在不进行池化的情况下扩大感受野,防止图像局部信息特征的丢失。
SegNet^[20]	提出了最大值池化索引方法	池化过程中丢失的信息可以通过最大值索引在解码阶段得到
PSPNet^[21]	提出金字塔模型提取图像多尺度信息特征	细节特征和全局特征的融合,极大地丰富了图像的语义信息。
U-net^[14]	采用跳跃拼接的编解码网络结构进行特征融合	影响深远,U-net网络被广泛地应用和改进。
V-net^[15]	采用3D 卷积和基于分割衡量指标DICE 系数作为目标函数	专为3D 医学图像分割而设计的改进版U-net网络
U-net++^[16]	把U-net网络结构各层连在一起	U-net网络结构的增强版本
CE-Net^[17]	将密集空洞卷积和多尺度池化相结合	在多种医学图像分割任务上效果显著