基于深度学习的医学图像分割方法研究进展

doi:10.16180/j.cnki.issn1007-7820.2024.01.011

Abstract

Abstract:

Medical image processing technology has developed rapidly with the rise of deep learning. The medical image segmentation technology based on deep learning has become the mainstream method in the segmentation field, which solves the shortcomings of the traditional segmentation method's insufficient segmentation accuracy. This technology has been maturely applied to the segmentation of some pathological images. This study introduces and compares the segmentation methods based on deep learning in recent years, and focuses on the major contributions of U-Net and its improved models in the segmentation field, and summarizes the common medical image modalities and evaluation indicators of segmentation algorithms and commonly used segmentation data sets. Finally, the future development of medical image segmentation technology is prospected.

Key words: medical image segmentation technology, deep learning, U-Net, segmentation algorithm, image processing, medical image modality, evaluation index, segmentation data set

CLC Number:

R318

LI Zenghui,WANG Wei. Research Progress of Medical Image Segmentation Method Based on Deep Learning[J].Electronic Science and Technology, 2024, 37(1): 72-80.

Figures/Tables 10

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 8.

Table 1.

Table 2.

References 54

[1]	Bigler E D. Neuroimaging as a biomarker in symptom validity and performance validity testing[J]. Brain Imaging and Behavior, 2015, 9(3):421-444. doi: 10.1007/s11682-015-9409-1 pmid: 26100657
[2]	Pun T. A new method for grey-level picture thresholding using the entropy of the histogram[J]. Signal Processing, 1980, 2(3):223-237. doi: 10.1016/0165-1684(80)90020-1
[3]	Khan J F, Bhuiyan S M A, Adhami R R. Image segmentation and shape analysis for road-sign detection[J]. IEEE Transactions on Intelligent Transportation Systems, 2010, 12(1):83-96. doi: 10.1109/TITS.2010.2073466
[4]	Tremeau A, Borel N. A region growing and merging algorithm to color segmentation[J]. Pattern Recognition, 1997, 30(7):1191-1203. doi: 10.1016/S0031-3203(96)00147-1
[5]	He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]. Shanghai: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:159-168.
[6]	Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[EB/OL].(2014-09-04)[2022-08-14]https://doi.org/10.48550/arXiv.1409.1556.
[7]	Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]. Boston: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015:307-316.
[8]	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, 2015:329-338.
[9]	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, 2017, 40(4):834-848. doi: 10.1109/TPAMI.2017.2699184
[10]	Chen L C, Papandreou G, Schroff F, et al. Rethinking atrous convolution for semantic image segmentation[EB/OL].(2016-06-17)[2022-08-14]https://doi.org/10.48550/arXiv.1706.05587.
[11]	Ronneberger O, Fischer P, Brox T. U-Net:Convolutional networks for biomedical image segmentation[C]. Madrid: International Conference on Medical Image Computing and Computer-assisted Intervention, 2015:98-105.
[12]	Zhou Z, Rahman S M, Tajbakhsh N, et al. UNet++:A nested U-Net architecture for medical image segmentation[M]. Shanghai: Springer, Cham, 2018:3-11.
[13]	Huang H, Lin L, Tong R, et al. UNet 3+:A full-scale connected unet for medical image segmentation[C]. Barcelona: ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing, 2020:497-506.
[14]	Ibtehaz N, Rahman M S. MultiResUNet:Rethinking the U-Net architecture for multimodal biomedical image segmentation[J]. Neural Networks, 2020, 18(6):74-87.
[15]	Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision[C]. Las Vegas: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:897-903.
[16]	Zhang Z, Liu Q, Wang Y. Road extraction by deep residual U-Net[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(5):749-753. doi: 10.1109/LGRS.2018.2802944
[17]	Kesavan S M, Al Naimi I, Al Attar F, et al. Res-UNet supported segmentation and evaluation of Covid-19 lesion in lung CT[C]. Puducherry: International Conference on System,Computation,Automation and Networking, 2021:633-640.
[18]	Liu Z, Yuan H. An Res-U Net method for pulmonary artery segmentation of CT images[C]. Shanghai:Journal of Physics: Conference Series, 2021:591-596.
[19]	Çiçek Ö, Abdulkadir A, Lienkamp S S, et al. 3D U-Net:Learning dense volumetric segmentation from sparse annotation[C]. Athens: International Conference on Medical Image Computing and Computer-Assisted Intervention, 2016:155-162.
[20]	Tong Q, Ning M, Si W, et al. 3D deeply-supervised U-Net based whole heart segmentation[C]. Hong Kong: International Workshop on Statistical Atlases and Computational Models of the Heart, 2017:602-609.
[21]	Wang C, Macgillivray T, Macnaught G, et al. A two-stage U-Net model for 3D multi-class segmentation on full-resolution cardiac data[C]. Shanghai: International Workshop on Statistical Atlases and Computational Models of the Heart, 2018:566-572.
[22]	Xu H, Xu Z, Gu W, et al. A two-stage fully automatic segmentation scheme using both 2D and 3D U-Net for multi-sequence cardiac MR[C]. Shanghai: International Workshop on Statistical Atlases and Computational Models of the Heart, 2019:981-990.
[23]	Zeng G, Wang Q, Lerch T, et al. Latent 3D U-Net: Multi-level latent shape space constrained 3D U-Net for automatic segmentation of the proximal femur from radial MRI of the hip[C]. Bern Switzerland: International Workshop on Machine Learning in Medical Imaging, 2018:1321-1337.
[24]	Wang C, Guo Y, Chen W, et al. Fully automatic intervertebral disc segmentation using multimodal 3D U-Net[C]. Shanghai: IEEE the Forty-third Annual Computer Software Apply Conference, 2019:506-512.
[25]	Mehta R, Arbel T. 3D U-Net for brain tum our segmentation[J]. MICCAI Brain Lesion Workshop, 2019, 17(6):643-646.
[26]	Owler J, Irving B, Ridgeway G, et al. Comparison of multi-atlas segmentation and U-Net approaches for automated 3D liver delineation in MRI[J]. Annual Conference on Medical Image Understanding and Analysis, 2019, 19(6):478-488.
[27]	Zhao C, Han J, Jia Y, et al. Lung nodule detection via 3D U-Net and contextual convolutional neural network[J]. International Conference on Networking and Network Applications, 2018, 20(7):356-361.
[28]	He Y, Yu X, Liu C, et al. A 3D dual path U-Net of cancer segmentation based on MRI[C]. Shanghai: IEEE the International Conference on Image,Vision and Computing, 2018:933-938.
[29]	Heinrich M P, Oktay O, Bouteldja N. OBELISK-Net: Fewer layers to solve 3D multi-organ segmentation with sparse deformable convolutions[J]. Medical Image Analysis, 2019, 10(7):1-9. doi: 10.1016/j.media.2005.11.001
[30]	Wang Y, Zhao L, Wang M, et al. Organ at risk segmentation in head and neck CT images using a two-stage segmentation framework based on 3D U-Net[J]. IEEE Access, 2019(5):144591-144602.
[31]	Li B, Vernooij M W, Ikram M A, et al. Reproducible white matter tract segmentation using 3D U-Net on a large-scale DTI dataset[J]. Workshop on Machine Learning in Medical Imaging, 2018, 8(3):205-213.
[32]	Feng X, Wang C, Cheng S, et al. Automatic liver and tumor segmentation of CT based on cascaded U-Net[J]. Chinese Intelligent System Conference, 2019, 9(4):155-164.
[33]	Liu Y, Qi N, Zhu Q, et al. CR-U-Net:Cascaded U-Net with residual mapping for liver segmentation in CT Images[J]. IEEE Visual Communications and Image Processing, 2019, 12(6):1-4.
[34]	Li H, Li A, Wang M. A novel end-to-end brain tumor segmentation method using improved fully convolutional networks[J]. Computers in Biology and Medicine, 2019, 18(9):150-160.
[35]	Vigneault D M, Xie W Ho C Y, et al. Ω-net(omega-net): Fully automatic,multi-view cardiac MR detection, orientation,and segmentation with deep neural networks[J]. Medical Image Analysis, 2018, 48(7): 95-106. doi: 10.1016/j.media.2018.05.008
[36]	Abd-Ellah M K, Khalaf A A, Awad A I, et al. TPUAR-Net: Two parallel U-Net with asymmetric residual-based deep convolutional neural network for brain tumor segmentation[J]. Journal of Image Analysis, 2019, 7(9):106-116.
[37]	Soltanpour M, Greiner R, Boulanger P, et al. Ischemic stroke lesion prediction in CT perfusion scans using multiple parallel U-Nets following by a pixel-level classifier[J]. IEEE the Nineteenth International Conference on Bioinformatics and Bioengineering, 2019, 16(7):957-963.
[38]	Zhang L, Xu L. An automatic liver segmentation algorithm for CT images U-Net with separated paths of feature extraction[C]. Tianjin: IEEE the Third International Conference Image, Vision Computing, 2018:294-298.
[39]	Huang G, Liu Z, Weinberger K Q. Densely connected convolutional networks[J]. IEEE Conference Computing Vision Pattern Recognit, 2017, 12(8):4700-4708.
[40]	Chen J, Lu Y, Yu Q, et al. Transunet:Transformers make strong encoders for medical image segmentation[EB/OL].(2021-02-08)[2022-08-14]https://doi.org/10.48550/arXiv.2102.04306.
[41]	Cao H, Wang Y, Chen J, et al. Swin-UNet:Unet-like pure transformer for medical image segmentation[EB/OL].(2021-05-12)[2022-08-14]https://doi.org/10.48550/arXiv.2105.05537.
[42]	Fu Z, Zhang J, Luo R, et al. TF-UNet:An automatic cardiac MRI image segmentation method[J]. Mathematical Biosciences and Engineering, 2022, 19(5):5207-5222. doi: 10.3934/mbe.2022244 pmid: 35430861
[43]	Zhao X, Wu Y, Song G, et al. A deep learning model integrating FCNNs and CRFs for brain tumor segmentation[J]. Medical Image Analysis, 2018, 12(6):98-111.
[44]	Lessmann N, Van Ginneken B, De Jong P A, et al. Iterative fully convolutional neural networks for automatic vertebra segmentation and identification[J]. Medical Image Analysis, 2019, 53(6):142-155. doi: 10.1016/j.media.2019.02.005
[45]	Tong N, Gou S, Yang S, 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. doi: 10.1002/mp.13147 pmid: 30136285
[46]	Roth H R, Shen C, Oda H, et al. Deep learning and its application to medical image segmentation[J]. Medical Imaging Technology, 2018, 36(2):63-71.
[47]	Jin Q, Meng Z, Sun C, et al. RA-UNet:A hybrid deep attention-aware network to extract liver and tumor in CT scans[J]. Frontiers in Bioengineering and Biotechnology, 2020, 15(9):1471-1480.
[48]	Lou A, Guan S, Loew M. DC-UNet:Rethinking the U-Net architecture with dual channel efficient CNN for medical image segmentation[C]. Sanya:Medical Imaging: Image Processing, 2021:59-68.
[49]	Xu G, Wu X, Zhang X, et al. Levit-Unet:Make faster encoders with transformer for medical image segmentation[EB/OL].(2021-07-19)[2022-08-14]https://doi.org/10.48550/arXiv.2107.08623.
[50]	Guo C, Szemenyei M, Yi Y, et al. SA-UNet:Spatial attention U-net for retinal vessel segmentation[C]. Milan: The Twenty-fifth International Conference on Pattern Recognition,IEEE, 2021:483-490.
[51]	Sinha A, Dolz J. Multi-scale self-guided attention for medical image segmentation[J]. IEEE Journal of Biomedical and Health Informatics, 2020, 25(1):121-130. doi: 10.1109/JBHI.6221020
[52]	Kamnitsas K, Ledig C, Newcombe V F J, et al. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation[J]. Medical Image Analysis, 2017, 36(3):61-78. doi: 10.1016/j.media.2016.10.004
[53]	Thoma M. A survey of semantic segmentation[EB/OL].(2016-02-21)[2022-08-14]https://doi.org/10.48550/arXiv.1602.06541.
[54]	Kim Y J, Jang H, Lee K, et al. PAIP 2019:Liver cancer segmentation challenge[J]. Medical Image Analysis, 2021, 67(5):101854-101860. doi: 10.1016/j.media.2020.101854

方法	特点	优点	缺点
FCN	用卷积替换全连接,引入跳跃连接	可输入任意尺寸的图片,高层特征与低层特征进行融合	没有充分利用全局上下文信息, 分割精度不足
DeepLab-V1	先用空洞卷积进行特征提取, 再全连接CRF 优化	通过扩大感受野,来提取更多的特征	深度卷积神经网络会导致空间分辨率下降,且需要很大的存储空间
DeepLab-V2	引入多尺度空间金字塔池化	同上	分割细节不足
DeepLab-V3	改进了旧版空洞卷积和多尺度空间金字塔池化	同上	输出图的放大效果较差
U-Net	在卷积网络的基础上加入对称的解码网络	更好的利用全局上下文信息, 对低层和高层信息进行有效融合	物体边界的分割粗糙
U-Net++	改进U-Net的跳跃连接	提高了分割精度,缩减了参数量	训练数据冗余, 占用显存多
U-Net3+	改进跳跃连接	同上	网络结构复杂, 参数量大
MultiResUnet	引入残差学习	减缓了梯度消失和梯度爆炸	增加了网络的训练时间
Attention U-Net	引入注意力机制	灵活捕获全局特征与局部特征的联系	网络的深层信息可能被破坏,从而影响模型的学习能力
3D U-Net	对图像进行三维分割	能直接分割三维医学图像	参数量大、训练时间长
Cascaded 3D U-Net	多阶段分割	对小目标的检测效果良好	增加了额外的计算成本
TransUNet	把Transformer 与U-Net融合	通过恢复局部空间信息来增强细节	所需数据量较大
Swin U-Net	使用移位窗口的Swin Trans- former作编码器提取特征	有良好的分割精度和鲁棒的泛化能力	直接使用Swin Transformer的训练权重来初始化网络,会影响模型的性能

部位	成像方式	名称	大小	格式	区域	地址
大脑	MRI	BraTs 2018	285	NIFIT	胶质瘤	https://aistudio.baidu.com/aistudio/datasetdetail/64660
膝盖	MRI	MRNET	60	NIFIT	骨骼和软骨	https://stanfordmlgroup.github.io/competitions/mrnet/
眼	视网膜图像	DRIVE	40	JPEG	视网膜血管	https://gitee.com/zongfang/retina-unet
		CHASE_ DB1	1 200	JPEG	病理性近视血管病变	https://blogs.kingston.ac.uk/retinal/chasedb1/
		STARE	20	JPEG	病理性近视血管病变	https://blogs.kingston.ac.uk/retinal/chasedb1/
		STARE	20	JPEG	同上	https://cecas.clemson.edu/~ahoover/stare/
腹部	CT	CHAOS	40	DICOM	肝脏和血管	https://zenodo.org/record/3431873#.Y0ABL3ZBxPZ
腹部	MRI	CHAOS	120	DICOM	肝脏和血管	https://zenodo.org/record/3431873#.Y0ABL3ZBxPZ
胸部	胸部 X光	SIIM- ACR	-	DICOM	气胸	https://www.kaggle.com/c/siim-acr-pneumothorax-segmentation
		SCR	247	JPEG	心脏和肺	http://www.isi.uu.nl/Research/Databases/ SCR/
	CT	Seg THOR	60	-	心脏和肺	https://github.com/FEanglang/SegTHOR- Pytorch
肾	CT	KiTS 19	300	NIFTI	肾肿瘤	https://github.com/neheller/kits19
肝	WSI CT	PAIP^[54]	50	-	肝癌肿瘤	-
肺	CT	Luna	888	Meta Image	肺结核分割	https://pan.baidu.com/s/1BJIBqu3q GZeXj9Vm_xftGQ 提取码:r6Ba

Research Progress of Medical Image Segmentation Method Based on Deep Learning

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 54

Related Articles 15

Metrics

Comments

Recommended 0

[1]	YU Zhihong,LI Feifei. Semi-Supervised Medical Image Segmentation Method Based on Meta-Learning and Neural Architecture Search [J]. Electronic Science and Technology, 2024, 37(1): 17-23.
[2]	WANG Jiawei,YU Xiao. Review of Text Classification Research Based on Deep Learning [J]. Electronic Science and Technology, 2024, 37(1): 81-86.
[3]	HUANG Zixuan,LI Qiaoxing. Research on Identification of Urban Illegal Vehicles Based on Random Forest Model [J]. Electronic Science and Technology, 2024, 37(1): 66-71.
[4]	Bin ,WANG Sen. Visual Detection of Structural Cracks Using Depth Deformable Contour ModelLAI [J]. Electronic Science and Technology, 2023, 36(9): 35-40.
[5]	CAO Hongfang,WANG Xiaolei,DU Gaoming,LI Zhenmin,NI Wei. Design and FPGA Implementation of Dehazing Based on Channel Difference Model and Guided Filtering [J]. Electronic Science and Technology, 2023, 36(8): 1-6.
[6]	SUN Hong,ZHAO Yingzhi. Lightweight Generative Adversarial Networks Based on Multi-Scale Gradient [J]. Electronic Science and Technology, 2023, 36(7): 32-38.
[7]	ZENG Xinxin,ZHANG Hongyan. A Farmland Parcel Extraction Network Based on Multi-Scale Semantic Information Enhancement [J]. Electronic Science and Technology, 2023, 36(7): 70-74.
[8]	GUO Qicheng,SHEN Tuo,ZHANG Xuanxiong. Recognition Method of the Combined Trackside Signal Light Based on Image Processing [J]. Electronic Science and Technology, 2023, 36(7): 8-15.
[9]	YUAN Zhenbo,BAI Bo,ZHANG Xiaowei,LUO Liujun,SHANG Tao. Automatic Alignment System for Visible Light Communication Based on Image Processing [J]. Electronic Science and Technology, 2023, 36(6): 8-15.
[10]	LI Keran,CHEN Sheng,KE Panpan. A Method of Facial Mask Segmentation Based on CA-Net [J]. Electronic Science and Technology, 2023, 36(6): 64-71.
[11]	SHI Jianke,QIAO Meiying,LI Bingfeng,ZHAO Yan. Underwater Occlusion Target Detection Algorithm Based on Attention Mechanism [J]. Electronic Science and Technology, 2023, 36(5): 62-70.
[12]	LIU Yuwei,CAO Min,FENG Haojia. CNAS Recognition Criteria Automatic Benchmarking System Based on Natural Language Processing [J]. Electronic Science and Technology, 2023, 36(5): 28-33.
[13]	ZHENG Yuheng,FU Dongxiang. UAV Detection Based on Slim-YOLOv4 with Embedded Device [J]. Electronic Science and Technology, 2023, 36(5): 55-61.
[14]	LUO Ruipeng,FENG Mingke,HUANG Xin,ZOU Renling,LI Dan. A Review of Research on EEG Signal Preprocessing Methods [J]. Electronic Science and Technology, 2023, 36(4): 36-43.
[15]	CUI Zhuodong,CHEN Wei,YIN Zhong. Helmet Wearing Detection Based on Enhanced Feature Fusion Network [J]. Electronic Science and Technology, 2023, 36(4): 44-51.