Multi-active contour cell segmentation method based on U-Net network

Zhu Linlin; Han Lu; Du Hong; Fan Huijie

doi:10.3788/IRLA20200121

Volume 49 Issue S1

Sep. 2020

Turn off MathJax

Article Contents

Article Navigation > Infrared and Laser Engineering > 2020 > 49(S1): 20200121

Zhu Linlin, Han Lu, Du Hong, Fan Huijie. Multi-active contour cell segmentation method based on U-Net network[J]. Infrared and Laser Engineering, 2020, 49(S1): 20200121. doi: 10.3788/IRLA20200121

Citation:

Zhu Linlin, Han Lu, Du Hong, Fan Huijie. Multi-active contour cell segmentation method based on U-Net network[J]. Infrared and Laser Engineering, 2020, 49(S1): 20200121. doi: 10.3788/IRLA20200121

Multi-active contour cell segmentation method based on U-Net network

doi: 10.3788/IRLA20200121

Zhu Linlin¹,
Han Lu¹,
Du Hong¹,
Fan Huijie^{2
,
,}

1. College of Automation, Shenyang Aerospace University, Shenyang 110135, China;
2. Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China

Received Date: 2020-05-11
Rev Recd Date: 2020-06-21
Publish Date: 2020-09-22

Abstract

Accurate segmentation of cells and nuclei is the key technology in computer-assisted diagnosis of cervical cancer. In this paper, a multi-active contour method, which was based on semantic segmentation of the U-Net model, was proposed for overlapping cells segmentation. First, each sample image was labeled as three parts:background, cell and cell nucleus. Then, the U-Net model was trained to segment the cervical images to obtain the cell and cell nucleus; meanwhile, the cell clump information could be obtained. The active contour for each cell was initialized according to the distance from the pixel point to the cell nucleus, and the energy functional was established based on shape prior of cells, the edge prior of images and the mutual prior between different contours. Finally, every single cell was segmented by minimizing the proposed energy functional. Experiment comparisons show that the segmentation method proposed in this paper can segment cervical cells under complex conditions, including independent cells, overlapping cells and their nuclei. The experimental results also prove the effectiveness of proposed method.
- cervical cells,
- active contour,
- level set,
- semantic segmentation,
- cell overlap

References

[1]	Brisson M, Kim J, Canfell K, et al. Impact of HPV vaccination and cervical screening on cervical cancer elimination:a comparative modelling analysis in 78 low-income and lower-middle-income countries[J]. Journal of Clinical Oncology, 2020, 38(4):10224.
[2]	Lin Sen, Liu Shiben, Tang Yandong. Multi-input fusion adversarial network for underwater image enhancement[J]. Infrared and Laser Engineering, 2020, 49(5):20200015. (in Chinese)林森, 刘世本, 唐延东. 多输入融合对抗网络的水下图像增强[J]. 红外与激光工程, 2020, 49(5):20200015.
[3]	Liu Dongmei, Chang Faliang. Active contour model for image segmentation based on Retinex correction and saliency[J]. Optics and Precision Engineering, 2019, 27(7):1593-1600. (in Chinese)刘冬梅,常发亮. 结合Retinex校正和显著性的主动轮廓图像分割[J]. 光学精密工程, 2019, 27(7):1593-1600.
[4]	Liu Cong, Dong Wenfei, Jiang Keming, et al. Recognition of dense fluorescent droplets using an improved watershed segmentation algorithm[J]. Chinese Optics, 2019, 12(4):783-790. (in Chinese)刘聪, 董文飞, 蒋克明, 等. 基于改进分水岭分割算法的致密荧光微滴识别[J]. 中国光学, 2019, 12(4):783-790.
[5]	Cao Haijie, Liu Ning, Xu Ji, et al. Infrared image adaptive inverse histogram enhancement technology[J]. Infrared and Laser Engineering, 2020, 49(4):0426003. (in Chinese)曹海杰, 刘宁, 许吉, 等. 红外图像自适应逆直方图增强技术[J]. 红外与激光工程, 2020, 49(4):0426003.
[6]	Zhao Zijuan, Zhao Juanjuan, Song Kai, et al. Joint DBN and Fuzzy C-Means unsupervised deep clustering for lung cancer patient stratification[J]. Elsevier Ltd, 2020, 91:103574.
[7]	Wang Chunzhe, An Junshe, Jiang Xiujie, et al. Region proposal optimization algorithm based on convolutional neural networks[J]. Chinese Optics, 2019, 12(6):1348-1361. (in Chinese)王春哲, 安军社, 姜秀杰, 等. 基于卷积神经网络的候选区域优化算法[J]. 中国光学, 2019, 12(6):1348-1361.
[8]	Yao P, Huaqiang W, Gao B, et al. Fully hardware-implemented memristor convolutional neural network[J]. Nature, 2020, 577(7792):641-646.
[9]	Lu J. P_Segnet and NP_Segnet:new neural network architectures for cloud recognition of remote sensing images[J]. IEEE Access, 2019, 7:87323-87333.
[10]	Ronneberger O, Fisccher P, Brox T. U-net:Convolutional networks for biomedicalimage segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention, 2015:234-241.
[11]	Chen Liangchieh, Papandreou George, Kokkinos Iasonas, 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.
[12]	Zuo L, Peilin H, Zhang C, et al. A robust approach to reading recognition of pointer meters based on improved Mask-RCNN[J]. Neurocomputing, 2020, 338:90-101.
[13]	Zhang L, Xu L. An automatic liver segmentation algorithm for CT images U-Net with separated paths of feature extraction[C]//2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC), 2018:94-298.
[14]	Ibtehaz N, Rahman S. MultiRes U-Net:Rethinking the U-Net architecture for multimodal biomedical image segmentation[J]. Neural Networks, 2020, 121:74-87.
[15]	Huang Y, Zhu H. Segmentation of overlapped cervical cells using asymmetric mixture model and shape constraint level set method[J]. Mathematical Problems in Engineering, 2020:1-14.
[16]	Ai L, Gao X L. Topology optimization of 2-D mechanical metamaterials using a parametric level set method combined with a meshfree algorithm[J]. Composite Structures, 2019, 229:111318.
[17]	Lu Z, Carneiro G, Bradley A P. An improved joint optimization of multiple level set functions for the segmentation of overlapping cervical cells[J]. IEEE Transactions on Image Processing, 2015, 24(4):1261-1272.
[18]	Caselles V, Kimmel R, Sapiro G. Geodesic active contours[J]. Int J Comput Vis, 1997, 22(1):61-79.
[19]	Li Xiaomao. Variation-based active contour image segmentation method[D]. Shenyang:Shenyang Institute of Automation, Chinese Academy of Sciences, 2008. (in Chinese)李小毛. 基于变分的主动轮廓图像分割方法[D]. 沈阳:中国科学院沈阳自动化研究所, 2008.
[20]	Wang X, Zhao X, Zhu Y, et al. An image segmentation algorithm based on NSST and the vector-valued C-V model[J]. IET Image Processing, 2020, 14(18):1614-1620.
[21]	Zhang Y, Zhao T, Yin Y, et al. Numerical research on energy evolution in granite under different confining pressures using Otsu's digital image processing and PFC2D[J]. Symmetry, 2019, 11(2):131.
[22]	Wang Jingjing, Liu Meir, Zhang Chunhui, et al. An adaptive sparse Bayesian model combined with probabilistic label fusion for multiple sclerosis lesion segmentation in brain MRI[J]. Elsevier B V, 2020, 105:695-704.
[23]	Ren Fenglei, He Xin, Wei Zhonghui, et al. Semantic segmentation based on DeepLabV³⁺ and superpixel optimization[J]. Optics and Precision Engineering, 2019, 27(12):2722-2729. (in Chinese)任凤雷, 何昕, 魏仲慧, 等. 基于DeepLabV³⁺与超像素优化的语义分割[J]. 光学精密工程, 2019, 27(12):2722-2729.

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Get Citation

PDF

XML

Article Metrics

Article views(361) PDF downloads(69) Cited by()

Proportional views

Multi-active contour cell segmentation method based on U-Net network

1. College of Automation, Shenyang Aerospace University, Shenyang 110135, China;

2. Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China

Received Date: 2020-05-11

Rev Recd Date: 2020-06-21

Publish Date: 2020-09-22

Key words:

Abstract: Accurate segmentation of cells and nuclei is the key technology in computer-assisted diagnosis of cervical cancer. In this paper, a multi-active contour method, which was based on semantic segmentation of the U-Net model, was proposed for overlapping cells segmentation. First, each sample image was labeled as three parts:background, cell and cell nucleus. Then, the U-Net model was trained to segment the cervical images to obtain the cell and cell nucleus; meanwhile, the cell clump information could be obtained. The active contour for each cell was initialized according to the distance from the pixel point to the cell nucleus, and the energy functional was established based on shape prior of cells, the edge prior of images and the mutual prior between different contours. Finally, every single cell was segmented by minimizing the proposed energy functional. Experiment comparisons show that the segmentation method proposed in this paper can segment cervical cells under complex conditions, including independent cells, overlapping cells and their nuclei. The experimental results also prove the effectiveness of proposed method.

HTML

Reference (23)

[1]	Brisson M, Kim J, Canfell K, et al. Impact of HPV vaccination and cervical screening on cervical cancer elimination:a comparative modelling analysis in 78 low-income and lower-middle-income countries[J]. Journal of Clinical Oncology, 2020, 38(4):10224.
[2]	Lin Sen, Liu Shiben, Tang Yandong. Multi-input fusion adversarial network for underwater image enhancement[J]. Infrared and Laser Engineering, 2020, 49(5):20200015. (in Chinese)林森, 刘世本, 唐延东. 多输入融合对抗网络的水下图像增强[J]. 红外与激光工程, 2020, 49(5):20200015.
[3]	Liu Dongmei, Chang Faliang. Active contour model for image segmentation based on Retinex correction and saliency[J]. Optics and Precision Engineering, 2019, 27(7):1593-1600. (in Chinese)刘冬梅,常发亮. 结合Retinex校正和显著性的主动轮廓图像分割[J]. 光学精密工程, 2019, 27(7):1593-1600.
[4]	Liu Cong, Dong Wenfei, Jiang Keming, et al. Recognition of dense fluorescent droplets using an improved watershed segmentation algorithm[J]. Chinese Optics, 2019, 12(4):783-790. (in Chinese)刘聪, 董文飞, 蒋克明, 等. 基于改进分水岭分割算法的致密荧光微滴识别[J]. 中国光学, 2019, 12(4):783-790.
[5]	Cao Haijie, Liu Ning, Xu Ji, et al. Infrared image adaptive inverse histogram enhancement technology[J]. Infrared and Laser Engineering, 2020, 49(4):0426003. (in Chinese)曹海杰, 刘宁, 许吉, 等. 红外图像自适应逆直方图增强技术[J]. 红外与激光工程, 2020, 49(4):0426003.
[6]	Zhao Zijuan, Zhao Juanjuan, Song Kai, et al. Joint DBN and Fuzzy C-Means unsupervised deep clustering for lung cancer patient stratification[J]. Elsevier Ltd, 2020, 91:103574.
[7]	Wang Chunzhe, An Junshe, Jiang Xiujie, et al. Region proposal optimization algorithm based on convolutional neural networks[J]. Chinese Optics, 2019, 12(6):1348-1361. (in Chinese)王春哲, 安军社, 姜秀杰, 等. 基于卷积神经网络的候选区域优化算法[J]. 中国光学, 2019, 12(6):1348-1361.
[8]	Yao P, Huaqiang W, Gao B, et al. Fully hardware-implemented memristor convolutional neural network[J]. Nature, 2020, 577(7792):641-646.
[9]	Lu J. P_Segnet and NP_Segnet:new neural network architectures for cloud recognition of remote sensing images[J]. IEEE Access, 2019, 7:87323-87333.
[10]	Ronneberger O, Fisccher P, Brox T. U-net:Convolutional networks for biomedicalimage segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention, 2015:234-241.
[11]	Chen Liangchieh, Papandreou George, Kokkinos Iasonas, 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.
[12]	Zuo L, Peilin H, Zhang C, et al. A robust approach to reading recognition of pointer meters based on improved Mask-RCNN[J]. Neurocomputing, 2020, 338:90-101.
[13]	Zhang L, Xu L. An automatic liver segmentation algorithm for CT images U-Net with separated paths of feature extraction[C]//2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC), 2018:94-298.
[14]	Ibtehaz N, Rahman S. MultiRes U-Net:Rethinking the U-Net architecture for multimodal biomedical image segmentation[J]. Neural Networks, 2020, 121:74-87.
[15]	Huang Y, Zhu H. Segmentation of overlapped cervical cells using asymmetric mixture model and shape constraint level set method[J]. Mathematical Problems in Engineering, 2020:1-14.
[16]	Ai L, Gao X L. Topology optimization of 2-D mechanical metamaterials using a parametric level set method combined with a meshfree algorithm[J]. Composite Structures, 2019, 229:111318.
[17]	Lu Z, Carneiro G, Bradley A P. An improved joint optimization of multiple level set functions for the segmentation of overlapping cervical cells[J]. IEEE Transactions on Image Processing, 2015, 24(4):1261-1272.
[18]	Caselles V, Kimmel R, Sapiro G. Geodesic active contours[J]. Int J Comput Vis, 1997, 22(1):61-79.
[19]	Li Xiaomao. Variation-based active contour image segmentation method[D]. Shenyang:Shenyang Institute of Automation, Chinese Academy of Sciences, 2008. (in Chinese)李小毛. 基于变分的主动轮廓图像分割方法[D]. 沈阳:中国科学院沈阳自动化研究所, 2008.
[20]	Wang X, Zhao X, Zhu Y, et al. An image segmentation algorithm based on NSST and the vector-valued C-V model[J]. IET Image Processing, 2020, 14(18):1614-1620.
[21]	Zhang Y, Zhao T, Yin Y, et al. Numerical research on energy evolution in granite under different confining pressures using Otsu's digital image processing and PFC2D[J]. Symmetry, 2019, 11(2):131.
[22]	Wang Jingjing, Liu Meir, Zhang Chunhui, et al. An adaptive sparse Bayesian model combined with probabilistic label fusion for multiple sclerosis lesion segmentation in brain MRI[J]. Elsevier B V, 2020, 105:695-704.
[23]	Ren Fenglei, He Xin, Wei Zhonghui, et al. Semantic segmentation based on DeepLabV³⁺ and superpixel optimization[J]. Optics and Precision Engineering, 2019, 27(12):2722-2729. (in Chinese)任凤雷, 何昕, 魏仲慧, 等. 基于DeepLabV³⁺与超像素优化的语义分割[J]. 光学精密工程, 2019, 27(12):2722-2729.

Multi-active contour cell segmentation method based on U-Net network

doi: 10.3788/IRLA20200121

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views