RCAR-UNet：Retinal Vessels Segmentation Network Based on Rough Channel Attention Mechanism

Sun Ying; Ding Weiping; Huang Jiashuang; Ju Hengrong; Li Ming; Geng Yu

doi:10.7544/issn1000-1239.202110735

Journal of Computer Research and Development > 2023 > 60(4): 947-961. > DOI: 10.7544/issn1000-1239.202110735 CSTR: 32373.14.issn1000-1239.202110735

Sun Ying, Ding Weiping, Huang Jiashuang, Ju Hengrong, Li Ming, Geng Yu. RCAR-UNet：Retinal Vessels Segmentation Network Based on Rough Channel Attention Mechanism[J]. Journal of Computer Research and Development, 2023, 60(4): 947-961. DOI: 10.7544/issn1000-1239.202110735

Citation:

PDF (3618 KB)

RCAR-UNet：Retinal Vessels Segmentation Network Based on Rough Channel Attention Mechanism

School of Information Science and Technology, Nantong University, Nantong, Jiangsu 226019

Funds: This work was supported by the General Program of the National Natural Science Foundation of China (61976120), the National Natural Science Foundation of China for Young Scientists (62006128, 62102199), the Natural Science Foundation of Jiangsu Province (BK20191445), the Double-Creation Doctoral Program of Jiangsu Province, the Postgraduate Research & Practice Innovation Program of Jiangsu Province (SJCX20_1150), the Major Program of the Natural Science Research of Jiangsu Province Higher Education Institutions (21KJA510004), the General Program of the Natural Science Foundation of Jiangsu Province Higher Education Institutions (20KJB520009), the Basic Science Research Program of Nantong Science and Technology Bureau (JC2020141, JC2021122), and the Qing Lan Project of Jiangsu Province.

More Information

Author Bio:
Sun Ying: born in 1997. Master candidate. Her main research interests include granular computing, rough sets, and deep learning

Ding Weiping: born in 1979. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include data mining, machine learning, granular computing, evolutionary computing, and big data analytics

Huang Jiashuang: born in 1988. PhD, lecturer. His main research interests include brain network analysis and deep learning. （hjshdym@163.com）

Ju Hengrong: born in 1989. PhD, associate professor. His main research interests include granular computing, rough sets, machine learning, and knowledge discovery. （juhengrong@ntu.edu.cn）

Li Ming: born in 1996. Master candidate. His main research interests include data mining, granular computing, and big data analytics. （liming_2014@163.com）

Geng Yu: born in 1998. Master candidate. His main research interests include granular computing, machine learning, and deep learning. （tian19981999@163.com）
Received Date: July 05, 2021
Revised Date: June 22, 2022
Available Online: February 26, 2023

Graphical Abstract

Abstract

Abstract

The health of retinal vessels in fundus images is of great significance for the early diagnosis of various ophthalmic diseases and diabetic cardiovascular diseases, etc. However, the retinal blood vessels are delicate, distributed irregularly and the boundary is ambiguous. Therefore, it is difficult to accurately segment them. Based on the characteristics of retinal blood vessels, we propose a U-shaped network—rough channel attention residual U-Net (RCAR-UNet), which combines rough neurons and channel attention mechanism. Firstly, the network introduces the concept of upper and lower approximation in rough set theory to design rough neurons. Secondly, the rough channel attention module is constructed based on rough neurons, and the module uses global max pooling and global average pooling in U-Net skip connections to construct upper and lower approximation neurons, and performs weighted summation between neurons to reasonably rough the established channel dependencies, which not only contain global information but also have local characteristics, and can effectively achieve accurate rescaling of the extracted retinal vessels features. Then adding residual connections to transfer features directly from the lower to the higher layers, to help solve the network performance degradation problem and effectively extract richer retinal vascular features. Finally, in order to verify the effectiveness of the proposed RCAR-UNet model, comparison experiments are performed on three public fundus image datasets with traditional network models such as U-Net, Attention U-Net, etc. The results show that the RCAR-UNet model has high superiority in the accuracy, sensitivity and similarity of blood vessel segmentation.
- rough set,
- rough neuron,
- attention mechanism,
- fundus retinal blood vessels,
- image segmentation,
- residual connection

FullText(HTML)

References (42)

References

[1]	梁礼明,黄朝林,石霏,等. 融合形状先验的水平集眼底图像血管分割[J]. 计算机学报,2018,41(7):1678−1692 doi: 10.11897/SP.J.1016.2018.01678 Liang Liming, Huang Chaolin, Shi Fei, et al. Vessels segmentation of fundus images with level set fusion with shape priors[J]. Chinese Journal of Computers, 2018, 41(7): 1678−1692 (in Chinese) doi: 10.11897/SP.J.1016.2018.01678
[2]	Wu Yicheng, Xia Yong, Song Yang, et al. NFN+: A novel network followed network for retinal vessel segmentation[J]. Neural Networks, 2020, 126: 153−162 doi: 10.1016/j.neunet.2020.02.018
[3]	Li Xiang, Jiang Yuchen, Li Minglei, et al. Lightweight attention convolutional neural network for retinal vessel image segmentation[J]. IEEE Transactions on Industrial Informatics, 2021, 17(3): 1958−1967 doi: 10.1109/TII.2020.2993842
[4]	Cheung C Y, Xu Dejiang, Cheng Chingyun, et al. A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibre[J]. Nature Biomedical Engineering, 2021, 5(6): 498−508
[5]	Abràmoff M D, Garvin M K, Sonka M. Retinal imaging and image analysis[J]. IEEE Reviews in Biomedical Engineering, 2010, 3: 169−208 doi: 10.1109/RBME.2010.2084567
[6]	陈加,陈亚松,李伟浩,等. 深度学习在视频对象分割中的应用与展望[J]. 计算机学报,2021,44(3):609−631 doi: 10.11897/SP.J.1016.2021.00609 Chen Jia, Chen Yasong, Li Weihao, et al. Application and prospect of deep learning in video object segmentation[J]. Chinese Journal of Computers, 2021, 44(3): 609−631 (in Chinese) doi: 10.11897/SP.J.1016.2021.00609
[7]	Sun Liang, Shao Wei, Wang Mingliang, et al. High-order feature learning for multi-atlas based label fusion: Application to brain segmentation with MRI[J]. IEEE Transactions on Image Processing, 2019, 29: 2702−2713
[8]	Sun Liang, Shao Wei, Zhang Daoqiang, et al. Anatomical attention guided deep networks for ROI segmentation of brain MR images[J]. IEEE Transactions on Medical Imaging, 2019, 39(6): 2000−2012
[9]	Hesamian M H, Jia Wenjing, He Xiangjian, 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
[10]	Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(4): 640−651
[11]	Sun Jindong, Peng Yanjun, Guo Yanfei, et al. Segmentation of the multimodal brain tumor image used the multi-pathway architecture method based on 3D FCN[J]. Neurocomputing, 2021, 423: 34−45 doi: 10.1016/j.neucom.2020.10.031
[12]	Ding Henghui, Jiang Xudong, Shuai Bing, et al. Semantic segmentation with context encoding and multi-path decoding[J]. IEEE Transactions on Image Processing, 2020, 29: 3520−3533 doi: 10.1109/TIP.2019.2962685
[13]	Wu Congzhong, Sun Jun, Wang Jing, et al. Encoding-decoding network with pyramid self-attention module for retinal vessel segmentation[J]. International Journal of Automation and Computing, 2021, 18(6): 973−980 doi: 10.1007/s11633-020-1277-0
[14]	何慧,陈胜. 改进预训练编码器U-Net模型的PET肿瘤自动分割[J]. 中国图象图形学报,2020,25(1):171−179 doi: 10.11834/jig.190058 He Hui, Chen Sheng. Improved pretrained encoder U-Net model for automatic segmentation of PET tumors[J]. Chinese Journal of Image and Graphics, 2020, 25(1): 171−179 (in Chinese) doi: 10.11834/jig.190058
[15]	Rundo L, Han C, Nagano Y, et al. USE-Net: Incorporating squeeze-and-excitation blocks into U-Net for prostate zonal segmentation of multi-institutional MRI datasets[J]. Neurocomputing, 2019, 365: 31−43 doi: 10.1016/j.neucom.2019.07.006
[16]	Jin Qiangguo, Meng Zhaopeng, Pham T D, et al. DUNet: A deformable network for retinal vessel segmentation[J]. Knowledge-Based Systems, 2019, 178: 149−162 doi: 10.1016/j.knosys.2019.04.025
[17]	Basiri M E, Nemati S, Abdar M, et al. ABCDM: An attention-based bidirectional CNN-RNN deep model for sentiment analysis[J]. Future Generation Computer Systems, 2021, 115: 279−294 doi: 10.1016/j.future.2020.08.005
[18]	Haut J M, Paoletti M E, Plaza J, et al. Visual attention-driven hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(10): 8065−8080 doi: 10.1109/TGRS.2019.2918080
[19]	Guo Bangjun, He Xiuxiu, Lei Yang, et al. Automated left ventricular myocardium segmentation using 3D deeply supervised attention U-Net for coronary computed tomography angiography: CT myocardium segmentation[J]. Medical Physics, 2020, 47(4): 1775−1785 doi: 10.1002/mp.14066
[20]	Cui Hengfei, Yuwen Chang, Jiang Lei, et al. Multiscale attention guided U-Net architecture for cardiac segmentation in short-axis MRI images[J]. Computer Methods and Programs in Biomedicine, 2021, 206: 106142
[21]	Guo Changlu, Szemenyei M, Yi Yugen, et al. SA-UNet: Spatial attention U-Net for retinal vessel segmentation[C] //Proc of the 25th Int Conf on Pattern Recognition (ICPR2020). Piscataway, NJ: IEEE, 2021: 1236−1242
[22]	Tang Xianlun, Zhong Bing, Peng Jiangping, et al. Multi-scale channel importance sorting and spatial attention mechanism for retinal vessels segmentation[J]. Applied Soft Computing, 2020, 93: 106353
[23]	Gu Ran, Wang Guotian, Song Tao, et al. CA-Net: Comprehensive attention convolutional neural networks for explainable medical image segmentation[J]. IEEE Transactions on Medical Imaging, 2020, 40(2): 699−711
[24]	Mou Lei, Zhao Yitian, Chen Li, et al. CS-Net: Channel and spatial attention network for curvilinear structure segmentation[C] //Proc of the Int Conf on Medical Image Computing and Computer-Assisted Intervention. Berlin: Springer, 2019: 721−730
[25]	Pawlak Z. Rough sets[J]. International Journal of Computer and Information Sciences, 1982, 11(5): 341−356 doi: 10.1007/BF01001956
[26]	刘文,米据生,孙妍. 一种新的犹豫模糊粗糙近似算子的公理刻画[J]. 计算机研究与发展,2021,58(9):2062−2070 doi: 10.7544/issn1000-1239.2021.20200517 Liu Wen, Mi Jusheng, Sun Yan. Axiomatic characterization of new hesitant fuzzy rough approximation operators[J]. Journal of Computer Research and Development, 2021, 58(9): 2062−2070 (in Chinese) doi: 10.7544/issn1000-1239.2021.20200517
[27]	苗夺谦,徐菲菲,姚一豫,等. 粒计算的集合论描述[J]. 计算机学报,2012,35(2):2351−2363 Miao Duoqian, Xu Feifei, Yao Yiyu, et al. A set-theoretic description of granular computing[J]. Chinese Journal of Computers, 2012, 35(2): 2351−2363 (in Chinese)
[28]	Oktay O, Schlemper J, Folgoc L L, et al. Attention U-Net: Learning where to look for the pancreas[J]. arXiv preprint, arXiv: 1804.03999, 2018
[29]	Lingras P. Rough neural networks[C] //Proc of the 6th Int Conf on Information Processing and Management of Uncertainty in Knowledge Based Systems. Piscataway, NJ: IEEE, 1996: 1445 − 1450
[30]	Jelonek J, Krawiec K, Slowiński R. Rough set reduction of attributes, and their domains for neural networks[J]. Computational Intelligence, 1995, 11(2): 339−347 doi: 10.1111/j.1467-8640.1995.tb00036.x
[31]	Khodayar M, Kaynak O, Khodayar M E. Rough deep neural architecture for short-term wind speed forecasting[J]. IEEE Transactions on Industrial Informatics, 2017, 13(6): 2770−2779 doi: 10.1109/TII.2017.2730846
[32]	Cao Bin, Zhao Jianwei, Lv Zhihan, et al. Multiobjective evolution of fuzzy rough neural network via distributed parallelism for stock prediction[J]. IEEE Transactions on Fuzzy Systems, 2020, 28(5): 939−952 doi: 10.1109/TFUZZ.2020.2972207
[33]	Liao Hongmei, Ding Shifei, Wang Miaomiao, et al. An overview on rough neural networks[J]. Neural Computing and Applications, 2016, 27(7): 1805−1816 doi: 10.1007/s00521-015-2009-6
[34]	Jahangir H, Tayarani H, Baghali S, et al. A novel electricity price forecasting approach based on dimension reduction strategy and rough artificial neural networks[J]. IEEE Transactions on Industrial Informatics, 2019, 16(4): 2369−2381
[35]	Sabzalian M H, Mohammadzadeh A, Lin Shuyi, et al. A robust control of a class of induction motors using rough type-2 fuzzy neural networks[J]. Soft Computing, 2020, 24(13): 9809−9819 doi: 10.1007/s00500-019-04493-3
[36]	宁尚明,滕飞,李天瑞. 基于多通道自注意力机制的电子病历实体关系抽取[J]. 计算机学报,2020,43(5):916−929 doi: 10.11897/SP.J.1016.2020.00916 Ning Shangming, Teng Fei, Li Tianrui. Entity relation extraction from electronic medical records based on multi-channel self-attention mechanism[J]. Chinese Journal of Computers, 2020, 43(5): 916−929 (in Chinese) doi: 10.11897/SP.J.1016.2020.00916
[37]	陈勇,刘曦,刘焕淋. 基于特征通道和空间联合注意机制的遮挡行人检测方法[J]. 电子与信息学报,2020,42(6):1486−1493 doi: 10.11999/JEIT190606 Chen Yong, Liu Xi, Liu Huanlin. Occluded pedestrian detection method based on feature channel and spatial joint attention mechanism[J]. Journal of Electronics and Information, 2020, 42(6): 1486−1493 (in Chinese) doi: 10.11999/JEIT190606
[38]	Ma Jiayi, Zhang Hao, Yi Peng, et al. SCSCN: A separated channel-spatial convolution net with attention for single-view reconstruction[J]. IEEE Transactions on Industrial Electronics, 2019, 67(10): 8649−8658
[39]	宋杰,肖亮,练智超,等. 基于深度学习的数字病理图像分割综述与展望[J]. 软件学报,2021,32(5):1427−1460 doi: 10.13328/j.cnki.jos.006205 Song Jie, Xiao Liang, Lian Zhichao, et al. Review and prospect of digital pathology image segmentation based on deep learning[J]. Journal of Software, 2021, 32(5): 1427−1460 (in Chinese) doi: 10.13328/j.cnki.jos.006205
[40]	梁礼明,刘博文,杨海龙,等. 基于多特征融合的有监督视网膜血管提取[J]. 计算机学报,2018,41(11):2566−2580 doi: 10.11897/SP.J.1016.2018.02566 Liang Liming, Liu Bowen, Yang Hailong, et al. Supervised retinal vessel extraction based on multi-feature fusion[J]. Chinese Journal of Computers, 2018, 41(11): 2566−2580 (in Chinese) doi: 10.11897/SP.J.1016.2018.02566
[41]	Liskowski P, Krawiec K. Segmenting retinal blood vessels with deep neural networks[J]. IEEE Transactions on Medical Imaging, 2016, 35(11): 2369−2380 doi: 10.1109/TMI.2016.2546227
[42]	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 doi: 10.1109/TPAMI.2016.2644615

[1]	Wang Lina, Wang Kaige, Xu Yibo, Tang Benxiao, Tan Xuanze. An Evaluation of Carrier Security for Image Steganography Based on Residual Co-Occurrence Probability[J]. Journal of Computer Research and Development, 2018, 55(12): 2664-2673. DOI: 10.7544/issn1000-1239.2018.20170757
[2]	Long Jianwu, Shen Xuanjing, and Chen Haipeng. Interactive Document Images Thresholding Segmentation Algorithm Based on Image Regions[J]. Journal of Computer Research and Development, 2012, 49(7): 1420-1431.
[3]	Wen Qiaonong, Wan Suiren, Xu Shuang. Noise Image Segmentation Using Fisher Criterion and Regularization Level Set Method[J]. Journal of Computer Research and Development, 2012, 49(6): 1339-1347.
[4]	Zhu Feng, Luo Limin, Song Yuqing, Chen Jianmei, Zuo Xin. Adaptive Spatially Neighborhood Information Gaussian Mixture Model for Image Segmentation[J]. Journal of Computer Research and Development, 2011, 48(11): 2000-2007.
[5]	Chen Yunjie, Zhang Jianwei, Wang Shunfeng, Zhan Tianming. Brain MR Image Segmentation Based on Anisotropic Wells Model[J]. Journal of Computer Research and Development, 2010, 47(11): 1878-1885.
[6]	Che Na, Che Xiangjiu, Gao Zhanheng, and Wang Zhengxuan. Secondary Segmentation Algorithm for Magnetic Resonance Brain Image Based on Local Entropy Minimization[J]. Journal of Computer Research and Development, 2010, 47(7): 1294-1303.
[7]	Wang Wenhui, Feng Qianjin, Chen Wufan. Segmentation of Brain MR Images Based on the Measurement of Difference of Mutual Information and Gauss-Markov Random Field Model[J]. Journal of Computer Research and Development, 2009, 46(3): 521-527.
[8]	Shi Chunqi, Shi Zhiping, Liu Xi, Shi Zhongzhi. Image Segmentation Based on Self-Organizing Dynamic Neural Network[J]. Journal of Computer Research and Development, 2009, 46(1): 23-30.
[9]	Shi Chengxian, Wang Hongyuan, Heng Pheng Ann, Xia Deshen. A Parametric Active Contour Model for Medical Image Segmentation Using Priori Shape Force Field[J]. Journal of Computer Research and Development, 2006, 43(12): 2131-2137.
[10]	Zhang Jianwei, Xia Deshen. An Image Segmentation Model Based on Dual Level Sets[J]. Journal of Computer Research and Development, 2006, 43(1): 120-125.

Cited By

Cited by

Periodical cited type(12)

1.	丁卫平, 周喆, 周天奕. 模糊轴向注意力的多尺度视网膜血管分割网络. 闽南师范大学学报(自然科学版). 2025(02)
2.	张文豪，瞿绍军，颜美丽. 基于深度学习的视网膜血管分割研究进展. 计算机应用研究. 2025(05): 1299-1311 .
3.	秦涛，杜尚恒，常元元，王晨旭. ChatGPT的工作原理、关键技术及未来发展趋势. 西安交通大学学报. 2024(01): 1-12 .
4.	贺鑫，王晓燕，周启香，张文凯. 基于深度学习的眼底血管图像分割研究进展. 计算机系统应用. 2024(03): 12-23 .
5.	王海鹏，高自强，董佳俊，胡军，陈奕帆，丁卫平. 基于粗糙注意力融合机制与Group Transformer的视网膜血管分割网络. 南通大学学报(自然科学版). 2024(01): 28-37+48 .
6.	徐武，沈智方，范鑫豪，刘洋，徐天奇. 改进D-Linknet的眼底视网膜血管分割. 应用科技. 2024(02): 99-104+119 .
7.	张子旭，李嘉莹，栾鹏鹏，彭圆圆. 基于注意力机制的U-Net眼底图像分割算法. 计算机与现代化. 2024(05): 110-114 .
8.	符灵利，邱宇，张新晨. 基于改进U-Net多特征融合的血管分割. 计算机与现代化. 2024(06): 76-82 .
9.	窦全胜，李丙春，刘静，张家源. 基于多方向特征和连通性检测的眼底图像分割. 吉林大学学报(信息科学版). 2024(04): 690-699 .
10.	张文杰，宋艳涛，王克琪，张越. 基于自分块轻量化Transformer的医学图像分割网络. 计算机应用研究. 2024(11): 3502-3508 .
11.	徐光宪，冯春，马飞. 基于UNet的医学图像分割综述. 计算机科学与探索. 2023(08): 1776-1792 .
12.	梁礼明，阳渊，何安军，李仁杰. 跨级可变形Transformer编解码视网膜图像分割算法. 无线电工程. 2023(09): 1990-2001 .