MIC-Net: multi-scale integrated context network for automatic retinal vessel segmentation in fundus image

Jinke Wang; Lubiao Zhou; Zhongzheng Yuan; Haiying Wang; Changfa Shi; Jinke Wang; Lubiao Zhou; Zhongzheng Yuan; Haiying Wang; Changfa Shi

doi:10.3934/mbe.2023298

Mathematical Biosciences and Engineering

2023, Volume 20, Issue 4: 6912-6931. doi: 10.3934/mbe.2023298

Previous Article Next Article

Research article Special Issues

MIC-Net: multi-scale integrated context network for automatic retinal vessel segmentation in fundus image

1.
Department of Software Engineering, Harbin University of Science and Technology, Rongcheng 264300, China
2.
School of Automation, Harbin University of Science and Technology, Harbin 150080, China
3.
Mobile E-business Collaborative Innovation Center of Hunan Province, Hunan University of Technology and Business, Changsha 410205, China

Academic Editor: Simon James Fong

Received: 08 October 2022 Revised: 28 January 2023 Accepted: 31 January 2023 Published: 08 February 2023

Purpose
Accurate retinal vessel segmentation is of great value in the auxiliary screening of various diseases. However, due to the low contrast between the ends of the branches of the fundus blood vessels and the background, and the variable morphology of the optic disc and cup in the retinal image, the task of high-precision retinal blood vessel segmentation still faces difficulties.
Method
This paper proposes a multi-scale integrated context network, MIC-Net, which fully fuses the encoder-decoder features, and extracts multi-scale information. First, a hybrid stride sampling (HSS) block was designed in the encoder to minimize the loss of helpful information caused by the downsampling operation. Second, a dense hybrid dilated convolution (DHDC) was employed in the connection layer. On the premise of preserving feature resolution, it can perceive richer contextual information. Third, a squeeze-and-excitation with residual connections (SERC) was introduced in the decoder to adjust the channel attention adaptively. Finally, we utilized a multi-layer feature fusion mechanism in the skip connection part, which enables the network to consider both low-level details and high-level semantic information.
Results
We evaluated the proposed method on three public datasets DRIVE, STARE and CHASE. In the experimental results, the Area under the receiver operating characteristic (ROC) and the accuracy rate (Acc) achieved high performances of 98.62%/97.02%, 98.60%/97.76% and 98.73%/97.38%, respectively.
Conclusions
Experimental results show that the proposed method can obtain comparable segmentation performance compared with the state-of-the-art (SOTA) methods. Specifically, the proposed method can effectively reduce the small blood vessel segmentation error, thus proving it a promising tool for auxiliary diagnosis of ophthalmic diseases.
- retinal vessel segmentation,
- fundus image,
- multi-scale,
- deep learning
Citation: Jinke Wang, Lubiao Zhou, Zhongzheng Yuan, Haiying Wang, Changfa Shi. MIC-Net: multi-scale integrated context network for automatic retinal vessel segmentation in fundus image[J]. Mathematical Biosciences and Engineering, 2023, 20(4): 6912-6931. doi: 10.3934/mbe.2023298

Related Papers:

Abstract

Purpose

Accurate retinal vessel segmentation is of great value in the auxiliary screening of various diseases. However, due to the low contrast between the ends of the branches of the fundus blood vessels and the background, and the variable morphology of the optic disc and cup in the retinal image, the task of high-precision retinal blood vessel segmentation still faces difficulties.

Method

This paper proposes a multi-scale integrated context network, MIC-Net, which fully fuses the encoder-decoder features, and extracts multi-scale information. First, a hybrid stride sampling (HSS) block was designed in the encoder to minimize the loss of helpful information caused by the downsampling operation. Second, a dense hybrid dilated convolution (DHDC) was employed in the connection layer. On the premise of preserving feature resolution, it can perceive richer contextual information. Third, a squeeze-and-excitation with residual connections (SERC) was introduced in the decoder to adjust the channel attention adaptively. Finally, we utilized a multi-layer feature fusion mechanism in the skip connection part, which enables the network to consider both low-level details and high-level semantic information.

Results

We evaluated the proposed method on three public datasets DRIVE, STARE and CHASE. In the experimental results, the Area under the receiver operating characteristic (ROC) and the accuracy rate (Acc) achieved high performances of 98.62%/97.02%, 98.60%/97.76% and 98.73%/97.38%, respectively.

Conclusions

Experimental results show that the proposed method can obtain comparable segmentation performance compared with the state-of-the-art (SOTA) methods. Specifically, the proposed method can effectively reduce the small blood vessel segmentation error, thus proving it a promising tool for auxiliary diagnosis of ophthalmic diseases.

References

[1]	S. Chaudhuri, S. Chatterjee, N. Katz, M. Nelson, M. Goldbaum, Detection of blood vessels in retinal images using two-dimensional matched filters, IEEE Trans. Med. Imaging, 8 (1989), 263–269. https://doi.org/10.1109/42.34715 doi: 10.1109/42.34715
[2]	Q. Li, J. You, D. Zhang, Vessel segmentation and width estimation in retinal images using multiscale production of matched filter responses, Expert Syst. Appl., 39 (2012), 7600–7610. https://doi.org/10.1016/j.eswa.2011.12.046 doi: 10.1016/j.eswa.2011.12.046
[3]	K. S. Sreejini, V. K. Govindan, Improved multiscale matched filter for retina vessel segmentation using PSO algorithm, Egypt. Inform. J.l, 16 (2015), 253–260. https://doi.org/10.1016/j.eij.2015.06.004 doi: 10.1016/j.eij.2015.06.004
[4]	A. M. Aibinu, M. I. Iqbal, A. A. Shafie, M. J.E. Salami, M. Nilsson, Vascular intersection detection in retina fundus images using a new hybrid approach, Comput. Biol. Med., 40 (2009), 81–89. https://doi.org/10.1016/j.compbiomed.2009.11.004 doi: 10.1016/j.compbiomed.2009.11.004
[5]	M. Vlachos, E. Dermatas, Multi-scale retinal vessel segmentation using line tracking, Comput. Med. Imaging Graphics, 34 (2010), 213–227. https://doi.org/10.1016/j.compmedimag.2009.09.006 doi: 10.1016/j.compmedimag.2009.09.006
[6]	F. Zana, J. C. Klein, Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation, IEEE Trans. Image Process., 10 (2001), 1010–1019. https://doi.org/10.1109/83.931095 doi: 10.1109/83.931095
[7]	M. M. Fraz, S. A. Barman, P. Remagnino, A. Hoppe, A. Basit, B. Uyyanonvara, et al., An approach to localize the retinal blood vessels using bit planes and centerline detection, Comput. Methods Programs Biomed., 108 (2012), 600–616. https://doi.org/10.1016/j.cmpb.2011.08.009 doi: 10.1016/j.cmpb.2011.08.009
[8]	Y. Yang, S. Y. Huang, N. N. Rao, An automatic hybrid method for retinal blood vessel extraction, Int. J. Appl. Math. Comput. Sci., 18 (2008), 399–407. https://doi.org/10.2478/v10006-008-0036-5 doi: 10.2478/v10006-008-0036-5
[9]	J. Staal, M. D. Abràmoff, M. Niemeijer, M. A. Viergever, B. V. Ginneken, Ridge-based vessel segmentation in color images of the retina, IEEE Trans. Med. Imaging, 23 (2004), 501–509. https://doi.org/10.1109/TMI.2004.825627 doi: 10.1109/TMI.2004.825627
[10]	J. V. B. Soares, J. J. G. Leandro, R. M. Cesar, H. F. Jelinek, M. J. Cree, Retinal vessel segmentation using the 2-D Morlet wavelet and supervised classification, IEEE Trans. Med. Image, 25 (2006). https://doi.org/10.1109/TMI.2006.879967. doi: 10.1109/TMI.2006.879967
[11]	A. Osareh, B. Shadgar, Automatic blood vessel segmentation in color images of retina, Iran. J. Sci. Technol., 33 (2009), 191–206.
[12]	S. A. Khowaja, P. Khuwaja, I. A. Ismaili, A framework for retinal vessel segmentation from fundus images using hybrid feature set and hierarchical classification, Signal Image Video Process., 13 (2019), 379–387. https://doi.org/10.1007/s11760-018-1366-x doi: 10.1007/s11760-018-1366-x
[13]	O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, in International Conference on Medical image computing and computer-assisted intervention, (2015), 234–241. https://doi.org/10.48550/arXiv.1505.04597
[14]	Y. Wu, Y. Xia, Y. Song, Y. Zhang, W. Cai, Multi-scale network followed network model for retinal vessel segmentation, in International conference on medical image computing and computer-assisted intervention, (2018), 119–126. https://doi.org/10.1007/978-3-030-00934-2_14
[15]	J. Zhuang, LadderNet: Multi-path networks based on U-Net for medical image segmentation, preprint, arXiv: 1810.07810.
[16]	M. Z. Alom, C. Yakopcic, M. Hasan, T. M. Taha, V. K. Asari, Recurrent residual U-Net for medical image segmentation, J. Med. Imaging, 6 (2019). https://doi.org/10.1117/1.JMI.6.1.014006 doi: 10.1117/1.JMI.6.1.014006
[17]	L. Li, M. Verma, Y. Nakashima, H. Nagahara, R. Kawasaki, Iternet: Retinal image segmentation utilizing structural redundancy in vessel networks, in Proceedings of the IEEE/CVF winter conference on applications of computer vision, (2020), 3656–3665. https://doi.org/10.48550/arXiv.1912.05763
[18]	Z. Gu, J. Cheng, H. Fu, K. Zhou, H. Hao, Y. Zhao, et al., Ce-net: Context encoder network for 2d medical image segmentation, IEEE Trans. Med. Imaging, 38 (2019), 2281–2292. https://doi.org/10.1109/TMI.2019.2903562 doi: 10.1109/TMI.2019.2903562
[19]	Z. F. Lin, J. P. Huang, Y. Y Chen, X. Zhang, W. Zhao, Y. Li, et al., A high resolution representation network with multi-path scale for retinal vessel segmentation, Comput. Methods Programs Biomed., 208 (2021). https://doi.org/10.1016/j.cmpb.2021.106206 doi: 10.1016/j.cmpb.2021.106206
[20]	Q. Jin, Z. Meng, T. D. Pham, Q. Chen, L. Wei, R. Su, DUNet: A deformable network for retinal vessel segmentation, Knowl. Based Syst., 178 (2019), 149–162. https://doi.org/10.1016/j.knosys.2019.04.025 doi: 10.1016/j.knosys.2019.04.025
[21]	Z. Wang, J. Lin, R. Wang, W. Zheng, Data augmentation is more important than model architectures for retinal vessel segmentation. in Proceedings of the 2019 International Conference on Intelligent Medicine and Health, (2019), 48–52. https://doi.org/10.1145/3348416.3348425
[22]	Y. Wu, Y. Xia, Y. Song, Y. Zhang, W. Cai, NFN+: a novel network followed network for retinal vessel segmentation, Neural Networks, 126 (2020), 153–162. https://doi.org/10.1016/j.neunet.2020.02.018 doi: 10.1016/j.neunet.2020.02.018
[23]	M. Yang, K. Yu, C. Zhang, Z. Li, K. Yang, Denseaspp for semantic segmentation in street scenes, in Proceedings of the IEEE conference on computer vision and pattern recognition, (2018), 3684–3692. https://doi.org/10.1109/cvpr.2018.00388
[24]	G. Azzopardi, N. Strisciuglio, M. Vento, N. Petkov, Trainable COSFIRE filters for vessel delineation with application to retinal images, Med. image Anal., 19 (2015), 46–57. https://doi.org/10.1016/j.media.2014.08.002 doi: 10.1016/j.media.2014.08.002
[25]	Q. Li, B. Feng, L. Xie, P. Liang, H. Zhang, T. Wang, A cross-modality learning approach for vessel segmentation in retinal images, IEEE Trans. Med. Imaging, 35 (2015), 109–118. https://doi.org/10.1109/TMI.2015.2457891 doi: 10.1109/TMI.2015.2457891
[26]	P. Liskowski, K. Krawiec, Segmenting retinal blood vessels with deep neural networks, IEEE Trans. Med. Imaging, 35 (2016), 2369–2380. https://doi.org/10.1109/TMI.2016.2546227 doi: 10.1109/TMI.2016.2546227
[27]	H. Z. Fu, Y. W. Xu, S. Lin. D.W.K.Wong, J. Liu, Deepvessel: Retinal vessel segmentation via deep learning and conditional random field, in International conference on medical image computing and computer-assisted intervention, (2016), 132–139. https://doi.org/10.1007/978-3-319-46723-8_16
[28]	A. Dasgupta, S. Singh, A fully convolutional neural network based structured prediction approach towards the retinal vessel segmentation, in 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), (2017), 248–251. https://doi.org/10.1109/ISBI.2017.7950512
[29]	Y. Chen, A labeling-free approach to supervising deep neural networks for retinal blood vessel segmentation, preprint, arXiv: 1704.07502.
[30]	Z. Yan, X. Yang, K. T. Cheng, Joint segment-level and pixel-wise losses for deep learning based retinal vessel segmentation, IEEE Trans. Biomed. Eng., 65 (2018), 1912–1923. https://doi.org/10.1109/TBME.2018.2828137 doi: 10.1109/TBME.2018.2828137
[31]	Z. Yan, X. Yang, K. T. Cheng, A three-stage deep learning model for accurate retinal vessel segmentation, IEEE J. Biomed. Health Inform., 23 (2018), 1427–1436. https://doi.org/10.1109/JBHI.2018.2872813 doi: 10.1109/JBHI.2018.2872813
[32]	D. Wang, A. Haytham, J. Pottenburgh, O. Saeedi, Y. Tao, Hard attention net for automatic retinal vessel segmentation, IEEE J. Biomed. Health Inform., 24 (2020), 3384–3396. https://doi.org/10.1109/JBHI.2020.3002985 doi: 10.1109/JBHI.2020.3002985
[33]	Z. Shi, T. Wang, Z. Huang, F. Xie, Z. Liu, B. Wang, et al., MD-Net: A multi-scale dense network for retinal vessel segmentation, Biomed. Signal Process. Control, 70 (2021), 102977. https://doi.org/10.1016/j.bspc.2021.102977 doi: 10.1016/j.bspc.2021.102977
[34]	F. Guo, W. Li, Z. Kuang, J. Tang, MES-Net: A new network for retinal image segmentation, Multimedia Tools Appl., 80 (2021), 14767–14788. https://doi.org/10.1007/s11042-021-10580-1 doi: 10.1007/s11042-021-10580-1
[35]	Y. Xu, Y. Fan, Dual-channel asymmetric convolutional neural network for an efficient retinal blood vessel segmentation in eye fundus images, Biocybern. Biomed. Eng., 42 (2022), 695–706. https://doi.org/10.1016/J.BBE.2022.05.003 doi: 10.1016/J.BBE.2022.05.003
[36]	Y. Zhang, J. Fang, Y. Chen, L. Jia, Edge-aware U-net with gated convolution for retinal vessel segmentation, Biomed. Signal Process. Control, 73 (2022), 103472. https://doi.org/10.1016/j.bspc.2021.103472 doi: 10.1016/j.bspc.2021.103472
[37]	X. Deng, J. Ye, A retinal blood vessel segmentation based on improved D-MNet and pulse-coupled neural network, Biomed. Signal Process. Control, 73 (2022), 103467. https://doi.org/10.1016/j.bspc.2021.103467 doi: 10.1016/j.bspc.2021.103467
[38]	A. G. Roy, N. Navab, C. Wachinger, Concurrent spatial and channel' squeeze & excitation'in fully convolutional networks, in International conference on medical image computing and computer-assisted intervention, (2018), 421–429. https://doi.org/10.1007/978-3-030-00928-1_48
[39]	D. X. Yang, H. D. Zhao, T. H. Han, Learning feature-rich integrated comprehensive context networks for automated fundus retinal vessel analysis, Neurocomputing, 491 (2022), 132–143. https://doi.org/10.1016/J.NEUCOM.2022.03.061 doi: 10.1016/J.NEUCOM.2022.03.061
[40]	P. Molchanov, S. Tyree, T. Karras, T. Aila, J. Kautz, Pruning convolutional neural networks for resource efficient inference, preprint arXiv: 1611.06440.
[41]	Z. Yan, X. Yang, K. T. Cheng, Joint segment-level and pixel-wise losses for deep learning based retinal vessel segmentation, IEEE Trans. Biomed. Eng., 65 (2018), 1912–1923. https://doi.org/10.1109/TBME.2018.2828137 doi: 10.1109/TBME.2018.2828137
[42]	Q. Jin, Z. Meng, T. D. Pham, Q. Chen, L. Wei, R. Su, DUNet: A deformable network for retinal vessel segmentation, Knowl. Based Syst., 178 (2019), 149–162. https://doi.org/10.1016/j.knosys.2019.04.025 doi: 10.1016/j.knosys.2019.04.025

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)