Skip to main content
SpringerLink
Log in

PCRTAM-Net: A Novel Pre-Activated Convolution Residual and Triple Attention Mechanism Network for Retinal Vessel Segmentation

  • Regular Paper
  • Published:
Journal of Computer Science and Technology Aims and scope Submit manuscript

Abstract

Retinal images play an essential role in the early diagnosis of ophthalmic diseases. Automatic segmentation of retinal vessels in color fundus images is challenging due to the morphological differences between the retinal vessels and the low-contrast background. At the same time, automated models struggle to capture representative and discriminative retinal vascular features. To fully utilize the structural information of the retinal blood vessels, we propose a novel deep learning network called Pre-Activated Convolution Residual and Triple Attention Mechanism Network (PCRTAM-Net). PCRTAM-Net uses the pre-activated dropout convolution residual method to improve the feature learning ability of the network. In addition, the residual atrous convolution spatial pyramid is integrated into both ends of the network encoder to extract multiscale information and improve blood vessel information flow. A triple attention mechanism is proposed to extract the structural information between vessel contexts and to learn long-range feature dependencies. We evaluate the proposed PCRTAM-Net on four publicly available datasets, DRIVE, CHASE_DB1, STARE, and HRF. Our model achieves state-of-the-art performance of 97.10%, 97.70%, 97.68%, and 97.14% for ACC and 83.05%, 82.26%, 84.64%, and 81.16% for F1, respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

References

  1. Li L Z, Verma M, Nakashima Y, Nagahara H, Kawasaki R. IterNet: Retinal image segmentation utilizing structural redundancy in vessel networks. In Proc. the 2020 IEEE Winter Conference on Applications of Computer Vision, Mar. 2020, pp.3645–3654. https://doi.org/10.1109/WACV45572.2020.9093621.

  2. Li Z Y, Zhang X F, Muller H, Zhang S T. Large-scale retrieval for medical image analytics: A comprehensive review. Medical Image Analysis, 2018, 43: 66–84. https://doi.org/10.1016/j.media.2017.09.007.

    Article  Google Scholar 

  3. Huang K, Yan M. A region based algorithm for vessel detection in retinal images. In Proc. the 9th International Conference on Medical Image Computing and Computer-Assisted Intervention, Oct. 2006, pp.645–653. https://doi.org/10.1007/11866565_79.

  4. Hoover A D, Kouznetsova V, Goldbaum M. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans. Medical Imaging, 2002, 19(3): 203–210. https://doi.org/10.1109/42.845178.

    Article  Google Scholar 

  5. Liskowski P, Krawiec K. Segmenting retinal blood vessels with deep neural networks. IEEE Trans. Medical Imaging, 2016, 35(11): 2369–2380. https://doi.org/10.1109/TMI.2016.2546227.

    Article  Google Scholar 

  6. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. In Proc. the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Oct. 2015, pp.234–241. https://doi.org/10.1007/978-3-319-24574-4_28.

  7. Staal J, Abramoff M D, Niemeijer M, Viergever M A, Van Ginneken B. Ridge-based vessel segmentation in color images of the retina. IEEE Trans. Medical Imaging, 2004, 23(4): 501–509. https://doi.org/10.1109/TMI.2004.825627.

    Article  Google Scholar 

  8. Orlando J I, Prokofyeva E, Blaschko M B. A discriminatively trained fully connected conditional random field model for blood vessel segmentation in fundus images. IEEE Trans. Biomedical Engineering, 2017, 64(1): 16–27. https://doi.org/10.1109/TBME.2016.2535311.

    Article  Google Scholar 

  9. Sheng B, Li P, Mo S J, Li H T, Hou X H, Wu Q, Qin J, Fang R G, Feng D D. Retinal vessel segmentation using minimum spanning superpixel tree detector. IEEE Trans. Cybernetics, 2018, 49(7): 2707–2719. https://doi.org/10.1109/TCYB.2018.2833963.

    Article  Google Scholar 

  10. Yin B J, Li H T, Sheng B, Hou X H, Chen Y, Wu W, Li P, Shen R M, Bao Y Q, Jia W P. Vessel extraction from non-fluorescein fundus images using orientation-aware detector. Medical Image Analysis, 2015, 26(1): 232–242. https://doi.org/10.1016/j.media.2015.09.002.

    Article  Google Scholar 

  11. Dai L, Wu L, Li H T, Cai C, Wu Q, Kong H Y, Liu R H, Wang X N, Hou X H, Liu Y X, Long X X, Wen Y, Lu L N, Shen Y X, Chen Y, Shen D G, Yang X K, Zou H D, Sheng B, Jia W P. A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nature Communications, 2021, 12: Article No. 3242. https://doi.org/10.1038/s41467-021-23458-5.

  12. Wang D Y, Haytham A, Pottenburgh J, Saeedi O, Tao Y. Hard attention net for automatic retinal vessel segmentation. IEEE Journal of Biomedical and Health Informatics, 2020, 24(12): 3384–3396. https://doi.org/10.1109/JBHI.2020.3002985.

    Article  Google Scholar 

  13. Sun M Y, Li K Q, Qi X Q, Dang H, Zhang G H. Contextual information enhanced convolutional neural networks for retinal vessel segmentation in color fundus images. Journal of Visual Communication and Image Representation, 2021, 77: 103134. https://doi.org/10.1016/j.jvcir.2021.103134.

  14. Jin Q G, Meng Z P, Pham T D, Chen Q, Wei L Y, Su R. DUNet: A deformable network for retinal vessel segmentation. Knowledge-Based Systems, 2019, 178: 149–162. https://doi.org/10.1016/j.knosys.2019.04.025.

    Article  Google Scholar 

  15. Mou L, Chen L, Cheng J, Gu Z W, Zhao Y T, Liu J. Dense dilated network with probability regularized walk for vessel detection. IEEE Trans. Medical Imaging, 2020, 39(5): 1392–1403. https://doi.org/10.1109/TMI.2019.2950051.

    Article  Google Scholar 

  16. Wei J H, Zhu G J, Fan Z, Liu J C, Rong Y B, Mo J J, Li W J, Chen X J. Genetic U-Net: Automatically designed deep networks for retinal vessel segmentation using a genetic algorithm. IEEE Trans. Medical Imaging, 2022, 41(2): 292–307. https://doi.org/10.1109/TMI.2021.3111679.

    Article  Google Scholar 

  17. Fu J, Liu J, Tian H J, Li Y, Bao Y J, Fang Z W, Lu H Q. Dual attention network for scene segmentation. In Proc. the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2019, pp.3141–3149. https://doi.org/10.1109/CVPR.2019.00326.

  18. Yang Q, Ma B Q, Cui H, Ma J Q. AMF-NET: Attention-aware multi-scale fusion network for retinal vessel segmentation. In Proc. the 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society, Nov. 2021, pp.3277–3280. https://doi.org/10.1109/EMBC46164.2021.9630756.

  19. Wu T F, Li L L, Li J B. MSCAN: Multi-scale channel attention for fundus retinal vessel segmentation. In Proc. the 2nd IEEE International Conference on Power Data Science, Dec. 2020, pp.18–27. https://doi.org/10.1109/ICPDS51559.2020.9332494.

  20. Wu H S, Wang W, Zhong J F, Lei B Y, Wen Z K, Qin J. SCS-Net: A scale and context sensitive network for retinal vessel segmentation. Medical Image Analysis, 2021, 70: 102025. https://doi.org/10.1016/j.media.2021.102025.

  21. Glorot X, Bordes A, Bengio Y. Deep sparse rectifier neural networks. In Proc. the 14th International Conference on Artificial Intelligence and Statistics, Apr. 2011, pp.315–323.

  22. Huang G, Liu Z, Van Der Maaten L, Weinberger K Q. Densely connected convolutional networks. In Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Jul. 2017, pp.2261–2269. https://doi.org/10.1109/CVPR.2017.243.

  23. He K M, Zhang X Y, Ren S Q, Sun J. Deep residual learning for image recognition. In Proc. the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2016, pp.770–778. https://doi.org/10.1109/CVPR.2016.90.

  24. Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proc. the 32nd International Conference on Machine Learning, Jul. 2015, pp.448–456.

  25. Mou L, Zhao Y T, Fu H Z, Liu Y H, Cheng J, Zheng Y L, Su P, Yang J L, Chen L, Frangi A F, Akiba M, Liu J. CS2-Net: Deep learning segmentation of curvilinear structures in medical imaging. Medical Image Analysis, 2021, 67: 101874. https://doi.org/10.1016/j.media.2020.101874.

  26. Shi Z J, Wang T Y, Huang Z, Xie F, Liu Z H, Wang B L, Xu J. MD-Net: A multi-scale dense network for retinal vessel segmentation. Biomedical Signal Processing and Control, 2021, 70: 102977. https://doi.org/10.1016/j.bspc.2021.102977.

  27. Owen C G, Rudnicka A R, Mullen R, Barman S A, Monekosso D, Whincup P H, Ng J, Paterson C. Measuring retinal vessel tortuosity in 10-year-old children: Validation of the computer-assisted image analysis of the retina (CAIAR) program. Investigative Ophthalmology & Visual Science, 2009, 50(5): 2004–2010. https://doi.org/10.1167/iovs.083018.

    Article  Google Scholar 

  28. Köhler T, Budai A, Kraus M F, Odstrčilik J, Michelson G, Hornegger J. Automatic no-reference quality assessment for retinal fundus images using vessel segmentation. In Proc. the 26th IEEE International Symposium on Computer-Based Medical Systems, Jun. 2013, pp.95–100. https://doi.org/10.1109/CBMS.2013.6627771.

  29. Woo S, Park J, Lee J Y, Kweon I S. CBAM: Convolutional block attention module. In Proc. the 15th European Conference on Computer Vision, Sept. 2018, pp.3–19. https://doi.org/10.1007/978-3-030-01234-2_1.

  30. Zhuo Z S, Huang J P, Lu K, Pan D R, Feng S T. A size-invariant convolutional network with dense connectivity applied to retinal vessel segmentation measured by a unique index. Computer Methods and Programs in Biomedicine, 2020, 196: 105508. https://doi.org/10.1016/j.cmpb.2020.105508.

  31. Wu Y C, Xia Y, Song Y, Zhang Y N, Cai W D. NFN+: A novel network followed network for retinal vessel segmentation. Neural Networks, 2020, 126: 153–162. https://doi.org/10.1016/j.neunet.2020.02.018.

    Article  Google Scholar 

  32. Khan T M, Khan M A U, Rehman N U, Naveed K, Afridi I U, Naqvi S S, Raazak I. Width-wise vessel bifurcation for improved retinal vessel segmentation. Biomedical Signal Processing and Control, 2022, 71: 103169. https://doi.org/10.1016/j.bspc.2021.103169.

  33. Li Q L, Feng B W, Xie L P, Liang P, Zhang H S, Wang T F. A cross-modality learning approach for vessel segmentation in retinal images. IEEE Trans. Medical Imaging, 2016, 35(1): 109–118. https://doi.org/10.1109/TMI.2015.2457891.

    Article  Google Scholar 

  34. Wu Y C, Xia Y, Song Y, Zhang Y N, Cai W D. Multiscale network followed network model for retinal vessel segmentation. In Proc. the 21st International Conference on Medical Image Computing and Computer-Assisted Intervention, Sept. 2018, pp.119–126.

  35. Tang P, Liang Q K, Yan X T, Zhang D, Coppola G, Sun W. Multi-proportion channel ensemble model for retinal vessel segmentation. Computers in Biology and Medicine, 2019, 111: 103352. https://doi.org/10.1016/j.compbiomed.2019.103352.

  36. Dong F F, Wu D Y, Guo C Y, Zhang S T, Yang B L, Gong X Y. CRAUNet: A cascaded residual attention U-Net for retinal vessel segmentation. Computers in Biology and Medicine, 2022, 147: 105651. https://doi.org/10.1016/j.compbiomed.2022.105651.

  37. Soomro T A, Afifi A J, Gao J B, Hellwich O, Zheng L H, Paul M. Strided fully convolutional neural network for boosting the sensitivity of retinal blood vessels segmentation. Expert Systems with Applications, 2019, 134: 36–52. https://doi.org/10.1016/j.eswa.2019.05.029.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Guangxi Key Laboratory of Image and Graphic Intelligent Processing, Guilin, 541004, China

    Hua-Deng Wang, Zhen-Bing Liu, Ru-Shi Lan & Xiao-Nan Luo

  2. School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, 541004, China

    Hua-Deng Wang, Zi-Zheng Li, Xi-Peng Pan, Zhen-Bing Liu, Ru-Shi Lan & Xiao-Nan Luo

  3. School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, 541004, China

    Idowu Paul Okuwobi

  4. Department of Pathology, Ganzhou Municipal Hospital, Ganzhou, 341000, China

    Bing-Bing Li

Authors
  1. Hua-Deng Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zi-Zheng Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Idowu Paul Okuwobi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Bing-Bing Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xi-Peng Pan
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Zhen-Bing Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Ru-Shi Lan
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Xiao-Nan Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Idowu Paul Okuwobi or Bing-Bing Li.

Additional information

Idowu Paul Okuwobi worked on the investigation and writing and provided computing power, and Bing-Bing Li was responsible for the data curation and methodology.

Supplementary Information

ESM 1

(PDF 2083 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, HD., Li, ZZ., Okuwobi, I.P. et al. PCRTAM-Net: A Novel Pre-Activated Convolution Residual and Triple Attention Mechanism Network for Retinal Vessel Segmentation. J. Comput. Sci. Technol. 38, 567–581 (2023). https://doi.org/10.1007/s11390-023-3066-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11390-023-3066-4

Keywords

Search

Navigation