Skip to main content
SpringerLink
Log in

SCAN: sequence-based context-aware association network for hepatic vessel segmentation

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Accurate segmentation of hepatic vessel is significant for the surgeons to design the preoperative planning of liver surgery. In this paper, a sequence-based context-aware association network (SCAN) is designed for hepatic vessel segmentation, in which three schemes are incorporated to simultaneously extract the 2D features of hepatic vessels and capture the correlations between adjacent CT slices. The two schemes of slice-level attention module and graph association module are designed to bridge feature gaps between the encoder and the decoder in the low- and high-dimensional spaces. The region-edge constrained loss is designed to well optimize the proposed SCAN, which integrates cross-entropy loss, dice loss, and edge-constrained loss. Experimental results indicate that the proposed SCAN is superior to several existing deep learning frameworks, in terms of 0.845 DSC, 0.856 precision, 0.866 sensitivity, and 0.861 F1-score.

Graphical Abstract

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Data availability

It should be noted that the data collected for research purposes is subject to informed patient consent, but due to confidentiality agreements, the dataset does not support open access at this time.

References

  1. Anwanwan D, Singh SK, Singh S et al (2020) Challenges in liver cancer and possible treatment approaches [J]. Biochimica et Biophysica Acta (BBA)-Reviews on Cancer 1873(1):188314

  2. Schumann C, Bieberstein J, Braunewell S et al (2012) Visualization support for the planning of hepatic needle placement [J]. Int J Comput-Assist Radiol Surg 7(2):191–197

    Article  PubMed  Google Scholar 

  3. Selle D, Preim B, Schenk A et al (2002) Analysis of vasculature for liver surgical planning [J]. IEEE Trans Med Imaging 21(11):1344–1357

    Article  PubMed  Google Scholar 

  4. Lafortune M, Madore F, Patriquin H et al (1991) Segmental anatomy of the liver: a sonographic approach to the Couinaud nomenclature [J]. Radiology 181(2):443–448

    Article  CAS  PubMed  Google Scholar 

  5. Sboarina A, Foroni RI, Minicozzi A et al (2010) Software for hepatic vessel classification: feasibility study for virtual surgery [J]. Int J Comput Assist Radiol Surg 5(1):39–48

    Article  CAS  PubMed  Google Scholar 

  6. Lebre MA, Vacavant A, Grand-Brochier M et al (2019) Automatic segmentation methods for liver and hepatic vessels from CT and MRI volumes, applied to the Couinaud scheme [J]. Comput Biol Med 110:42–51

    Article  PubMed  Google Scholar 

  7. Zhang L, Zhang Y (2016) Big data analysis by infinite deep neural networks [J]. J Comput Res Dev 53(1):68–79

    Google Scholar 

  8. Shen D, Wu G, Suk HI (2017) Deep learning in medical image analysis [J]. Annu Rev Biomed Eng 19(5):221–248

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  9. Sun X, Fang H, Yang Y et al (2021) Robust retinal vessel segmentation from a data augmentation perspective [C]//International Workshop on Ophthalmic Medical Image Analysis. Springer, Cham, pp 189–198

    Google Scholar 

  10. Bano S, Vasconcelos F, Shepherd LM et al (2020) Deep placental vessel segmentation for fetoscopic mosaicking [C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham 763–773

  11. Zhou S, Li N, Zhang B et al (2019) Statistical intensity-and shape-modeling to automate cerebrovascular segmentation from TOF-MRA data. International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, pp 164–172

  12. Zhao G, Liang K, Pan C, Zhang F, Wu X, Hu X, Yu Y (2022) Graph Convolution Based Cross-Network Multiscale Feature Fusion for Deep Vessel Segmentation. IEEE Trans Med Imaging 42(1):183–195

    Article  PubMed  Google Scholar 

  13. Affane A, Lebre MA, Mittal U et al (2020) Literature review of deep learning models for liver vessels reconstruction [C]//2020 Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA). IEEE 1–6

  14. Frericks BB, Caldarone FC, Nashan B et al (2004) 3D CT modeling of hepatic vessel architecture and volume calculation in living donated liver transplantation [J]. Eur Radiol 14(2):326–333

    Article  PubMed  Google Scholar 

  15. Lu S, Huang H, Liang P et al (2017) Hepatic vessel segmentation using variational level set combined with non-local robust statistics [J]. Magn Reson Imaging 36:180–186

    Article  PubMed  Google Scholar 

  16. Kitrungrotsakul T, Han XH, Iwamoto Y et al (2019) VesselNet: a deep convolutional neural network with multi pathways for robust hepatic vessel segmentation [J]. Comput Med Imaging Graph 75:74–83

    Article  PubMed  Google Scholar 

  17. Huang Q, Sun J, Ding H et al (2018) Robust liver vessel extraction using 3D U-Net with variant dice loss function [J]. Comput Biol Med 101:153–162

    Article  PubMed  Google Scholar 

  18. Yan Q, Wang B, Zhang W et al (2021) Attention-guided deep neural network with multi-scale feature fusion for liver vessel segmentation [J]. IEEE J Biomed Health Inform 25(7):2629–2642

    Article  PubMed  Google Scholar 

  19. Zhang D, Liu S, Chaganti S et al (2020) Graph attention network based pruning for reconstructing 3D liver vessel morphology from contrasted CT images [J]. arXiv preprint arXiv:2003.07999

  20. Li R, Huang YJ, Chen H et al (2022) 3D graph-connectivity constrained network for hepatic vessel segmentation [J]. IEEE J Biomed Health Inform 26(3):1251–1262. https://doi.org/10.1109/JBHI.2021.3118104

    Article  PubMed  Google Scholar 

  21. Wu M, Qian Y, Liao X et al (2021) Hepatic vessel segmentation based on 3D swin-transformer with inductive biased multi-head self-attention [J]. arXiv preprint arXiv:2111.03368

  22. Isensee F, Jäger PF, Kohl SAA et al (2019) Automated design of deep learning methods for biomedical image segmentation [J]. arXiv preprint arXiv:1904.08128

  23. Yi-de M, Qing L, Zhi-Bai Q (2004) Automated image segmentation using improved PCNN model based on cross-entropy [C]//Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004. IEEE 743–746

  24. Milletari F, Navab N, Ahmadi SA (2016) V-net: fully convolutional neural networks for volumetric medical image segmentation [C]//2016 Fourth International Conference on 3D Vision (3DV). IEEE 565–571

  25. Karimi D, Salcudean SE (2019) Reducing the Hausdorff distance in medical image segmentation with convolutional neural networks [J]. IEEE Trans Med Imaging 39(2):499–513

    Article  PubMed  Google Scholar 

  26. Scarselli F, Gori M, Ah Chung Tsoi, Hagenbuchner M, Monfardini G (2009) The graph neural network model. IEEE TNNLS 20(1):61–80

  27. Rockafellar RT, Wets RJB (2009). Variational analysis, vol 317. Springer Science & Business Media

    Google Scholar 

  28. Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation [C]//International Conference on Medical Image Computing and Computer-assisted Intervention. Springer, Cham 234–241

  29. Oktay O, Schlemper J, Folgoc LL et al (2018) Attention U-Net: learning where to look for the pancreas [J]. arXiv preprint arXiv:1804.03999

  30. Woo S, Park J, Lee JY et al (2018) CBAM: convolutional block attention module [C]//Proceedings of the European conference on computer vision (ECCV). 3–19

  31. Park J, Woo S, Lee JY et al (2018) BAM: bottleneck attention module [J]. arKiv preprint arKiv :1807.06514

  32. Beck D, Haffari G, Cohn T (2018) Graph-to-sequence learning using gated graph neural networks. arXiv preprint arXiv:1806.09835

  33. Ballas N, Yao L, Pal C, Courville A (2015) Delving deeper into convolutional networks for learning video representations. arXiv preprint arXiv:1511.06432

  34. Su J, Liu Z, Zhang J et al (2021) DV-Net: accurate liver vessel segmentation via dense connection model with D-BCE loss function [J]. Knowl-Based Syst 232:107471

    Article  Google Scholar 

  35. Yushkevich P A, Gao Y, Gerig G (2016) ITK-SNAP: an interactive tool for semi-automatic segmentation of multi-modality biomedical images [C]//2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE 3342–3345

  36. Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Chintala S (2019) Pytorch: An imperative style, high-performance deep learning library. Adv Neural Inf Process Syst 32

  37. Çiçek Ö, Abdulkadir A, Lienkamp SS et al (2016) 3D U-Net: learning dense volumetric segmentation from sparse annotation [C]//International Conference on Medical Image Computing and Computer-assisted Intervention. Springer, Cham 424–432

  38. Cao H, Wang Y, Chen J et al (2021) Swin-unet: Unet-like pure transformer for medical image segmentation [J]. arXiv preprint arXiv:2105.05537

Download references

Funding

This work was supported by the Science and Technology Program in Guangzhou (No. 202102010251) and partly by the Science and Technology Program in Maoming City (No. 2022S048).

Author information

Authors and Affiliations

  1. School of Information Engineering, Guangdong University of Technology, Guangzhou, China

    Yinghong Zhou, Yu Zheng, Yinfeng Tian, Youfang Bai & Nian Cai

  2. Department of Hepatobiliary Surgery in the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China

    Ping Wang

Authors
  1. Yinghong Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yu Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yinfeng Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Youfang Bai
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Nian Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Ping Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Nian Cai or Ping Wang.

Ethics declarations

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhou, Y., Zheng, Y., Tian, Y. et al. SCAN: sequence-based context-aware association network for hepatic vessel segmentation. Med Biol Eng Comput 62, 817–827 (2024). https://doi.org/10.1007/s11517-023-02975-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-023-02975-z

Keywords

Search

Navigation