Abstract
The topology of the segmented vessels is essential to evaluate a vessel segmentation approach. However, most popular convolutional neural network (CNN) models, such as U-Net and its variants, pay minimal attention to the topology of vessels. This paper proposes integrating graph neural networks (GNN) and classic CNN to enhance the model performance on the vessel topology. Specifically, we first use a U-Net as our base model. Then, to form the underlying graph in GNN, we sample the corners on the skeleton of the labeled vessels as the graph nodes and use the semantic information from the base U-Net as the node features, which construct the graph edges. Furthermore, we extend the previously reported graphical connectivity constraint module (GCCM) to predict the links between different nodes to maintain the vessel topology. Experiments on DRIVE and 1092 digital subtraction angiography (DSA) images of coronary arteries dataset show that our method has achieved comparable results with the current state-of-the-art methods on classic Dice and centerline-Dice.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)
Ahn, S.J., Kim, M.: Variational graph normalized autoencoders. In: Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pp. 2827–2831 (2021)
Hu, X., Li, F., Samaras, D., Chen, C.: Topology-preserving deep image segmentation. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Isensee, F., Jaeger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203–211 (2021)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint. arXiv:1412.6980 (2014)
Kipf, T.N., Welling, M.: Variational graph auto-encoders. arXiv preprint. arXiv:1611.07308 (2016)
Lam, L., Lee, S.W., Suen, C.Y.: Thinning methodologies-a comprehensive survey. IEEE Trans. Pattern Anal. Mach. Intell. 14(09), 869–885 (1992)
Li, R., et al.: 3d graph-connectivity constrained network for hepatic vessel segmentation. IEEE J. Biomed. Health Inform. 26(3), 1251–1262 (2021)
Livne, M., et al.: A U-Net deep learning framework for high performance vessel segmentation in patients with cerebrovascular disease. Front. Neurosci. 13, 97 (2019)
Mosinska, A., Koziński, M., Fua, P.: Joint segmentation and path classification of curvilinear structures. IEEE Trans. Pattern Anal. Mach. Intell. 42(6), 1515–1521 (2019)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Saueressig, C., Berkley, A., Munbodh, R., Singh, R.: A joint graph and image convolution network for automatic brain tumor segmentation. arXiv preprint. arXiv:2109.05580 (2021)
Sethian, J.A.: Fast marching methods. SIAM Rev. 41(2), 199–235 (1999)
Shi, J., et al.: Good features to track. In: 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 593–600. IEEE (1994)
Shin, S.Y., Lee, S., Yun, I.D., Lee, K.M.: Deep vessel segmentation by learning graphical connectivity. Med. Image Anal. 58, 101556 (2019)
Shit, S., et al.: clDice-a novel topology-preserving loss function for tubular structure segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16560–16569 (2021)
Staal, J., Abràmoff, M.D., Niemeijer, M., Viergever, M.A., Van Ginneken, B.: Ridge-based vessel segmentation in color images of the retina. IEEE Trans. Med. Imaging 23(4), 501–509 (2004)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint. arXiv:1710.10903 (2017)
Wang, B., Qiu, S., He, H.: Dual encoding U-Net for retinal vessel segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11764, pp. 84–92. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32239-7_10
Wang, C., Zhao, Z., Ren, Q., Xu, Y., Yu, Y.: Dense U-net based on patch-based learning for retinal vessel segmentation. Entropy 21(2), 168 (2019)
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Philip, S.Y.: A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32(1), 4–24 (2020)
Yu, F., et al.: Annotation-free cardiac vessel segmentation via knowledge transfer from retinal images. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 714–722. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_79
Acknowledgements
This work is supported by the Grants under Beijing Natural Science Foundation (Z180001), The National Natural Science Foundation of China (NSFC) under Grants 81801778, 12090022, and 11831002.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yu, H., Zhao, J., Zhang, L. (2022). Vessel Segmentation via Link Prediction of Graph Neural Networks. In: Li, X., Lv, J., Huo, Y., Dong, B., Leahy, R.M., Li, Q. (eds) Multiscale Multimodal Medical Imaging. MMMI 2022. Lecture Notes in Computer Science, vol 13594. Springer, Cham. https://doi.org/10.1007/978-3-031-18814-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-18814-5_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18813-8
Online ISBN: 978-3-031-18814-5
eBook Packages: Computer ScienceComputer Science (R0)
