Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Morphology Edge Attention Network and Optimal Geometric Matching Connection model for vascular segmentation (2306.01808v2)

Published 2 Jun 2023 in eess.IV and cs.CV

Abstract: There are many unsolved problems in vascular image segmentation, including vascular structural connectivity, scarce branches and missing small vessels. Obtaining vessels that preserve their correct topological structures is currently a crucial research issue, as it provides an overall view of one vascular system. In order to preserve the topology and accuracy of vessel segmentation, we proposed a novel Morphology Edge Attention Network (MEA-Net) for the segmentation of vessel-like structures, and an Optimal Geometric Matching Connection (OGMC) model to connect the broken vessel segments. The MEA-Net has an edge attention module that improves the segmentation of edges and small objects by morphology operation extracting boundary voxels on multi-scale. The OGMC model uses the concept of curve touching from differential geometry to filter out fragmented vessel endpoints, and then employs minimal surfaces to determine the optimal connection order between blood vessels. Finally, we calculate the geodesic to repair missing vessels under a given Riemannian metric. Our method achieves superior or competitive results compared to state-of-the-art methods on four datasets of 3D vascular segmentation tasks, both effectively reducing vessel broken and increasing vessel branch richness, yielding blood vessels with a more precise topological structure.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. L. Mou et al., “Dense dilated network with probability regularized walk for vessel detection,” IEEE Trans. Med. Imaging, vol. 39, no. 5, pp. 1392–1403, May 2020.
  2. Q. Huang et al., “Robust liver vessel extraction using 3d u-net with variant dice loss function,” Computers in Biology and Medicine, vol. 101, pp. 153–162, Oct. 2018.
  3. K. K. W. Chan et al., “Retinal vasculature in glaucoma: A review,” BMJ Open Ophth, vol. 1, no. 1, p. e000032, Jul. 2017.
  4. G. Ning, “Chinese guideline on the primary prevention of cardiovascular diseases: Time to start better cardiovascular primary prevention,” Cardiology Discovery, vol. 1, no. 2, pp. 65–67, Jun. 2021.
  5. “Easl clinical practice guidelines: Vascular diseases of the liver,” Journal of Hepatology, vol. 64, no. 1, pp. 179–202, Jan. 2016.
  6. A. F. Frangi et al., “Multiscale vessel enhancement filtering,” in Medical Image Computing and Computer-Assisted Intervention — MICCAI’98, ser. Lecture Notes in Computer Science, vol. 1496, pp. 130–137.
  7. T. Jerman et al., “Enhancement of vascular structures in 3d and 2d angiographic images,” IEEE Transactions on Medical Imaging, vol. 35, no. 9, pp. 2107–2118, Sep. 2016.
  8. H. Jiang et al., “A region growing vessel segmentation algorithm based on spectrum information,” Computational and Mathematical Methods in Medicine, vol. 2013, p. 743870.
  9. Yanfeng Shang et al., “Vascular active contour for vessel tree segmentation,” IEEE Transactions on Biomedical Engineering, vol. 58, no. 4, pp. 1023–1032, Apr. 2011.
  10. Z. Zhai, M. Staring, and B. C. Stoel, “Lung vessel segmentation in ct images using graph-cuts,” in Medical Imaging 2016: Image Processing, vol. 9784, p. 97842K.
  11. F. Benmansour and L. D. Cohen, “Fast object segmentation by growing minimal paths from a single point on 2d or 3d images,” Journal of Mathematical Imaging and Vision, vol. 33, no. 2, pp. 209–221, Feb. 2009.
  12. D. Chen, J.-M. Mirebeau, and L. D. Cohen, “Global minimum for a finsler elastica minimal path approach,” International Journal of Computer Vision, vol. 122, no. 3, pp. 458–483, May 2017.
  13. M. R. K. Mookiah et al., “A review of machine learning methods for retinal blood vessel segmentation and artery/vein classification,” Medical Image Analysis, vol. 68, p. 101905, Feb. 2021.
  14. M. Ciecholewski and M. Kassjański, “Computational methods for liver vessel segmentation in medical imaging: A review,” Sensors, vol. 21, no. 6, p. 2027, Mar. 2021.
  15. S. Gupta et al., “Learning topological interactions for multi-class medical image segmentation,” in Computer Vision – ECCV 2022, 2022, pp. 701–718.
  16. J. Clough et al., “A topological loss function for deep-learning based image segmentation using persistent homology,” IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1–1, 2020.
  17. X. Hu et al., “Topology-aware segmentation using discrete morse theory,” in International Conference on Learning Representations, 2021.
  18. S. Shit et al., “cldice - a novel topology-preserving loss function for tubular structure segmentation,” in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 16 555–16 564.
  19. D. Oner et al., “Enforcing connectivity of 3d linear structures using their 2d projections,” in Medical Image Computing and Computer Assisted Intervention – MICCAI 2022, 2022, vol. 13435, pp. 591–601.
  20. X. Hu and C. Chen, “Image segmentation with homotopy warping,” ArXiv, vol. abs/2112.07812, 2021.
  21. X. Wang et al., “Non-local neural networks,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 7794–7803.
  22. J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132–7141.
  23. A. Vaswani et al., “Attention is all you need,” in Advances in Neural Information Processing Systems, vol. 30, 2017.
  24. L. Xia et al., “3d vessel-like structure segmentation in medical images by an edge-reinforced network,” Medical Image Analysis, vol. 82, p. 102581, Nov. 2022.
  25. Z. Zhang et al., “Confluent vessel trees with accurate bifurcations,” arXiv:2103.14268 [cs], Mar. 2021.
  26. D. Chen, J.-M. Mirebeau, and L. D. Cohen, “Vessel tree extraction using radius-lifted keypoints searching scheme and anisotropic fast marching method,” Journal of Algorithms & Computational Technology, vol. 10, no. 4, pp. 224–234, Dec. 2016.
  27. L. Liu et al., “Trajectory grouping with curvature regularization for tubular structure tracking,” IEEE Trans. on Image Process., vol. 31, pp. 405–418, 2022.
  28. J. He et al., “Learning hybrid representations for automatic 3d vessel centerline extraction,” in Medical Image Computing and Computer Assisted Intervention – MICCAI 2020, 2020, pp. 24–34.
  29. O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, vol. 9351, pp. 234–241.
  30. H. Wu et al., “Scs-net: A scale and context sensitive network for retinal vessel segmentation,” Medical Image Analysis, vol. 70, p. 102025, May 2021.
  31. O. Oktay et al., “Attention u-net: Learning where to look for the pancreas,” ArXiv, vol. abs/1804.03999, 2018.
  32. T. Lee, R. Kashyap, and C. Chu, “Building skeleton models via 3-d medial surface axis thinning algorithms,” CVGIP: Graphical Models and Image Processing, vol. 56, no. 6, pp. 462–478, 1994.
  33. Z. Zhang et al., “Divergence prior and vessel-tree reconstruction,” in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 10 208–10 216.
  34. G. Tetteh et al., “Deepvesselnet: Vessel segmentation, centerline prediction, and bifurcation detection in 3-d angiographic volumes,” Front. Neurosci., vol. 14, p. 592352, Dec. 2020.
  35. J.-M. Mirebeau and J. Portegies, “Hamiltonian fast marching: A numerical solver for anisotropic and non-holonomic eikonal pdes,” Image Processing On Line, vol. 9, pp. 47–93, 2019.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now