Advertisement

An Improved Method Based on Dynamic Programming for Tracking the Central Axis of Vascular Perforating Branches in Human Brain

  • Wei Peng
  • Qiuyue WeiEmail author
  • Haoyang Shi
  • Jinlu Ma
  • Hao Xu
  • Tongjie Mu
  • Shaojie Tang
  • Qi Yang
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 891)

Abstract

In the traditional method, generally, it is hard to track the vascular perforating branches in human brain, considering the lower spatial resolution of MRI and involuntary movement of human head. Firstly, the method makes full use of the fuzzy distance transform (FDT) and the local significant factor (LSF) to accurately extract the pivot points in the blood vessel. Then, we improve the original method essentially that the step size is adaptively adjusted according to the curvature of the blood vessel and grayscale information of the vascular perforating branches in MRI data. Thirdly, the central axis of the blood vessel is smoothly and accurately tracked by using the minimum cost path based on dynamic programming. Experiments show that the central axis of vascular perforating branches can be tracked effectively by the improved method.

Keywords

Fuzzy distance transform Local significant factor Minimum cost path 

Notes

Acknowledgments

This work was supported in part by the project for the innovation and entrepreneurship in XUPT (2018SC-03), the Key Lab of Computer Networks and Information Integration (Southeastern University), Ministry of Education, China (K93-9-2017-03), the Department of Education Shaanxi Province (15JK1673), Shaanxi Provincial Natural Science Foundation of China (2016JM8034, 2016JQ5051).

References

  1. 1.
    Yang, G., Kitslaar, P., Frenay, M.: Automatic centerline extraction of coronary arteries in coronary computed tomographic angiography. Int. J. Cardiovasc. Imaging 28(4), 921–933 (2012).  https://doi.org/10.1007/s10554-011-9894-2CrossRefGoogle Scholar
  2. 2.
    Akhtar, Y., Mukherjee, D.P.: Reconstruction of three-dimensional linear structures in the breast from craniocaudal and mediolateral oblique mammographic views. IET Image Proc. 11(11), 1114–1121 (2017).  https://doi.org/10.1049/iet-ipr.2016.1063CrossRefGoogle Scholar
  3. 3.
    Sadleir, R., Whelan, P.: Fast colon centerline calculation using optimized 3D topological thinning. Comput. Med. Imaging Graph. 29(4), 251–258 (2005).  https://doi.org/10.1016/j.compmedimag.2004.10.002CrossRefGoogle Scholar
  4. 4.
    Jin, D., Saha, P.K.: A new fuzzy skeletonization algorithm and its applications to medical imaging. In: 17th International Conference on Image Analysis and Processing (ICIAP). LNCS, Naples, Italy, pp. 662–671 (2013).  https://doi.org/10.1007/978-3-642-41181-6_67CrossRefGoogle Scholar
  5. 5.
    Blum, H.: A transformation for extracting new descriptors of shape. In: Models for the Perception of Speech and Visual Form, pp. 362–380. MIT Press, Cambridge, (1967)Google Scholar
  6. 6.
    Saha, P.K., Strand, R., Borgefors, G.: Digital topology and geometry in medical imaging: a survey. IEEE Trans. Med. Imaging 34(9), 1940–1964 (2015).  https://doi.org/10.1109/TMI.2015.2417112CrossRefGoogle Scholar
  7. 7.
    Lukač, A., Subašić, M.: Blood vessel segmentation using multiscale Hessian and tensor voting. In: 40th International Convention on Information and Communication Technology, pp. 1534–1539. Electronics and Microelectronics (MIPRO), Opatija (2017).  https://doi.org/10.23919/mipro.2017.7973665
  8. 8.
    Saha, P.K., Wehrli, F.W., Gomberg, B.R.: Fuzzy distance transform: theory, algorithms, and applications. Comput. Vis. Image Underst. 86(3), 171–190 (2002).  https://doi.org/10.1006/cviu.2002.0974CrossRefzbMATHGoogle Scholar
  9. 9.
    Jin, D., Iyer, K.S., Hoffman, E.A., Saha, P.K.: A new approach of arc skeletonization for tree-like objects using minimum cost path. In: 22nd International Conference on Pattern Recognition, Proceedings of the IAPR International Conference Pattern Recognition, Stockholm, pp. 942–947 (2014).  https://doi.org/10.1109/icpr.2014.172

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Wei Peng
    • 1
  • Qiuyue Wei
    • 1
  • Haoyang Shi
    • 1
  • Jinlu Ma
    • 1
  • Hao Xu
    • 1
  • Tongjie Mu
    • 1
  • Shaojie Tang
    • 1
  • Qi Yang
    • 2
  1. 1.School of AutomationXi’an University of Posts and TelecommunicationsXi’anChina
  2. 2.Department of RadiologyXuanwu Hospital, Capital Medical UniversityBeijingChina

Personalised recommendations