Skip to main content

Advertisement

SpringerLink
Log in

PixelTopoIS: a pixel-topology-coupled guidewire tip segmentation framework for robot-assisted intervention

  • Original Article
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Purpose

Existing works showed great performance in pixel-level guidewire segmentation. However, topology-level segmentation has not been fully exploited in these works. Guidewire (tip) endpoint localization and (guidewire) loop detection are typical topology-level guidewire segmentation tasks. A superb guidewire segmentation algorithm should achieve both low endpoint localization error and high loop detection accuracy.

Methods

This paper focuses on pixel-topology-coupled guidewire (tip) segmentation. The contributions are (1) two algorithmic improvements including an iterative segmentation framework and a pixel-topology-coupled loss function (2) a new metric that comprehensively evaluates the segmentation results at both pixel and topology level (3) the first publicly available guidewire dataset (The dataset can be downloaded from www.njzdyyrobocgsu.com) containing 4500+ X-ray images with radiologist-annotated results.

Results

The algorithm rivals the state-of-the-art methods in pixel-level metric (0.06–4.21% for the F1-score) in most sequences, achieving performance comparable to the best method on two sequences. Our method also shows competitive performance (20% for the loop existence accuracy) on the newly introduced metric. Experiments are also performed to quantitatively validate the functionality of different components in our framework.

Conclusion

The framework is effective in segmenting the guidewire by considering pixel and topology equally, providing an accurate position of the tip’s endpoint (pixel-level) to the surgeon/robot and preserving the clinically meaningful guidewire structure (topology-level) simultaneously.

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
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Notes

  1. The Supplementary Material can be found at https://github.com/Shenghao28/TopoISGuidewireSegmentation/blob/master/SupplementaryMaterial.pdf.

  2. In fact, initial segmentation \({S}_{0}\) is produced based on fluoroscopic image \(I\) by an Attention mechanism. Since the Attention mechanism is irrelevant to the core algorithmic improvements proposed in this paper, it has been moved to Supplementary Material. For now, Reviewers can assume that \({S}_{0}\) has been acquired.

References

  1. Shinohara K (2015) Ergonomic investigation of interventional radiology. In: International conference on applied human factors and ergonomics (AHFE 2015), vol 3, pp 308–311

  2. Walsum T, Baert S (2005) Niessen WJ(2005) Guidewire Reconstruction and Visualization in 3DRA Using Monoplane Fluoroscopic Imaging. IEEE Trans Med Imaging 24:612–623

    Article  Google Scholar 

  3. Shen H, Wang C, Xie L, Zhou S, Gu L (2019) Xie H (2019) A novel robotic system for vascular intervention: principles, performances, and applications. Int J Comput Assist Radiol Surg 14(4):671–683

    Article  Google Scholar 

  4. Chang PL, Rolls A, Praetere HD, Vander H, Poorten E, Riga CV, Bicknell CD (2016) Stoyanov D (2016) Robust catheter and guidewire tracking using b-spline tube model and pixel-wise posteriors. IEEE Robot Autom Lett 1(1):303–308

    Article  Google Scholar 

  5. Chen BJ, Wu Z, Sun S, Zhang D, Chen T (2016) Guidewire tracking using a novel sequential segment optimization method in interventional x-ray videos. In: IEEE Int Symp Biomed Imaging, pp 103–106

  6. Heibel H, Glocker B, Groher M, Pfister M, Navab N (2013) Interventional tool tracking using discrete optimization. IEEE Trans Med Imaging 32:544–555

    Article  Google Scholar 

  7. Heibel H, Glocker B, Groher M, Paragios N, Komodakis N, Navab N (2009) Discrete tracking of parametrized curves. In: IEEE conference on computer vision and pattern recognition, pp 1754–1761

  8. Vandini A, Glocker B, Hamady M (2017) Yang GZ (2017) Robust guidewire tracking under large deformations combining segment-like features (seglets). Med Image Anal 38:150–164

    Article  Google Scholar 

  9. Bismuth V, Vaillant R, Talbot H, Najman L (2012) Curvilinear structure enhancement with the polygonal path image-application to guidewire segmentation in X-ray fluoroscopy. In: International conference on medical image computing and computer-assisted intervention, Springer, pp 9–16

  10. Ambrosini P, Ruijters D, Niessen WJ, Moelker A, Walsum T (2017) Fully automatic and real-time catheter segmentation in X-ray fluoroscopy. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 577–585

  11. Zhou Y, Xie XL, Bian GB, Hou ZG, Wu Y, Liu S, Zhou X, Wang J (2019) Fully automatic dual-guidewire segmentation for coronary bifurcation lesion. In: International joint conference on neural networks, pp 1–6

  12. Zhou YJ, Xie XL, Zhou XH, Liu SQ, Bian GB, Hou ZG (2020) Pyramid attention recurrent networks for real-time guidewire segmentation and tracking in intraoperative X-ray fluoroscopy. Comput Med Imaging Graph 101734

  13. Vlontzos A, Mikolajczyk K (2018) Deep segmentation and registration in X-ray angiography video. arXiv:1805.06406

  14. Wu YD, Xie XL, Bian GB, Hou ZG, Cheng XR, Chen S, Liu SQ, Wang QL (2018) Automatic guidewire tip segmentation in 2D X-ray fluoroscopy using convolution neural networks. In: International joint conference on neural networks, pp 65–72

  15. Mosinska A, Marquez-Neila P, Kozinski M, Fua P (2018) Beyond the pixel-wise loss for topology-aware delineation. In: IEEE conference on computer vision & pattern recognition, pp 664–653

  16. Araújo R, Cardoso J, Oliveira H (2019) A deep learning design for improving topology coherence in blood vessel segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, Cham, pp 128–137

Download references

Acknowledgements

This work was funded by the National Natural Science Foundation of China (No. 81827805, 61401451).

Author information

Author notes

  1. Shenghao Jiang and Sitong Teng contributed equally.

Authors and Affiliations

  1. Department of Radiology, Zhongda Hospital Southeast University, Nanjing, China

    Jian Lu, Jianjun Zhu & Gaojun Teng

  2. Hanglok-Tech Co., Ltd., Guangdong, China

    Shenghao Jiang, Sitong Teng, Cheng Wang & Jianjun Zhu

  3. School of Engineering and Applied Sciences, Harvard University, Cambridge, USA

    Shenghao Jiang

  4. SIEMENS, Healthineers, Shanghai, China

    Sitong Teng

  5. Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Beijing, China

    Tiexiang Wen

Authors
  1. Shenghao Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sitong Teng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jian Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Cheng Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Tiexiang Wen
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jianjun Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Gaojun Teng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Gaojun Teng.

Ethics declarations

Ethical approval

The study was conducted with ethical standards.

Informed consent

Informed consent was obtained in the study.

Conflict of interest

All authors declare no conflict of interest.

Additional information

Publisher's Note

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

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (PDF 1353 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jiang, S., Teng, S., Lu, J. et al. PixelTopoIS: a pixel-topology-coupled guidewire tip segmentation framework for robot-assisted intervention. Int J CARS 17, 329–341 (2022). https://doi.org/10.1007/s11548-021-02529-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-021-02529-4

Keywords

Search

Navigation