Advertisement

Discriminative Correlation Filter Network for Robust Landmark Tracking in Ultrasound Guided Intervention

  • Chunxu Shen
  • Jishuai He
  • Yibin Huang
  • Jian WuEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11768)

Abstract

Due to uncertainties from breathing and drift in image-guided abdominal intervention, surgeon would add margins around target so that it can be adequately covered and treated. To mitigate the uncertainties and make motion management more effective, we develop a real-time and high accuracy algorithm for anatomical landmark tracking in liver ultrasound sequences. In this paper, we firstly generate a feature extractor based on an end-to-end network by embedding fully convolutional network (FCN) into discriminative correlation filter (DCF). Meanwhile, we reformulate traditional DCF as a differentiable neural layer (DCF layer) to guarantee generated convolutional features are tightly coupled to DCF. Then we train the end-to-end network by encoding millions of ultrasound images and optimizing an elaborate designed loss function. Finally, we utilize the tailored feature extractor and DCF tracker to perform online tracking. Proposed algorithm is evaluated on 85 landmarks across 39 ultrasound sequences by the organizers of the Challenge on Liver Ultrasound Tracking (CLUST), and yielding 1.11 ± 0.91 mm mean and 2.68 mm 95%ile tracking error. The processing speed for per landmark is about 44–47 frames per second with GPU implementation. Extensive evaluation is performed among proposed and published state-of-the-art algorithms, and results show our algorithm significantly reduces maximum error and achieves a leading performance. Ablation study further supports the benefit from the tailored feature extractor. Clinical application analysis proves our tracker can lessen the heavy burden on surgeon and reduce dependence on medical experience.

Keywords

Fully convolutional network Discriminative correlation filter Abdominal interventional therapy 

Notes

Acknowledgement

This work is supported in part by Knowledge Innovation Program of Basic Research Projects of Shenzhen under Grant JCYJ20160428182053361, in part by Guangdong Science and Technology Plan under Grant 2017B020210003 and in part by National Natural Science Foundation of China under Grant 81771940, 81427803.

References

  1. 1.
    Riley, C., et al.: Dosimetric evaluation of the interplay effect in respiratory-gated RapidArc radiation therapy. Med. Phys. 41(1), 011715 (2014)CrossRefGoogle Scholar
  2. 2.
    Nouri, D., Rothberg, A.: Liver ultrasound tracking using a learned distance metric. In: MICCAI 2015 Challenge on Liver Ultrasound Tracking, Munich, Germany (2015)Google Scholar
  3. 3.
    Gomariz, A., et al.: Siamese networks with location prior for landmark tracking in liver ultrasound sequences. arXiv preprint arXiv:1901.08109 (2019)
  4. 4.
    Hallack, A., et al.: Robust liver ultrasound tracking using dense distinctive image features. In: MICCAI 2015 Challenge on Liver Ultrasound Tracking, Munich, Germany (2015)Google Scholar
  5. 5.
    Shepard, A., et al.: A block matching based approach with multiple simultaneous templates for the real-time 2D ultrasound tracking of liver vessels. Med. Phys. 44(11), 5889–5900 (2017)CrossRefGoogle Scholar
  6. 6.
    Makhinya, M., Goksel, O.: Motion tracking in 2D ultrasound using vessel models and robust optic-flow. In: MICCAI 2015 Challenge on Liver Ultrasound Tracking, Munich, Germany (2015)Google Scholar
  7. 7.
    Williamson, T., et al.: Ultrasound-based liver tracking utilizing a hybrid template/optical flow approach. Int. J. Comput. Assist. Radiol. Surg. 13(10), 1605–1615 (2018)CrossRefGoogle Scholar
  8. 8.
    Kondo, S.: Liver ultrasound tracking using kernelized correlation filter with adaptive window size selection. In: MICCAI 2015 Challenge on Liver Ultrasound Tracking, Munich, Germany (2015)Google Scholar
  9. 9.
    Ozkan, E., et al.: Robust motion tracking in liver from 2D ultrasound images using supporters. Int. J. Comput. Assist. Radiol. Surg. 12(6), 941–950 (2017)CrossRefGoogle Scholar
  10. 10.
    Henriques, J., et al.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583–596 (2015)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Luca, V., et al.: The 2014 liver ultrasound tracking benchmark. Phys. Med. Biol. 60(14), 5571–5599 (2015)CrossRefGoogle Scholar
  12. 12.
    Christoph, B., et al.: On the computation of complex valued gradients with application to statistically optimum beamforming. arXiv preprint arXiv:1701.00392 (2019)

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Chunxu Shen
    • 1
    • 2
  • Jishuai He
    • 1
    • 2
  • Yibin Huang
    • 3
  • Jian Wu
    • 2
    Email author
  1. 1.Tsinghua UniversityBeijingChina
  2. 2.Graduate School at ShenzhenTsinghua UniversityShenzhenChina
  3. 3.Shenzhen Traditional Chinese Medicine HospitalShenzhenChina

Personalised recommendations