Skip to main content
SpringerLink
Log in

A fiducial-less tracking method for radiation therapy of liver tumors by diaphragm disparity analysis part 1: simulation study using machine learning through artificial neural network

  • Original Research
  • Published:
Journal of Radiation Oncology

Abstract

Objective

The large respiratory-induced motion of the liver tumors can affect treatment planning and delivery in many ways. As a result, motion management techniques are necessary to mitigate these effects. An effective approach to reducing the effects of respiratory motion of liver tumors is real-time tracking of the tumor. The Cyberknife treatment modality uses a combination of kV X-ray images, LED markers, an optic camera, and surgically implanted fiducial markers to track liver tumors. However, the use of an invasive method for implanting fiducial markers can lead to complications. We propose a tracking method that requires no fiducial markers for liver tumors by using the projected location of the diaphragm to identify the 3D location of the liver tumor. With the use of the 4D extended cardiac-torso (XCAT) phantom, this simulation study aims to investigate the feasibility of localizing liver tumors through the tracking of the diaphragm-lung border.

Methods

An abdominal 4DCT dataset containing 20 phases of one breathing cycle was created by using the male model of the 4D XCAT phantom. One set of orthogonal DRR images (+ 45°) was generated for each phase. On each DRR image, an outline of the lung-diaphragm border was detected using an edge detection algorithm. The simulated tumor’s gravity center was identified for each phase of the breathing cycle. Using artificial neural networks (ANNs), two respiratory scenarios correlating the diaphragm’s location with the corresponding 3D location of the tumor were compared: (1) lung-defined tumor motion (TL) and (2) user-defined tumor motion (TA). Additionally, using the user-defined tumor motion, we also examined the accuracy of using ANN to track the tumor under the mismatched conditions during 4DCT reconstruction.

Results

Evaluation of the ANN model was quantified by the root mean square error (RMSE) values through the leave-one-out (LOO) validation technique. The RMSE for the TL motion was 0.67 mm and for the TA motion was 0.32 mm. When the ANN model was applied to the mismatched data, it generated the RMSE of 1.63 mm, whereas applied to the ground-truth data, the RMSE is 0.88 mm.

Conclusion

This simulation study shows that the diaphragm and tumor position are closely related. The developed diaphragm disparity-analysis approach, featuring tracking capability and verified with clinically acceptable errors, has the potential to replace fiducial markers for clinical application. The tracking method will be further investigated in clinical datasets from patients.

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

Similar content being viewed by others

References

  1. Shimizu S, Shirato H, Xo B, Kagei K, Nishioka T, Hashimoto S, Tsuchiya K, Aoyama H, Miyasaka K (1999) Three-dimensional movement of a liver tumor detected by high-speed magnetic resonance imaging. Radiother Oncol 50:367–370

    Article  CAS  PubMed  Google Scholar 

  2. Hallman J, Mori S, Sharp G (2012) A four-dimensional computed tomography analysis of multiorgan abdominal motion. Int J Radiat Oncol Biol Phys 83:435–441

    Article  PubMed  Google Scholar 

  3. Abbas H, Chang B, Chen Z (2014) Motion management in gastrointestinal cancers. J Gastrointest Oncol 5:223–235

    PubMed  PubMed Central  Google Scholar 

  4. Keall P, Mageras G, Balter J et al (2006) The management of respiratory motion in radiation oncology report of AAPM Task Group 76. Med Phys 33(10):3874–3900

    Article  PubMed  Google Scholar 

  5. Rosu M, Dawson LA, Balter JM, McShan DL, Lawrence TS, Ten Haken RK (2003) Alterations in normal liver doses due to organ motion. Int J Radiat Oncol Biol Phys 57(5):1472–1479

    Article  PubMed  Google Scholar 

  6. RadiologyInfo. Fiducial marker placement, January 2016. [Online]. Available: https://www.radiologyinfo.org/en/info.cfm?pg=fiducial-marker

  7. Kim J, Hong S, Kwon S (2012) Safety and efficacy of ultrasound-guided fiducial marker implantation for CyberKnife radiation therapy. Korean J Radiol 13(3):307–313

    Article  PubMed  PubMed Central  Google Scholar 

  8. Roberge D, Cabrera T (2011) Percutaneous liver fiducial implants: techniques, materials and complications. In: Liver biopsy in modern medicine. InTechOpen, Canada

    Google Scholar 

  9. Yang J, Cai J, Wang H, Chang Z, Czito B, Bashir M, Palta M, Yin F (2014) Is diaphragm motion a good surrogate for liver tumor motion? Int J Oncol Biol Phys 90(4):952–958

    Article  Google Scholar 

  10. Balter J, Dawson L, Kazanjian S, McGinn C, Brock K, Lawrence T, Haken R (2001) Determination of ventilatory liver movement via radiographic evaluation of diaphragm position. Int J Radiat Oncol Biol Phys 51(1):267–270

    Article  CAS  PubMed  Google Scholar 

  11. Wang M, Sharp G, Rit S, Delmon V, Wang G (2014) 2D/4D marker-free tumor tracking using 4D CBCT as the reference image. Phys Med Biol 59(9):2219–2233

    Article  PubMed  PubMed Central  Google Scholar 

  12. Goodband JH, Haas OL, Mills JA (2008) A comparison of neural network approaches for on-line prediction in IGRT. Med Phys 35(3):1113–1122

    Article  CAS  PubMed  Google Scholar 

  13. Murphy MJ, Pokhrel D (2009) Optimization of an adaptive neural network to predict breathing. Med Phys 36(1):40–47

    Article  PubMed  Google Scholar 

  14. Laurent R, Henriet J, Salomon M, Sauget M, Gschwind R, Makovicka L (2012) Respiratory lung motion using an artificial neural network. Neural Comput Applic 21(5):929–934

    Article  Google Scholar 

  15. Yun J, Mackenzie M, Rathee S, Robinson D, Fallone BG (2012) An artificial neural network (ANN)-based lung-tumor motion predictor for intrafractional MR tumor tracking. Med Phys 39(7):4423–4433

    Article  PubMed  Google Scholar 

  16. Stam M, Crijns S, Zonnenberg B, Barendrecht M, van Vulpen M, Lagendijkl J, Raaymakers B (2012) Navigators for motion detection during real-time MRI-guided radiotherapy. Phys Med Biol 57:6797–6805

    Article  PubMed  Google Scholar 

  17. Torshabi A, Pella A, Riboldi M, Baroni G (2010) Targeting accuracy in real-time tumor tracking via external surrogates: a comparative study. Technol Cancer Res Treat 9(6):551–561

    Article  CAS  PubMed  Google Scholar 

  18. Segars W, Sturgeon G, Mendonca S, Grimes J, Tsui BMW (2010) 4D XCAT phantom for multimodality imaging research. Med Phys 37(9):4902–4915

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  19. Plathow C, Fink C, Ley S (2004) Measurement of diaphragmatic length during the breathing cycle by dynamic MRI: comparison between healthy adults and patients with an intrathoracic tumor. Eur Radiol 14(8):1392–1399

    Article  PubMed  Google Scholar 

  20. Eken C, Bilge U, Kartal M, Eray O (2009) Artificial neural network, genetic algorithm, and logistic regression applications for predicting renal colic in emergency settings. Int J Emerg Med 2(2):99–105

    Article  PubMed  PubMed Central  Google Scholar 

  21. McCulloch W, Pitts W (1943) A logical calculus of ideas immanent in nervous activity. Bull Math Biophys 5(4):115–133

    Article  Google Scholar 

  22. Rosenberg A (2009) Lesson 5: linear regression with regularization. [Online]. Available: https://www.coursehero.com/file/18384131/lecture5/

  23. Lourakis M (2005) A brief description of the Levenberg-Marquardt algorithm implemented by levmar. Found Res Technol 4:1–6

    Google Scholar 

  24. Dan Forsee F, Hagan M (1997) Gauss-Newton approximation to Bayesian learning. [Online]. Available: http://hagan.ecen.ceat.okstate.edu/icnn97a.pdf

  25. Burden F, Winkler D (2008) Bayesian regularization of neural networks. Methods Mol Biol 458:25–44

    PubMed  Google Scholar 

  26. Lopez I, Aragones L, Villacampa Y, Serra J (2017) Neural network for determining the characteristic points of the bars. Ocean Eng 136:141–151

    Article  Google Scholar 

  27. Low D, White B, Lee P, Thomas D, Gaudio S, Jani S, Wu X, Lamb J (2013) A novel CT acquisition and analysis technique for breathing motion modeling. Phys Med Biol 58(11):L31–L36

    Article  PubMed  PubMed Central  Google Scholar 

  28. Rietzel E, Chen GTY (2006) Improving retrospective sorting of 4D computed tomography data. Med Phys 33:377–379

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

Authors are grateful to Dr. Paul W. Segars and his research group for giving permission to use the 4D XCAT phantom for this research.

Author information

Authors and Affiliations

  1. Department of Biomedical Engineering, University of Miami, 1251 Memorial Drive, Coral Gables, FL, 33146, USA

    Deon Dick, Xiaodong Wu & Weizhao Zhao

  2. Biophysics Research Institute of America, Aventura, FL, 33179, USA

    Xiaodong Wu

  3. JFK Comprehensive Cancer Institute, Lake Worth, FL, 33461, USA

    Xiaodong Wu & Georges F. Hatoum

Authors
  1. Deon Dick
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaodong Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Georges F. Hatoum
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Weizhao Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaodong Wu.

Ethics declarations

Funding

No funding support is associated with this study.

Conflict of interest

Deon Dick and Weizhao Zhao declare that they have no conflict of interest. Xiaodong Wu and Georges Hatoum declare that they have a US patent for the design of the concept.

Ethical approval

This report does not contain any studies with human participants or animals performed by any of the authors.

Informed consent

Statement of informed consent was not applicable since the manuscript does not contain any patient data.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dick, D., Wu, X., Hatoum, G.F. et al. A fiducial-less tracking method for radiation therapy of liver tumors by diaphragm disparity analysis part 1: simulation study using machine learning through artificial neural network. J Radiat Oncol 7, 275–284 (2018). https://doi.org/10.1007/s13566-018-0358-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13566-018-0358-3

Keywords

Search

Navigation