Abstract
Radiation dose delivery into the thoracic and abdomen cavities during radiotherapy treatment is a challenging task as respiratory motion leads to the motion of the target tumor. Real-time repositioning of the treatment beam during radiotherapy requires a method for predicting the tumor motion in order to overcome the inherent electro-mechanical latency of the radiotherapy equipment. Thus, besides respiratory motion, system latency also affects the accuracy of dose delivery. To compensate for the latency, a predictor should be employed to anticipate the position of the tumor and give some time to the radiotherapy system for repositioning the radiation beam. This study investigated the ability of spatio-temporal and dynamic neural networks in predicting tumor displacement caused by respiration. Nine different designs of neural networks with 665-ms prediction horizon were examined. The most accurate result was obtained using a dynamic 35-to-3 neural network which resulted in a mean absolute error of 0.54 ± 0.13 and a root mean square error of 0.57 ± 0.20. Moreover, the proposed predictor model is independent of any time-consuming processes such as real-time retraining and real-time baseline shift averaging. The results are comparable or superior with the current literature in terms of prediction accuracy.
Similar content being viewed by others
References
Langen K, Jones D (2001) Organ motion and its management. Int J of Radiation Oncology* Biology* Physics 50(1):265–278
Ross CS, Hussey DH, Pennington EC, Stanford W, Doornbos JF (1990) Analysis of movement of intrathoracic neoplasms using ultrafast computerized tomography. Int J of Radiation Oncology∙ Biology∙ Physics 18(3):671–677
Seco J, Sharp GC, Wu Z, Gierga D, Buettner F, Paganetti H (2008) Dosimetric impact of motion in free-breathing and gated lung radiotherapy: a 4d monte carlo study of intrafraction and interfraction effects. Med Phys 35(1):356–366
Morgan-Fletcher S (2001) Prescribing, recording and reporting photon beam therapy (supplement to ICRU Report 50), ICRU Report 62. ICRU, pp. ix+ 52, 1999 (ICRU Bethesda, MD) $ 65.00 ISBN 0-913394-61-0
Baroni G, Garibaldi C, Riboldi M, Spadea MF, Catalano G, Tagaste B, Tosi G, Orecchia R, Pedotti A (2006) 3d optoelectronic analysis of interfractional patient setup variability in frameless extracranial stereotactic radiotherapy. Int J of Radiation Oncology* Biology* Physics 64(2):635–642
Gianoli C, Riboldi M, Spadea MF, Travaini LL, Ferrari M, Mei R, Orecchia R, Baroni G (2011) A multiple points method for 4D CT image sorting. Med Phys 38(2):656–667
Seregni M, Pella A, Riboldi M, Orecchia R, Cerveri P, Baroni G (2013) Real-time tumor tracking with an artificial neural networks-based method: a feasibility study. Physica Medica 29(1):48–59
Ford E, Mageras G, Yorke E, Rosenzweig K, Wagman R, Ling C (2002) Evaluation of respiratory movement during gated radiotherapy using film and electronic portal imaging. Int J of Radiation Oncology* Biology* Physics 52(2):522–531
Meeks SL, Tomé WA, Willoughby TR, Kupelian PA, Wagner TH, Buatti JM, Bova FJ (2005) Optically guided patient positioning techniques. In: Seminars in radiation oncology, vol 15. Elsevier, pp 192–201
Bert C, Metheany KG, Doppke K, Chen GT (2005) A phantom evaluation of a stereo-vision surface imaging system for radiotherapy patient setup. Med Phys 32(9):2753–2762
Cho B, Poulsen PR, Sloutsky A, Sawant A, Keall PJ (2009) First demonstration of combined kv/MV image-guided real-time dynamic multileaf-collimator target tracking. Int J of Radiation Oncology* Biology* Physics 74(3):859–867
Pollock S, Lee D, Keall P, Kim T (2013) Audiovisual biofeedback improves motion prediction accuracy. Med Phys 40(4):041705–041713
Teo TP, Ahmed SB, Kawalec P, Alayoubi N, Bruce N, Lyn E, Pistorius S (2018) Feasibility of predicting tumor motion using online data acquired during treatment and a generalized neural network optimized with offline patient tumor trajectories. Med Phys 45(2):830–845
Ruan D, Fessler JA, Balter J, Keall P (2009) Real-time profiling of respiratory motion: baseline drift, frequency variation and fundamental pattern change. Phys Med Biol 54(15):4777–4792
Sharp GC, Jiang SB, Shimizu S, Shirato H (2004) Prediction of respiratory tumour motion for real-time image-guided radiotherapy. Phys Med Biol 49(3):425–425
Isaksson M, Jalden J, Murphy MJ (2005) On using an adaptive neural network to predict lung tumor motion during respiration for radiotherapy applications. Med Phys 32(12):3801–3809
Murphy MJ, Dieterich S (2006) Comparative performance of linear and nonlinear neural networks to predict irregular breathing. Phys Med Biol 51(22):5903–5903
Ma L, Herrmann C, Schilling K (2007) Modeling and prediction of lung tumor motion for robotic assisted radiotherapy. In: IEEE/RSJ int conf on intelligent robots and systems, IROS. IEEE, pp 189–194
Li XA, Keall PJ, Orton CG (2007) Respiratory gating for radiation therapy is not ready for prime time. Med Phys 34(3):867–870
Demachi K, Zhu H, Ishikawa M, Shirato H (2009) Predictive simulation of tumor movement for chasing radiotherapy. J of the Japan Society of Appl Electromagnetics and Mechanics 17:222–226
Ruan D (2010) Kernel density estimation-based real-time prediction for respiratory motion. Phys Med Biol 55(5):1311–1326
Ruan D (2010) Prospective detection of large prediction errors: a hypothesis testing approach. Phys Med Biol 55(13):3885–3904
Buzurovic I, Podder TK, Huang K, Yu Y (2010) Tumor motion prediction and tracking in adaptive radiotherapy. In: IEEE Int Conf on BioInformatics and BioEngineering (BIBE). IEEE, pp 273–278
Benchetrit G (2000) Breathing pattern in humans: diversity and individuality. Respir Physiol 122(2-3):123–129
Shirato H, Shimizu S, Kunieda T, Kitamura K, van Herk M, Kagei K, Nishioka T, Hashimoto S, Fujita K, Aoyama H, et al. (2000) Physical aspects of a real-time tumor-tracking system for gated radiotherapy. Int J of Radiation Oncology* Biology* Physics 48(4):1187–1195
Ren Q, Nishioka S, Shirato H, Berbeco RI (2007) Adaptive prediction of respiratory motion for motion compensation radiotherapy. Phys Med Biol 52(22):6651–6661
Riaz N, Shanker P, Wiersma R, Gudmundsson O, Mao W, Widrow B, Xing L (2009) Predicting respiratory tumor motion with multi-dimensional adaptive filters and support vector regression. Phys Med Biol 54 (19):5735–5748
Vedam S, Keall P, Docef A, Todor D, Kini V, Mohan R (2004) Predicting respiratory motion for four-dimensional radiotherapy. Med Phys 31(8):2274–2283
Murphy MJ, Pokhrel D (2009) Optimization of an adaptive neural network to predict breathing. Med Phys 36(1):40–47
Murphy MJ, Isaakson M, Jalden J (2002) Adaptive filtering to predict lung tumor motion during free breathing. In: CARS 2002 computer assisted radiology and surgery. Springer, pp 539–544
Putra D, Haas O, Mills J, Burnham K (2006) Prediction of tumour motion using interacting multiple model filter. In: 3Rd int conf on advances in medical, signal and information processing MEDSIP, IET, pp 65–69
Murphy MJ (2008) Using neural networks to predict breathing motion. In: Seventh int conf on machine learning and applications, 2008. ICMLA’08. IEEE, pp 528–532
Goodband J, Haas O, Mills J (2008) A comparison of neural network approaches for on-line prediction in igrt. Med Phys 35(3):1113–1122
Rottmann J, Berbeco R (2014) Using an external surrogate for predictor model training in real-time motion management of lung tumors. Med Phys 41(12):121706–121711
Adler Jr JR, Chang SD, Murphy MJ, Doty J, Geis P, Hancock SL (1997) The cyberknife: a frameless robotic system for radiosurgery. Stereotact Funct Neurosurg 69(1-4):124– 128
Ichiji K, Homma N, Bukovsky I, Yoshizawa M (2011) Intelligent sensing of biomedical signals-lung tumor motion prediction for accurate radiotherapy. In: IEEE Wksh on merging fields of computational intelligence and sensor technology (CompSens). IEEE, pp 35–41
Krauss A, Nill S, Oelfke U (2011) The comparative performance of four respiratory motion predictors for real-time tumour tracking. Phys Med Biol 56(16):5303–5317
Dias FM, Antunes A, Vieira J, Mota AM (2004) Implementing the levenberg-marquardt algorithm on-line: a sliding window approach with early stopping. IFAC Proc 37(16):49–54
Dias FM, Antunes A, Vieira J, Mota AM (2005) On-line training of neural networks: a sliding window approach for the levenberg-marquardt algorithm. In: Int work-conf on the interplay between natural and artificial computation. Springer, pp 577–585
Li J, Maier D, Tufte K, Papadimos V, Tucker PA (2005) No pane, no gain: efficient evaluation of sliding-window aggregates over data streams. SIGMOD Record 34(1):39–44
Bukovsky I, Homma N, Ichiji K, Cejnek M, Slama M, Benes PM, Bila J (2015) A fast neural network approach to predict lung tumor motion during respiration for radiation therapy applications. BioMed Research Int 2015:1–13
Moghadam SM, Seyyedsalehi SA (2017) Nonlinear analysis of video images using deep recurrent auto-associative neural networks for facial understanding. In: 3Rd int conf on pattern recognition and image analysis (IPRIA). IEEE, pp 20–25
Moghadam SM, Seyyedsalehi SA, Amini N (2017) Nonlinear synthesis of expression variation dynamics on video using deep dynamic bottleneck neural networks. In: 24th national and 2nd int iranian conf on biomedical engineering (ICBME). IEEE, pp 1–6
Moghadam SM, Seyyedsalehi SA (2018) Nonlinear analysis and synthesis of video images using deep dynamic bottleneck neural networks for face recognition. Neural Netw 105:304–315
Murphy MJ, Adler JR, Bodduluri M, Dooley J, Forster K, Hai J, Le Q, Luxton G, Martin D, Poen J (2000) Image-guided radiosurgery for the spine and pancreas. Computer Aided Surgery 5(4):278–288
Schweikard A, Glosser G, Bodduluri M, Murphy MJ, Adler JR (2000) Robotic motion compensation for respiratory movement during radiosurgery. Computer Aided Surgery: Official J of the Int Society for Computer Aided Surgery (ISCAS) 5(4):263–277
Schweikard A, Shiomi H, Adler J (2004) Respiration tracking in radiosurgery. Med Phys 31(10):2738–2741
Seppenwoolde Y, Berbeco RI, Nishioka S, Shirato H, Heijmen B (2007) Accuracy of tumor motion compensation algorithm from a robotic respiratory tracking system: a simulation study. Med Phys 34(7):2774–2784
Murphy MJ (2004) Tracking moving organs in real time. In: Seminars in radiation oncology, vol 14. Elsevier, pp 91–100
Dieterich S (2005) Dynamic tracking of moving tumors in stereotactic radiosurgery. Robotic Radiosurgery 1:51–63
Kilby W, Dooley J, Kuduvalli G, Sayeh S, Maurer Jr C (2010) The cyberknife®; robotic radiosurgery system in 2010. Technology in Cancer Research & Treatment 9(5):433–452
Suh Y, Dieterich S, Cho B, Keall PJ (2008) An analysis of thoracic and abdominal tumour motion for stereotactic body radiotherapy patients. Phys Med Biol 53(13):3623–3623
Hoogeman M, Prévost J B, Nuyttens J, Pöll J, Levendag P, Heijmen B (2009) Clinical accuracy of the respiratory tumor tracking system of the cyberknife: assessment by analysis of log files. Int J of Radiation Oncology* Biology* Physics 74(1):297–303
George R, Vedam SS, Chung T, Ramakrishnan V, Keall PJ (2005) The application of the sinusoidal model to lung cancer patient respiratory motion. Med Phys 32(9):2850–2861
Seppenwoolde Y, Shirato H, Kitamura K, Shimizu S, Van Herk M, Lebesque JV, Miyasaka K (2002) Precise and real-time measurement of 3D tumor motion in lung due to breathing and heartbeat, measured during radiotherapy. Int J of Radiation Oncology* Biology* Physics 53(4):822–834
Mukumoto N, Nakamura M, Akimoto M, Miyabe Y, Yokota K, Matsuo Y, Mizowaki T, Hiraoka M (2017) Impact of sampling interval in training data acquisition on intrafractional predictive accuracy of indirect dynamic tumor-tracking radiotherapy. Med Phys 44(8):3899–3908
Ansari Z, Seyyedsalehi SA (2017) Toward growing modular deep neural networks for continuous speech recognition. Neural Comput & Applic 28(1):1177–1196
Gupta M, Jin L, Homma N (2004) Static and dynamic neural networks: from fundamentals to advanced theory. Wiley, New York
Hecht-Nielsen R (1992) Theory of the backpropagation neural network. In: Neural networks for perception. Elsevier, pp 65–93
Williams RJ, Zipser D (1989) A learning algorithm for continually running fully recurrent neural networks. Neural Comput 1(2):270–280
Yun J, Mackenzie M, Rathee S, Robinson D, Fallone B (2012) An artificial neural network (ANN)-based lung-tumor motion predictor for intrafractional mr tumor tracking. Med Phys 39(7Part1):4423–4433
Phillips S (1999) Systematic minds, unsystematic models: learning transfer in humans and networks. Mind Mach 9(3):383–398
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Mafi, M., Moghadam, S.M. Real-time prediction of tumor motion using a dynamic neural network. Med Biol Eng Comput 58, 529–539 (2020). https://doi.org/10.1007/s11517-019-02096-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-019-02096-6