Abstract
To reduce the radiation exposure of personnel during an interventional procedure for arrhythmia, a robot has been developed and implemented herein for use in interventional procedures. Studies on the control of an electrophysiology catheter by robots are being conducted. However, controlling a catheter using a robot has limited precision owing to external forces subjected on the catheter due to blood flow and pulse inside a heart. This study implements a reinforcement learning method for automated control of a catheter by a robot. Using the reinforcement learning method, this study aims to show that such a robot can learn to manipulate a catheter to reach a target in a simulated environment and subsequently control a catheter in an actual environment. Randomization noise is used during the simulation to reduce the differences between the simulation and actual learning environments. Each environment is implemented with different movement values depending on insertion angles and steps of the catheter model. When the results from the simulated learning model are implemented in the actual environment, the success rate of catheter reaching the designated target is 73 %. In addition, the noise-implemented model shows that the success rate can be increased up to 87 %. Through these experiments, the study verifies that a simulated learning model can be implemented in a robot system to control an actual catheter as well as that the success rate of the model can be increased using randomization noise.
Similar content being viewed by others
Abbreviations
- P r[X]:
-
Expectation of a random variable
- ≐:
-
Equality relationship that is true by definition
- Argmax :
-
A value of x at which x takes its maximal value
- \(E\left[ {\mathop X\limits^x } \right]\) :
-
Expectation of a random variable
- S :
-
Set of all states
- A :
-
Set of all actions
- R :
-
Set of all possible rewards
- γ:
-
Discount-rate parameter
- π :
-
Policy
- s :
-
State
- a :
-
An action
- r :
-
A reward
- t :
-
Discrete time step
- S t :
-
States at the time step t
- A t :
-
An action at the time step t
- R t :
-
A reward at the time step t
- Q(s,a):
-
Expected value from state and action
- A(s,a):
-
Expected advantage value from state and action under policy π
- V (s,a):
-
Expected state value from state and action under policy π
References
K. H. Kuck, M. Schluter, M. Geige, J. Siebels and W. Duckeck, Radiofrequency current catheter ablation of accessory atrio-ventricular pathways, The Lancet, 337 (8757) (1991) 1557–1561.
W. M. Jackman, X. Wang, K. J. Friday, C. A. Roman, K. P. Moulton, K. J. Beckman and P. D. Margolis, Catheter ablation of accessory atrioventricular pathways (Wolff–Parkinson–White syndrome) by radiofrequency current, New England Journal of Medicine, 324 (23) (1991) 1605–1611.
R. J. Kanter, J. Papagiannis, M. P. Carboni, R. M. Ungerleider, W. E. Sanders and J. M. Wharton, Radiofrequency catheter ablation of supraventricular tachycardia substrates after Mustard and Senning operations for d-transposition of the great arteries, Journal of the American College of Cardiology, 35 (2) (2000) 428–441.
E. Vano, L. Gonzalez, J. M. Fernandez, F. Alfonso and C. Macaya, Occupational radiation doses in interventional cardiology: A 15-year follow-up, The British Journal of Radiology, 79 (941) (2006) 383–388.
Catheter Robotics, Inc., Amigo Remote Catheter System, http://www.catheterrobotics.com/.
Hansen Medical, Inc., Sensei X Robotic Catheter System, http://hansenmedical.com (2016).
P. M. Loschak, A. Degirmenci and R. D. Howe, Predictive filtering in motion compensation with steerable cardiac catheters, IEEE International Conference on Robotics and Automation, Singapore (2017) 4830–4836.
M. Khoshnam and R. V. Patel, Robotics-assisted control of steerable ablation catheters based on the analysis of tendonsheath transmission mechanisms, IEEE/ASME Transactions on Mechatronics, 22 (3) (2017) 1473–1484.
Y. Thakur, J. S. Bax, D. W. Holdsworth and M. Drangova, Design and performance evaluation of a remote catheter navigation system, IEEE Transactions on Biomedical Engineering, 56 (7) (2009) 1901–1908.
R. Ginhoux, J. Gangloff, M. de Mathelin, L. Soler, M. M. A. Sanchez and J. Marescaux, Active filtering of physiological motion in robotized surgery using predictive control, IEEE Transactions on Robotics, 21 (1) (2005) 67–79.
T. N. Do, T. Tjahjowidodo, M. W. S. Lau and S. J. Phee, Nonlinear friction modelling and compensation control of hysteresis phenomena for a pair of tendon-sheath actuated surgical robots, Mechanical Systems and Signal Processing, 60 (2015) 770–784.
S. B. Kesner and R. D. Howe, Robotic catheter cardiac ablation combining ultrasound guidance and force control, The International Journal of Robotics Research, 33 (4) (2014) 631–644.
Y. Ganji and F. Janabi-Sharifi, Catheter kinematics for intracardiac navigation, IEEE Transactions on Biomedical Engineering, 56 (3) (2009) 621–632.
A. Degirmenci, P. M. Loschak, C. M. Tschabrunn, E. Anter and R. D. Howe, Compensation for unconstrained catheter shaft motion in cardiac catheters, IEEE International Conference on Robotics and Automation Stockholm, Sweden (2016) 4436–4442.
S. Levine, C. Finn, T. Darrell and P. Abbeel, End-to-end training of deep visuomotor policies, The Journal of Machine Learning Research, 17 (1) (2016) 1334–1373.
J. Matas, S. James and A. J. Davison, Sim-to-real reinforcement learning for deformable object manipulation, CoRL 2018 (2018).
J. Tan, T. Zhang, E. Coumans, A. Iscen, Y. Bai, D. Hafner and V. Vanhoucke, Sim-to-real: Learning agile locomotion for quadruped robots, arXiv preprint arXiv:1804.10332 (2018).
R. Antonova, S. Cruciani, C. Smith and D. Kragic, Reinforcement learning for pivoting task, arXiv preprint arXiv:1703.00472 (2017).
A. A. Rusu, M. Vecerik, T. Rothörl, N. Heess, R. Pascanu and R. Hadsell, Sim-to-real robot learning from pixels with progressive nets, arXiv preprint arXiv:1610.04286 (2016).
Y. Tsurumine, Y. Cui, E. Uchibe and T. Matsubara, Deep reinforcement learning with smooth policy update: Application to robotic cloth manipulation, Robotics and Autonomous Systems, 112 (2019) 72–83.
Y. Chebotar, A. Handa, V. Makoviychuk, M. Macklin, J. Issac, N. Ratliff and D. Fox, Closing the sim-to-real loop: Adapting simulation randomization with real world experience, arXiv preprint arXiv:1810.05687 (2018).
M. Hessel, J. Modayil, H. Van Hasselt, T. Schaul, G. Ostrovski, W. Dabney and D. Silver, Rainbow: Combining improvements in deep reinforcement learning, Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, Louisiana, USA (2018).
C. J. Watkins and P. Dayan, Q-learning, Machine Learning, 8 (3-4) (1992) 279–292.
L. J. Lin, Reinforcement Learning for Robots Using Neural Networks, School of Computer Science, Carnegie-Mellon Univ., Pittsburgh, PA (1993) (No. CMU-CS-93-103).
P. Kormushev, S. Calinon and D. Caldwell, Reinforcement learning in robotics: Applications and real-world challenges, Robotics, 2 (3) (2013) 122–148.
R. S. Sutton and A. G. Barto, Introduction to Reinforcement Learning, Cambridge: MIT Press, 4 (2) (1998).
T. Hester, M. Vecerik, O. Pietquin, M. Lanctot, T. Schaul, B. Piot and G. Dulac-Arnold, Deep q-learning from demonstrations, Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, Louisiana, USA (2018).
V. Mnih, K. Kavukcuoglu, D. Silver, A. A. Rusu, J. Veness, M. G. Bellemare and S. Petersen, Human-level control through deep reinforcement learning, Nature, 518 (7540) (2015) 529.
S. Ruder, An overview of gradient descent optimization algorithms, arXiv preprint arXiv: 1609.04747 (2016).
Z. Wang, T. Schaul, M. Hessel, H. Hasselt, M. Lanctot and N. Freitas, Dueling network architectures for deep reinforcement learning, International Conference on Machine Learning New York City, New York, USA (2016) 1995–2003.
L. Wang, H. R. Weerasooriya and M. J. E. Davis, Radiofrequency catheter ablation of atrial tachycardia, Australian and New Zealand Journal of Medicine, 25 (2) (1995) 127–132.
W. E. Sanders, R. A. Sorrentino, R. A. Greenfield, H. Shenasa, M. E. Hamer and J. M. Wharton, Catheter ablation of sinoatrial node reentrant tachycardia, Journal of the American College of Cardiology, 23 (4) (1994) 926–934.
Z. Hu, J. Won, Y. Moon, S. Park and J. Choi, Design of a robotic catheterization platform with use of commercial ablation catheter, 2017 Design of Medical Devices Conference, American Society of Mechanical Engineers Minneapolis, Minnesota, USA (2017) V001T08A005–V001T08A005.
B. Yu, J. D. G. Fernández and T. Tan, Probabilistic kinematic model of a robotic catheter for 3D position control, Soft Robotics, 6 (2) (2019) 184–194.
Unity, http://www.unity3d.com.
Y. Ganji and F. Janabi-Sharifi, Catheter kinematics and control to enhance cardiac ablation, Optomechatronic Actuators, Manipulation, and Systems Control, International Society for Optics and Photonics, 6374 (2006) 63740.
F. Zhang, J. Leitner, M. Milford, B. Upcroft and P. Corke, Towards vision-based deep reinforcement learning for robotic motion control, arXiv preprint arXiv:1511.03791 (2015).
E. Rodrigues Gomes and R. Kowalczyk, Dynamic analysis of multiagent Q-learning with ε-greedy exploration, Proceedings of the 26th Annual International Conference on Machine Learning (2009) 369–376.
V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra and M. Riedmiller, Playing atari with deep reinforcement learning, arXiv preprint arXiv:1312.5602 (2013).
S. B. Kesner and R. D. Howe, Position control of motion compensation cardiac catheters, IEEE Transactions on Robotics, 27 (6) (2011) 1045–1055.
J. Tobin, R. Fong, A. Ray, J. Schneider, W. Zaremba and P. Abbeel, Domain randomization for transferring deep neural networks from simulation to the real world, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2017) 23–30.
X. B. Peng, M. Andrychowicz, W. Zaremba and P. Abbeel, Sim-to-real transfer of robotic control with dynamics randomization, IEEE International Conference on Robotics and Automation, Brisbane, Australia (2018) 1–8.
Acknowledgments
This research was supported by a grant of the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (HI17C2410) and the Ministry of Trade, Industry and Energy, Republic of Korea (10077502).
Author information
Authors and Affiliations
Corresponding author
Additional information
Recommended by Editor Ja Choon Koo
Hyeonseok You is in M.S. course in Department of Biomedical College of Medicine, University of Ulsan, Korea. He received the B.S. degree in Department of Biomedical College of Medicine, University of Ulsan, Korea. He current research interests include machine learning and, reinforcement learning, robot control, catheter, medical training simulation system in virtual reality.
Eunkyung Bae is in Ph.D. course in Department of Biomedical Engineering, College of Medicine, University of Ulsan, Korea. She received the B.S. and M.S. degrees in Biomedical Engineering from Yonsei University, Korea. Her current research interests include analyze bio-signal and design the rehabilitation training system and medical training simulation system in virtual reality.
Jihoon Kweon received the B.S. and Ph.D. degrees in Mechanical Engineering from Seoul National University, Seoul, South Korea, in 2004 and 2011, respectively. He is currently an Associate Professor at the Asan Institute for Life Sciences, Asan Medical Center, Seoul. His research interests include biomimetics, Computational fluid dynamics, Hemodynamic fluid dynamics.
Youngjin Moon received the B.S. and M.S. degrees in control and mechanical engineering and mechanical and precision engineering from Pusan National University, Busan, South Korea, in 1996 and 1996, respectively, and the Ph.D. degree in mechanical and aerospace engineering from the University of Florida, Gainesville, FL, USA, in 2011. He is with Asan Medical Center and University of Ulsan College of Medicine, Seoul, South Korea as a Research Assistant Professor. His research interests include design and analysis of kinematic mechanisms, and robotic systems with medical purpose such as surgery, intervention, and rehabilitation.
Jaesoon Choi received the B.S. degree in control and instrumentation engineering and the M.S. and Ph.D. degrees in biomedical engineering from Seoul National University, Seoul, South Korea, in 1995, 1997 and 2003, respectively. He had predoctoral training at Lerner Research Institute, Cleveland Clinic, USA, from 1999 to 2000. From 2003 to 2006, he worked as a Staff Researcher at National Cancer Center, Seoul. From 2007 to 2012, he was a Research Professor at College of Medicine, Korea University, Seoul. He is currently an Associate Professor at Asan Medical Center, Seoul. His research interests include computer-aided surgery and intervention.
Rights and permissions
About this article
Cite this article
You, H., Bae, E., Moon, Y. et al. Automatic control of cardiac ablation catheter with deep reinforcement learning method. J Mech Sci Technol 33, 5415–5423 (2019). https://doi.org/10.1007/s12206-019-1036-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-019-1036-0