An efficient cardiac mapping strategy for radiofrequency catheter ablation with active learning
Tóm tắt
A major challenge in radiofrequency catheter ablation procedures is the voltage and activation mapping of the endocardium, given a limited mapping time. By learning from expert interventional electrophysiologists (operators), while also making use of an active-learning framework, guidance on performing cardiac voltage mapping can be provided to novice operators or even directly to catheter robots. A learning from demonstration (LfD) framework, based upon previous cardiac mapping procedures performed by an expert operator, in conjunction with Gaussian process (GP) model-based active learning, was developed to efficiently perform voltage mapping over right ventricles (RV). The GP model was used to output the next best mapping point, while getting updated towards the underlying voltage data pattern as more mapping points are taken. A regularized particle filter was used to keep track of the kernel hyperparameter used by GP. The travel cost of the catheter tip was incorporated to produce time-efficient mapping sequences. The proposed strategy was validated on a simulated 2D grid mapping task, with leave-one-out experiments on 25 retrospective datasets, in an RV phantom using the Stereotaxis Niobe® remote magnetic navigation system, and on a tele-operated catheter robot. In comparison with an existing geometry-based method, regression error was reduced and was minimized at a faster rate over retrospective procedure data. A new method of catheter mapping guidance has been proposed based on LfD and active learning. The proposed method provides real-time guidance for the procedure, as well as a live evaluation of mapping sufficiency.
Tài liệu tham khảo
Arulampalam M, Maskell S, Gordon N, Clapp T (2001) A tutorial on particle filters for online. Non-linear/non-Gausssian Bayesin tracking. IEEE 50(2):174–188
Bhakta D, Address M, Avenue C (2008) Principles of electroanatomic mapping. Indian Pacing Electrophysiol J 8(1):32–50
Cheung CL, Lee KH, Guo Z, Dong Z, Leong MCW, Chen Y, Lee APW, Kwok KW (2016) Kinematic-model-free positional control for robot-assisted cardiac catheterization. In: Proceedings of the Hamlyn symposium on medical robotics, pp 80–81
Gordon NJ, Salmond DJ, Smith AF (1993) Novel approach to nonlinear/non-Gaussian Bayesian state estimation. In: IEE Proceedings F-radar and signal processing, vol 140, pp 107–113. IET
Ko CW, Lee J, Queyranne M (1995) An exact algorithm for maximum entropy sampling. Oper Res 43(4):684–691
Krause A (2007) Nonmyopic active learning of Gaussian processes: an exploration exploitation approach. In: Proceedings of the IEEE international conference on machine learning, pp 449–456
Macke JH, Gerwinn S, White LE, Kaschube M, Bethge M (2011) Gaussian process methods for estimating cortical maps. NeuroImage 56(2):570–581
Musso C, Oudjane N, Gland FL (2001) Improving regularized particle filters
Nemhauser GL, Wolsey LA, Fisher ML (1978) An analysis of approximations for maximizing submodular set functionsi. Math Program 14(1):265–294
Rasmussen CE, Nickisch H (2010) Gaussian processes for machine learning (GPML) toolbox. J Mach Learn Res 11:3011–3015
Rasmussen CE, Williams CKI (2006) Regression. Gaussian processes for Machine Learning, Chapter 2
Thompson WR (1933) On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika 25(3/4):285–294
Wallman M, Smith NP, Rodriguez B (2014) Computational methods to reduce uncertainty in the estimation of cardiac conduction properties from electroanatomical recordings. Med Image Anal 18(1):228–240
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612
Zhou XY, Ernst S, Lee SL (2016) Path planning for robot-enhanced cardiac radiofrequency catheter ablation. In: 2016 IEEE international conference on robotics and automation (ICRA), pp 4172–4177. IEEE