Genetic algorithm-based regularization parameter estimation for the inverse electrocardiography problem using multiple constraints

In inverse electrocardiography, the goal is to estimate cardiac electrical sources from potential measurements on the body surface. It is by nature an ill-posed problem, and regularization must be employed to obtain reliable solutions. This paper employs the multiple constraint solution approach proposed in Brooks et al. (IEEE Trans Biomed Eng 46(1):3–18, 1999) and extends its practical applicability to include more than two constraints by finding appropriate values for the multiple regularization parameters. Here, we propose the use of real-valued genetic algorithms for the estimation of multiple regularization parameters. Theoretically, it is possible to include as many constraints as necessary and find the corresponding regularization parameters using this approach. We have shown the feasibility of our method using two and three constraints. The results indicate that GA could be a good approach for the estimation of multiple regularization parameters.

[1]  Y. Rudy,et al.  The use of temporal information in the regularization of the inverse problem of electrocardiography , 1992 .

[2]  F. Liu,et al.  Application of kernel principal component analysis and support vector regression for reconstruction of cardiac transmembrane potentials , 2011, Physics in medicine and biology.

[3]  L. Xia,et al.  A comparison of different choices for the regularization parameter in inverse electrocardiography models , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  R.S. MacLeod,et al.  Map3d: interactive scientific visualization for bioengineering data , 1993, Proceedings of the 15th Annual International Conference of the IEEE Engineering in Medicine and Biology Societ.

[5]  Rob S. MacLeod,et al.  An Admissible Solution Approach to Inverse Electrocardiography , 1998, Annals of Biomedical Engineering.

[6]  Francisco Herrera,et al.  Tackling Real-Coded Genetic Algorithms: Operators and Tools for Behavioural Analysis , 1998, Artificial Intelligence Review.

[7]  R. Macleod,et al.  Multiply constrained inverse electrocardiography: combining temporal, multiple spatial, and iterative regularization , 1994, Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[8]  Y. Rudy,et al.  The use of temporal information in the regularization of the inverse problem of electrocardiography , 1990, IEEE Transactions on Biomedical Engineering.

[9]  Rob S. MacLeod,et al.  Inverse electrocardiography by simultaneous imposition of multiple constraints , 1999, IEEE Transactions on Biomedical Engineering.

[10]  L. Xia,et al.  The Use of Genetic Algorithms for Solving the Inverse Problem of Electrocardiography , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[11]  Bin He,et al.  Noninvasive Estimation of Global Activation Sequence Using the Extended Kalman Filter , 2011, IEEE Transactions on Biomedical Engineering.

[12]  Danny C. Sorensen,et al.  Solving the inverse problem of electrocardiography using a Duncan and Horn formulation of the Kalman filter , 2004, IEEE Transactions on Biomedical Engineering.

[13]  ProblemsPer Christian HansenDepartment.  The L-curve and its use in the numerical treatment of inverse problems , 2000 .

[14]  Dana H. Brooks,et al.  Wavefront-based models for inverse electrocardiography , 2006, IEEE Transactions on Biomedical Engineering.

[15]  L. Xia,et al.  Combination of the LSQR method and a genetic algorithm for solving the electrocardiography inverse problem. , 2007, Physics in medicine and biology.

[16]  Umit Aydin,et al.  A Kalman filter-based approach to reduce the effects of geometric errors and the measurement noise in the inverse ECG problem , 2011, Medical & Biological Engineering & Computing.

[17]  Fred Greensite,et al.  The temporal prior in bioelectromagnetic source imaging problems , 2003, IEEE Transactions on Biomedical Engineering.

[18]  Mark Potse,et al.  Cardiac anisotropy in boundary-element models for the electrocardiogram , 2009, Medical & Biological Engineering & Computing.

[19]  R. Hren,et al.  Noninvasive characterisation of multiple ventricular events using electrocardiographic imaging , 2006, Medical and Biological Engineering and Computing.

[20]  R S MacLeod,et al.  A possible mechanism for electrocardiographically silent changes in cardiac repolarization. , 1998, Journal of electrocardiology.

[21]  R. Gulrajani,et al.  A new method for regularization parameter determination in the inverse problem of electrocardiography , 1997, IEEE Transactions on Biomedical Engineering.

[22]  Ling Xia,et al.  The application of subspace preconditioned LSQR algorithm for solving the electrocardiography inverse problem. , 2009, Medical engineering & physics.

[23]  R. Gulrajani.  The forward and inverse problems of electrocardiography. , 1998, IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society.

[24]  M. N. Morrow,et al.  The Effects of Thoracic Inhomogeneities on the Relationship Between Epicardial and Torso Potentials , 1986, IEEE Transactions on Biomedical Engineering.