×

The combination of self-organizing feature maps and support vector regression for solving the inverse ECG problem. (English) Zbl 1381.92056

Summary: Noninvasive electrical imaging of the heart aims to quantitatively reconstruct transmembrane potentials (TMPs) from body surface potentials (BSPs), which is a typical inverse problem. Classically, electrocardiography (ECG) inverse problem is solved by regularization techniques. In this study, it is treated as a regression problem with multi-inputs (BSPs) and multi-outputs (TMPs). Then the resultant regression problem is solved by a hybrid method, which combines the support vector regression (SVR) method with self-organizing feature map (SOFM) techniques. The hybrid SOFM-SVR method conducts a two-step process: SOFM algorithm is used to cluster the training samples and the individual SVR method is employed to construct the regression model. For each testing sample, the cluster operation can effectively improve the efficiency of the regression algorithm, and also helps the setup of the corresponding SVR model for the TMPs reconstruction. The performance of the developed SOFM-SVR model is tested using our previously developed realistic heart-torso model. The experiment results show that, compared with traditional single SVR method in solving the inverse ECG problem, the proposed method can reduce the cost of training time and improve the reconstruction accuracy in solving the inverse ECG problem.

MSC:

92C55 Biomedical imaging and signal processing
62H30 Classification and discrimination; cluster analysis (statistical aspects)

Software:

LIBSVM; GPUSVM
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Rudy, Y.; Messinger-Rapport, B. J., The inverse problem in electrocardiography: solutions in terms of epicardial potentials, CRC Crit. Rev. Biomed. Eng., 16, 215-268 (1998)
[2] MacLeod, R. S.; Brooks, D. H., Recent progress in inverse problems in electrocardiology, IEEE Eng. Med. Biol. Soc. Mag., 17, 73-83 (1998)
[3] Cheng, L. K.; Bodley, J. M.; Pullan, A. J., Comparison of potential and activation-based formulations for the inverse problem of electrocardiology, IEEE Trans. Biomed. Eng., 50, 11-22 (2003)
[4] Ramanathan, C.; Ghamen, R.; Jia, P.; Ryu, K.; Y, Noninvasive electrocardiographic imaging for cardiac electrophysiology and arrhythmia, Nature Med., 10, 422-428 (2004)
[5] van Dam, P. M., Non-invasive imaging of cardiac activation and recovery, Ann. Biomed. Eng., 37, 1739-1756 (2009)
[6] Ghodrati, A.; Brooks, D. H.; Tadmor, G.; MacLeod, R. S., Wavefront based models for inverse electrocardiography, IEEE Trans. Biomed. Eng., 53, 1821-1831 (2006)
[7] Liu, Z.; Liu, C.; He, B., Noninvasive reconstruction of three-dimensional ventricular activation sequence from the inverses solution of distributed equivalent current density, IEEE Trans. Biomed. Eng., 53, 1307-1318 (2006)
[8] Messnarz, B.; Tilg, B.; Modre, R.; Fischer, G.; Hanser, F., A new spatiotemporal regularization approach for reconstruction of cardiac transmembrane potential patterns, IEEE Trans. Biomed. Eng., 51, 273-281 (2004)
[9] Messnarz, B.; Seger, M.; Modre, R.; Fischer, G.; Hanser, F.; Tilg, B., A comparison of noninvasive reconstruction of epicardial versus transmembrane potentials in consideration of the null space, IEEE Trans. Biomed. Eng., 51, 1609-1618 (2004)
[10] Nielsen, B. F.; Cai, X.; Lysaker, M., On the possibility for computing the transmembrane potential in the heart with a one shot method: an inverse problem, Math. Biosci., 210, 523-553 (2007) · Zbl 1134.92021
[11] Jiang, M.; Xia, L.; Shou, G.; Wei, Q.; Liu, F.; Crozier, S., Effect of cardiac motion on solution of the electrocardiography inverse problem, IEEE Trans. Biomed. Eng., 56, 923-931 (2009)
[12] Jiang, M.; Xia, L.; Huang, W.; Shou, G.; Liu, F.; Crozier, S., The application of subspace preconditioned LSQR algorithm for solving the electrocardiography inverse problem, Med. Eng. Phys., 31, 979-985 (2009)
[13] Shou, G.; Xia, L.; Jiang, M.; Wei, Q.; Liu, F.; Crozier, S., Truncated total least squares: a new regularization method for the solution of ECG inverse problems, IEEE Trans. Biomed. Eng., 55, 1327-1335 (2008)
[14] Shou, G.; Xia, L.; Liu, F.; Jiang, M.; Crozier, S., On epicardial potential reconstruction using regularization schemes with the \(L 1\)-norm data term, Phys. Med. Biol., 56, 57-72 (2011)
[15] Wang, L.; Qin, J.; Wong, T.; Heng, P. A., Application of \(L 1\)-norm regularization to epicardial potential reconstruction based on gradient projection, Phys. Med. Biol., 56, 6291-6310 (2011)
[16] Vapnik, V., An overview of statistical learning theory, IEEE Trans. Neural Netw., 10, 988-999 (1999)
[17] Cristianini, N.; Taylor, J., An Introduction to Support Vector Machines (2000), Cambridge University Press: Cambridge University Press Cambridge, UK
[18] Smola, A.; Schölkopf, B., A tutorial on support vector regression, Statist. Comput., 14, 199-222 (2004)
[19] Jiang, M.; Zhu, L.; Wang, Y.; Shou, G.; Liu, F.; Crozier, S., Application of kernel principal component analysis and support vector regression for reconstruction of cardiac transmembrane potential, Phys. Med. Biol., 56, 1727-1742 (2011)
[20] Jiang, M.; Liu, F.; Wang, Y.; Shou, G.; Huang, W.; Zhang, H., A hybrid model of maximum margin clustering method and support vector regression for noninvasive electrocardiographic imaging, Comput. Math. Methods Med. (2012) · Zbl 1261.92027
[21] Kim, K., Financial time series forecasting using support vector machines, Neurocomputing, 55, 307-319 (2003)
[22] Thissen, U.; Van Brakel, R.; De Weijer, A.; Melssen, W.; Buydens, L., Using support vector machines for time series prediction, Chemometr. Intell. Lab. Syst., 69, 35-49 (2003)
[23] Mostafa, M. M., Clustering the ecological footprint of nations using Kohonen’s self-organizing maps, Expert Syst. Appl., 37, 2747-2755 (2010)
[24] Ismail, S.; Shabri, A.; Samsudin, R., A hybrid model of self-organizing maps (SOM) and least square support vector machine (LSSVM) for time-series forecasting, Expert Syst. Appl., 38, 10574-10578 (2011)
[25] Hsu, S. H.; Hsieh, J. J.P.; Chih, T. C.; Hsu, K. C., A two-stage architecture for stock price forecasting by integrating self-organizing map and support vector regression, Expert Syst. Appl., 36, 7947-7951 (2009)
[26] Wang, L.; Mu, Z.; Guo, H., Combining self-organizing feature map with support vector regression based on expert system, Atac Autom. Sinica, 31, 612-619 (2005)
[27] Cao, L., Support vector machines experts for time series forecasting, Neurocomputing, 51, 321-339 (2003)
[28] Huang, C. L.; Tsai, C. Y., A hybrid SOFM-SVR with a filter-based feature selection for stock market forecasting, Expert Syst. Appl., 36, 1529-1539 (2009)
[29] Li, C.; Liu, F.; Xie, Y., Face recognition using self-organizing feature maps and support vector machines, Proc. of ICCIMA, 2003, 27-30 (2003)
[31] Steinwart, I., On the influence of the kernel on the consistency of support vector machines, J. Mach. Learn. Res., 2, 67-93 (2002) · Zbl 1009.68143
[32] Tay, F. E.H.; Cao, L., Application of support vector machines in financial time series forecasting, Omega, 29, 309-317 (2001)
[33] Schölkopf, B.; Smola, A. J., Learning with Kernels (2002), MIT Press: MIT Press Cambridge, MA
[35] Kohonen, T., Self-organized Maps (1997), Springer: Springer New York
[36] Lu, W.; Xia, L., Computer simulation of epicardial potentials using a heart-torso model with realistic geometry, IEEE Trans. Biomed. Eng., 43, 211-217 (1996)
[37] Xia, L.; Huo, M.; Wei, Q.; Liu, F.; Crozier, S., Analysis of cardiac ventricular wall motion based on a three-dimensional electromechanical biventricular model, Phys. Med. Biol., 50, 1901-1917 (2005)
[39] Athanasopoulos, A.; Dimou, A.; Mezaris, V.; Kompatsiaris, I., GPU acceleration for support vector machines [C], (Proc. 12th International Workshop on Image Analysis for Multimedia Interactive Services. Proc. 12th International Workshop on Image Analysis for Multimedia Interactive Services, (WIAMIS 2011) (2011), Delft: Delft The Netherlands)
[40] Li, Q.; Salman, R.; Test, E.; Strack, R.; Kecman, V., GPUSVM: a comprehensive CUDA based support vector machine package, Cent. Eur. J. Comput. Sci., 4, 387-405 (2011) · Zbl 1253.68282
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.