Artificial Neural Networks Ensemble Applied to the Electrical Impedance Tomography Problem to Determine the Cardiac Ejection Fraction

详细信息    查看全文

• 作者：Rogério G. N. Santos Filho (6)
  Luciana C. D. Campos (6)
  Rodrigo Weber dos Santos (6)
  Luis Paulo S. Barra (6)
  
• 关键词：Cardiac mechanics ; Medical applications ; Cardiac ejection fraction ; Electrical impedance tomography ; Artificial neural networks
• 刊名：Lecture Notes in Computer Science
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：1
• 期：1
• 页码：734-741
• 全文大小：135 KB
• 参考文献：1. American Heart Association: Ejection fraction heart failure measurement (2013), http://www.heart.org
  2. Kim, M., Kim, K., Kim, S.: Phase boundary estimation in two-phase flows with electrical impedance tomography. Int. Comm. Heat Transfer 31, 1105-114 (2004) CrossRef
  3. Trigo, F., Lima, R., Amato, M.: Electrical impedance tomography using extended kalman filter. I3ETBE 51, 72-1 (2004)
  4. Polydorides, N., Lionheart, W.R.B., McCann, H.: Krylov subspace iterative thechniques: On the brain activity with electrical impedance tomography. I3ETMI 21, 596-03 (2002)
  5. Seo, J., Kwon, O., Ammari, H., Woo, E.: A mathematical model for breast cancer lesion estimation: Electrical impedance technique using ts2000 commercial system. I3ETBE 51, 1898-906 (2004)
  6. Moura, F.S., Lima, R.G., Aya, J.C.C., Fleury, A.T., Amato, M.B.P.: Dynamic imaging in electrical impedance tomography of the human chest with online transition matrix identification. IEEE Trans. Biomed. Engineering 57, 422-31 (2010) CrossRef
  7. Isaacson, D., Mueller, J.L., Newell, J.C., Siltanen, S.: Imaging cardiac activity by the d-bar method for electrical impedance tomography. Physiological Measurement 27, S43 (2006) CrossRef
  8. Peters, F.C., Barra, L.P.S., dos Santos, R.W.: Determination of cardiac ejection fraction by electrical impedance tomography - numerical experiments and viability analysis. In: Allen, G., Nabrzyski, J., Seidel, E., van Albada, G.D., Dongarra, J., Sloot, P.M.A. (eds.) ICCS 2009, Part I. LNCS, vol. 5544, pp. 819-28. Springer, Heidelberg (2009) CrossRef
  9. Peters, F.C., Barra, L.P.S., Santos, R.W.: Determination of cardiac ejection fraction by electrical impedance tomography. In: Erondu, O.F. (ed.) Medical Imaging, pp. 253-70. InTech (2011)
  10. Filho, R.G.N.S., Campos, L.C.D., dos Santos, R.W., Barra, L.P.S.: Determination of cardiac ejection fraction by electrical impedance tomography using an artificial neural network. In: Castro, F., Gelbukh, A., González, M. (eds.) MICAI 2013, Part II. LNCS, vol. 8266, pp. 130-38. Springer, Heidelberg (2013) CrossRef
  11. Hansen, L.K., Salamon, P.: Neural network ensembles. IEEE Transactions on Pattern Analysis and Machine Intelligence 12, 993-001 (1990) CrossRef
  12. Opitz, D., Maclin, R.: Popular ensemble methods: An empirical study. Journal of Artificial Intelligence Research 11, 169-98 (1999)
  13. Gheyas, I.A., Smith, L.S.: A novel neural network ensemble architecture for time series forecasting. Neurocomputing 74, 3855-864 (2011) CrossRef
  14. Zhou, Z.H., Jiang, Y., Yang, Y.B., Chen, S.F.: Lung cancer cell identification based on artificial neural network ensembles. Artificial Intelligence in Medicine 24, 25-6 (2002) CrossRef
  15. Cunningham, P., Carney, J., Jacob, S.: Stability problems with artificial neural networks and the ensemble solution. Artificial Intelligence in Medicine 20, 217-25 (2000) CrossRef
  16. Hashem, S.: Optimal linear combinations of neural networks. Neural Networks 10, 599-14 (1997) CrossRef
  17. Maclin, R., Shavlik, J.W.: Combining the predictions of multiple classifiers: Using competitive learning to initialize neural networks. In Proceedings of the Fourteenth Internationa
• 作者单位：Rogério G. N. Santos Filho (6)
  Luciana C. D. Campos (6)
  Rodrigo Weber dos Santos (6)
  Luis Paulo S. Barra (6)
  
  6. Federal University of Juiz de Fora, Juiz de Fora, Brazil
  
• ISSN：1611-3349

文摘

Cardiac Ejection Fraction (EF) is a parameter that indicates how much blood the heart is pumping to the body. It is a very important clinical parameter since it is highly correlated to the functional status of the heart. To measure the EF, diverse non-invasive techniques have been applied such as Magnetic Resonance. The method studied in this work is the Electrical Impedance Tomography (EIT) which consists in generate an image of the inner body using measures of electrical potentials - some electrodes are attached to the body boundary and small currents are applied in the body, the potentials are then measured in these electrodes. This technique presents lower costs and a high portability compared to others. It can be done in the patient bed and does not use ionizing radiation. The EIT problem consists in define the electrical distribution of the inner parts that results in the potentials measured. Therefore, it is considered as a non-linear inverse problem. To solve that, this work propose the application of an Artificial Neural network (ANN) Ensemble since it is simple to understand and implement. Our results show that the ANN Ensemble presents fast and good results, which are crucial for the continuous monitoring of the heart.