Abstract
Linear models such as factor analysis, independent component analysis (ICA), and nonnegative matrix factorization (NMF) were successfully applied to dynamic myocardial \(H_{2}^{15}O\) PET image data, showing that meaningful factor images and appropriate time activity curves were estimated for the quantification of myocardial blood flow. In this paper we apply the ensemble ICA to dynamic myocardial \(H_{2}^{15}O\) PET image data. The benefit of the ensemble ICA (or Bayesian ICA) in such a task is to decompose the image data into a linear sum of independent components as in ICA, with imposing the nonnegativity constraints on basis vectors as well as encoding variables, through the rectified Gaussian prior. We show that major cardiac components are separated successfully by the ensemble ICA method and blood flow could be estimated in 15 patients. Mean myocardial blood flow was 1.2 ± 0.40 ml/min/g in rest, 1.85 ± 1.12 ml/min/g in stress state. Blood flow values obtained by an operator in two different occasion were highly correlated (r=0.99). In myocardium component images, the image contrast between left ventricle and myocardium was 1:2.7 in average.
An erratum to this chapter can be found at http://dx.doi.org/10.1007/11550907_163 .
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ahn, J.Y., Lee, D.S., Lee, J.S., Kim, S.K., Cheon, G.J., Yeo, J.S.: Quantification of regional myocardial blood flow using dynamic \(H_2 ^{15}O\) PET and factor analysis. J. Nucl. Med. 42, 782–787 (2001)
Lee, J.S., Lee, D.S., Ahn, J.Y., Cheon, G.J., Yeo, J.S.: Blind separation of cardiac components and extraction of input function from \(H_2 ^{15}O\) dynamic myocardial PET using independent component analysis. J. Nucl. Med. 42, 938–943 (2001)
Lee, J.S., Lee, D.D., Choi, S., Lee, D.S.: Application of non-negative matrix factorization to dynamic positron emission tomography. In: Proc. ICA, San Diego, California, pp. 629–632 (2001)
Iida, H., Tamura, Y., Kitamura, K., Eberl, P.M.B.S., Ono, Y.: Histochemical correlates of 15 O-water-perfusable tissue fraction in experimental canine studies of old myocardial infarction. J. Nucl. Med. 41, 1737–1745 (2000)
Iida, H., Kanno, I., Takahashi, A.: Measurement of absolute myocardial blood flow with \(H_2 ^{15}O\) and dynamic positron-emission tomography strategy for quantification in relation to the partial volume effect. Circulation 78, 104–115 (1998)
Kaufmann, P.A., Gnecchi-Ruscone, T., Yap, J.T., Rimoldi, O., Camici, P.G.: Assessment of the reproducibility of baseline and hyperemic myocardial blood flow measurements with 15 O-labeled water and pet. J. Nucl. Med. 40, 1848–1856 (1999)
Miskin, J.W., MacKay, D.J.C.: Ensemble learning for blind source separation. In: Roberts, S., Everson, R. (eds.) Independent Component Analysis: Principles and Practice, pp. 209–233. Cambridge University Press, Cambridge (2001)
Miskin, J.W., MacKay, D.J.C.: Application of ensemble learning to infra-red imaging. In: Proc. ICA, pp. 399–404 (2000)
Schafers, K.P., Spinks, T.J., Camici, P.G., Rhodes, P.M.B.C.G., Law, M.P.: Absolute quantification of myocardial blood flow with \(H_2 ^{15}O\) and 3-dimensional PET: an experimental validation. J. Nucl. Med. 43, 1031–1040 (2002)
Choi, S., Cichocki, A., Park, H.M., Lee, S.Y.: Blind source separation and independent component analysis: A review. Neural Information Processing - Letters and Review 6, 1–56 (2005)
Lee, D.D., Seung, H.S.: Learning the parts of objects by non-negative matrix factorization. Nature 401, 788–791 (1999)
Schaefer, W.M., Nowak, B., Kaiser, H.J., Block, K.C.K.S., Dahl, J.V.: Comparison of microsphere-equivalent blood flow (15 O-water PET) and relative perfusion (99m Tc-Tetrofosmin SPECT) in myocardium showing metabolism-perfusion mismatc. J. Nucl. Med. 44, 33–39 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lee, B.I., Lee, J.S., Lee, D.S., Choi, S. (2005). Myocardial Blood Flow Quantification in Dynamic PET: An Ensemble ICA Approach. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds) Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005. ICANN 2005. Lecture Notes in Computer Science, vol 3697. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550907_113
Download citation
DOI: https://doi.org/10.1007/11550907_113
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28755-1
Online ISBN: 978-3-540-28756-8
eBook Packages: Computer ScienceComputer Science (R0)