Abstract
Ensemble independent component analysis (ICA) is a Bayesian multivariate data analysis method which allows various prior distributions for parameters and latent variables, leading to flexible data fitting. In this paper we apply ensemble ICA with a rectified Gaussian prior to dynamic \( H^{{15}}_{2} O \) positron emission tomography (PET) image data, emphasizing its clinical usefulness by showing that major cardiac components are successfully extracted in an unsupervised manner and myocardial blood flow can be estimated in 15 among 20 patients. Detailed experiments and results are illustrated.
Similar content being viewed by others
References
J.Y. Ahn, D.S. Lee, J.S. Lee, S.K. Kim, G.J. Cheon, J.S. Yeo, and et al., “Quantification of Regional Myocardial Blood Flow Using \( H^{{15}}_{2} \) PET and Factor Analysis,” J. Nucl. Med., vol. 42, 2001, pp. 782–787.
P.Chareonthaitawee, P.A. Kaufmann, O.Rimoldi and P.G. Camici, “Heterogeneity of Resting and Hyperemic Myocardial Blood Flow in Healthy Humans,” Cardiovasc. Res., vol. 50, 2001, pp. 151–161.
S. Choi, A. Cichocki, H.M. Park and S.Y. Lee, “Blind Source Separation and Independent Component Analysis: A Review,” Neural Information Processing—Letters and Review, vol. 6, no. 1, 2005, pp. 1–57.
A. Cichocki and S. Amari, “Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications,” Wiley, 2002.
K.H. Hwang, D.S. Lee, B.I. Lee, J.S. L. H.Y. Lee, J.K. Chung and et al., “Evaulation of Endothelium-Dependent Myocardial Perfusion Reserve in Healthy Smokers: Cold Pressor Test Using \( H^{{15}}_{2} O \) PET,” Korean J. Nucl. Med., vol. 38, 2004, pp. 21–29.
A. Hyvärinen, J. Karhunen and E. Oja, “Independent Component Analysis,” Wiley, 2001.
H. Iida, I. Kanno, A. Takahashi and et al., “Measurement of Absolute Myocardial Blood Flow with \( H^{{15}}_{2} O \) and Dynamic Positron Emission Tomography Strategy for Qualification in Relation to the Partial Volume Effect,” Circulation, vol. 78, 1998, pp. 104–115.
H. Iida, Y. Tamura, K. Kitamura, P.M. Bloomfield, S. Eberl and Y. Ono, “Histochemical Correlates of \( ^{{15}} O \)-Water-Perfusable Tissue Fraction in Experimental Canine Studies of Old Myocardial Infraction,” J Nucl Med, vol. 41, 2000, pp. 1737–1745.
P.A. Kaufmann, T. Gnecchi-Ruscone, J.T. Yap, O.Rimoldi and P.G. Camici, “Assessment of the Reproducibility of Baseline and Hyperemic Myocardial Blood Flow Measurements with \( ^{{15}} O \)-Labeled Water and PET,” J. Nucl. Med., vol. 40, 1999, pp. 1848–1856.
S.K. Kim, S. Choi, B.I. Lee, K.H. Hwang, J.S. Lee and D.S. Lee, “Improved Visualization of Dynamic \( H^{{15}}_{2} O \) PET using NMF,” Korean J. Nucl. Med., vol. 36, 2002.
B.I. Lee, J.S. Lee, D.S. Lee and S. Choi, “Myocardial blood flow quantification in dynamic PET: An ensemble ICA approach,” in Proc. Int’l Conf. Artificial Neural Networks, 2005, pp. 709–714.
D.D. Lee and H.S. Seung, “Learning the Parts of Objects by Non-Negative Matrix Factorization,” Nature, vol. 401, 1999, pp. 788–791.
D.S. Lee, K.W. Kang, K.H. Lee, J.M. Jeong, C. Kwark and J.K. Chung, “Stress/Rest Tc-99 m-MIBI SPECT in comparison with Rest/Stress rubidium-82 PET,” Korean J. Nucl. Med., vol. 29, 1995, pp. 31–40.
J.S. Lee, D.D. Lee, S. Choi and D.S. Lee, “Application of Non-Negative Matrix Factorization to Dynamic Positron Emission Tomography,” in Proc. ICA, San Diego, California, 2001, pp. 629–632.
J.S. Lee, D.D. Lee, S.Choi, K.S. Park and D.S. Lee, “Nonnegative Matrix Factorization of Dynamic Images in Nuclear Medicine,” IEEE Medical Imaging Conference, vol. 4, 2001, pp. 2027–2030.
J.S. Lee and D.S. Lee, “Measurement of Myocardial and Cerebral Blood Flow Using \( ^{{15}} O \) Water,” Korean J. Nucl. Med., vol. 35, 2001, pp. 43–51.
J.S. Lee, D.S. Lee, J.Y. Ahn, S.K. Kim, G.J. Cheon, J.S. Yeo, K.S. Park, J.K. Chung and M.C. Lee, “Blind Separation of Cardiac Components and extraction of Input Function from \( H^{{15}}_{2} O \) Dynamic Myocardial PET Using Independent Component Analysis,” J. Nucl. Med., vol. 42, no. 6, 2001, pp. 938–943.
J.S. Lee, K.S. Park, D.S. Lee, C.W. Lee, J.K. Chung and M.C. Lee, “Development and Applications of a Software for Functional Image Registration (FIRE),” Comput. Methods Programs Biomed., vol. 78, 2005, pp. 157–164.
J.W. Miskin and D.J.C. MacKay, “Ensemble Learning for Blind Source Separation,” in Independent Component Analysis: Principles and Practice, S. Roberts and R. Everson (Eds.), Cambridge University Press, 2001, pp. 209–233.
W.M. Schaefer, B. Nowak, H.J. Kaiser, K.C. K.S. Block and J.V. Dahl, “Comparison of Microsphere-Equivalent Blood Flow (\( ^{{15}} O \)-water PET) and Relative Perfusion (99 m Tc-Tetrofosmin SPECT) in Myocardium Showing Metabolism–Perfusion Mismatch,” J. Nucl. Med., vol. 44, 2003, pp. 33–39.
K.P. Schäfers, T.J. Spinks, P.G. Camici, P.M.B.C.G. Rhodes, and M.P. Law, “Absolute Quantification of Myocardial Blood Flow with \( H^{{15}}_{2} O \) and 3-Dimensional PET: An Experimental Validation,” J. Nucl. Med., vol. 43, 2002, pp. 1031–1040.
Author information
Authors and Affiliations
Corresponding author
Additional information
Submitted to a special issue of data fusion Journal of VLSI Signal Processing Systems.
Rights and permissions
About this article
Cite this article
Lee, B.I., Lee, J.S., Lee, D.S. et al. A Clinical Application of Ensemble ICA to the Quantification of Myocardial Blood Flow in Dynamic \( H^{{15}}_{2} O \) PET . J VLSI Sign Process Syst Sign Im 49, 233–241 (2007). https://doi.org/10.1007/s11265-007-0080-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11265-007-0080-7