Browse > Article

Development of Quantification Methods for the Myocardial Blood Flow Using Ensemble Independent Component Analysis for Dynamic $H_2^{15}O$ PET  

Lee, Byeong-Il (Department of Nuclear Medicine, Seoul National University College of Medicine)
Lee, Jae-Sung (Department of Nuclear Medicine, Seoul National University College of Medicine)
Lee, Dong-Soo (Department of Nuclear Medicine, Seoul National University College of Medicine)
Kang, Won-Jun (Department of Nuclear Medicine, Seoul National University College of Medicine)
Lee, Jong-Jin (Department of Nuclear Medicine, Seoul National University College of Medicine)
Kim, Soo-Jin (Department of Nuclear Medicine, Seoul National University College of Medicine)
Choi, Seung-Jin (Department of Computer Science, Pohang University of Science and Technology)
Chung, June-Key (Department of Nuclear Medicine, Seoul National University College of Medicine)
Lee, Myung-Chul (Department of Nuclear Medicine, Seoul National University College of Medicine)
Publication Information
The Korean Journal of Nuclear Medicine / v.38, no.6, 2004 , pp. 486-491 More about this Journal
Abstract
Purpose: factor analysis and independent component analysis (ICA) has been used for handling dynamic image sequences. Theoretical advantages of a newly suggested ICA method, ensemble ICA, leaded us to consider applying this method to the analysis of dynamic myocardial $H_2^{15}O$ PET data. In this study, we quantified patients' blood flow using the ensemble ICA method. Materials and Methods: Twenty subjects underwent $H_2^{15}O$ PET scans using ECAT EXACT 47 scanner and myocardial perfusion SPECT using Vertex scanner. After transmission scanning, dynamic emission scans were initiated simultaneously with the injection of $555{\sim}740$ MBq $H_2^{15}O$. Hidden independent components can be extracted from the observed mixed data (PET image) by means of ICA algorithms. Ensemble learning is a variational Bayesian method that provides an analytical approximation to the parameter posterior using a tractable distribution. Variational approximation forms a lower bound on the ensemble likelihood and the maximization of the lower bound is achieved through minimizing the Kullback-Leibler divergence between the true posterior and the variational posterior. In this study, posterior pdf was approximated by a rectified Gaussian distribution to incorporate non-negativity constraint, which is suitable to dynamic images in nuclear medicine. Blood flow was measured in 9 regions - apex, four areas in mid wall, and four areas in base wall. Myocardial perfusion SPECT score and angiography results were compared with the regional blood flow. Results: Major cardiac components were separated successfully by the ensemble ICA method and blood flow could be estimated in 15 among 20 patients. Mean myocardial blood flow was $1.2{\pm}0.40$ ml/min/g in rest, $1.85{\pm}1.12$ 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 image, the image contrast between left ventricle and myocardium was 1:2.7 in average. Perfusion reserve was significantly different between the regions with and without stenosis detected by the coronary angiography (P<0.01). In 66 segment with stenosis confirmed by angiography, the segments with reversible perfusion decrease in perfusion SPECT showed lower perfusion reserve values in $H_2^{15}O$ PET. Conclusions: Myocardial blood flow could be estimated using an ICA method with ensemble learning. We suggest that the ensemble ICA incorporating non-negative constraint is a feasible method to handle dynamic image sequence obtained by the nuclear medicine techniques.
Keywords
Dynamic $H_2^{15}O$ PET; ensemble ICA; blood flow;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Lee JS, Lee DS, Ahn JY, Cheon GJ, Kim SK, Yeo JS, et al. 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 2001;42:938-43   PUBMED
2 Schfers KP, Spinks TJ, Camici PG, Bloomfield PM, Rhodes CG, Law MP, et al. Absolute quantification of myocardial blood flow with $H_{2}^{15}O$ and 3-dimensional PET: an experimental validation. J Nucl Med 2002;43:1031-40
3 Lee JS, Park KS, Lee DS, Chung J-K, Lee MC. Development of IDL-based software for multimodal image registration. Korean J Nucl Med 2001;35:30(Abstract)
4 Iida H, Tamura Y, Kitamura K, Bloomfield PM, Eberl S, and Ono Y. Histochemical correlates of $^{15}O$-waterperfusable tissue fraction in experimental canine studies of old myocardial infarction. J Nucl Med 2000;41:1737-45   PUBMED
5 Miskin JW, MacKay DJC. Application of ensemble learning to infra-red imaging. Proc 2nd Inter Workshop Independent Component Anal and Blind Signal Separation. 2000;399-404
6 Lee JS, Lee DD, Choi S, Park KS, Lee DS. Non-negative matrix factorization of dynamic images in nuclear medicine. Proc IEEE Nucl Sci Symp Med Imag Conf. 2001
7 Lee DS, Kang KW, Lee KH, Jeong JM, Kwark C, Chung J-K et al. Stress/Rest Tc-99m-MIBI SPECT in Comparison with Rest/Stress Rubidium-82 PET. Korean J Nucl Med 1995;29(1)31-40
8 Hwang KH, Lee DS, Lee BI, Lee JS, Lee HY, Chung JK, et al. Evaluation of endothelium-dependent myocardial perfusion reserve in healthy smokers; cold pressor test using $H_{2}^{15}O$ PET. Korean J Nucl Med 2004;38(1)21-29
9 Iida H, Kanno I, Takahashi A, Miura S, Murakami M, Takahashi K, et al. 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 1988;78:104-15   DOI   PUBMED   ScienceOn
10 Lee DD, Seung HS. Learning the parts of objects by non-negative matrix factorization. Nature 401, 1999;788-91
11 Kaufmann PA, Gnecchi-Ruscone T, Yap JT, Rimoldi O, Camici PG. Assessment of thereproducibility of baseline and hyperemic myocardial blood flow measurements with $^{15}O$-labeled water and PET. J Nucl Med 1999;40:1848-56   PUBMED
12 Schaefer WM, Nowak B, Kaiser HJ, Koch KC, Block S, Dahl JV, et al. Comparison of microsphere-equivalent blood flow ($^{15}O$-water PET) and relative perfusion ($^{99m}$99m Tc-Tetrofosmin SPECT) in myocardium showing metabolism-perfusion mismatch. J Nucl Med 2003;44(1)33-9
13 Kim SK, Choi S, Lee BI, Hwang KH, Lee JS, Lee DS. Improved visualization of dynamic $H_{2}^{15}O$ PET data using NMF. Korean J Nucl Med 2002;36:53P (Abstract)
14 Lee JS, Lee DS. Measurement of myocardial and cerebral blood flow using O-15 water. Korean J Nucl Med 2001;35:43-51P
15 Chareonthaitawee P, Kaufmann PA, Rimoldi O, Camici PG. Heterogeneity of resting and hyperemic myocardial blood flow in healthy humans. Cardiovascular Research 2001;50:151-61   DOI   ScienceOn
16 Ahn JY, Lee DS, Lee JS, Kim SK, Cheon GJ, Yeo JS, et al. Quantification of regional myocardial blood flow using dynamic $H_{2}^{15}O$ PET and factor analysis. J Nucl Med 2001;42:782-7   PUBMED