HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Abstract Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Email this article to a friend Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Lee, J. S. Articles by Lee, M. C. Search for Related Content PubMed PubMed Citation Articles by Lee, J. S. Articles by Lee, M. C.

Blind Separation of Cardiac Components and Extraction of Input Function from H₂¹⁵O Dynamic Myocardial PET Using Independent Component Analysis

Departments of Nuclear Medicine and Biomedical Engineering, Seoul National University College of Medicine, Seoul, Korea

View larger version (35K): [in a new window]   FIGURE 1. Schematic diagram of processor for blind source separation problem: Demixer extracts estimates of independent source signal from mixed input data by adjusting weights between its input and output nodes.

View larger version (31K): [in a new window]   FIGURE 2. Flow chart of image-processing steps.

View larger version (74K): [in a new window]   FIGURE 3. Cardiac regions separated using ICA method. Short-axis views of independent component images of RV (A), LV (B), and myocardium (C).

View larger version (13K): [in a new window]   FIGURE 4. Plot of log-likelihood of PDF of observation during training as function of repetition time: It increased rapidly and reached a plateau after 5–10 repetitions.

View larger version (16K): [in a new window]   FIGURE 5. LV input function by ICA () and by arterial blood sampling (): Their shapes were very similar except for noiseless tail of ICA-generated one and short time lags in input function by arterial sampling.

View larger version (21K): [in a new window]   FIGURE 6. Correlation of MBFs obtained using ICA method and microsphere technique (y = 0.45 + 0.98x; r = 0.95, P < 0.000).