Fully Automated Registration of First-Pass Myocardial Perfusion MRI Using Independent Component Analysis Export

@incollection{citeulike:6071865, abstract = {This paper presents a novel method for registration of cardiac perfusion MRI. The presented method successfully corrects for breathing motion without any manual interaction using Independent Component Analysis to extract physiologically relevant features together with their time-intensity behavior. A time-varying reference image mimicking intensity changes in the data of interest is computed based on the results of ICA, and used to compute the displacement caused by breathing for each frame. Qualitative and quantitative validation of the method is carried out using 46 clinical quality, short-axis, perfusion MR datasets comprising 100 images each. Validation experiments showed a reduction of the average LV motion from 1.26�0.87 to 0.64�0.46 pixels. Time-intensity curves are also improved after registration with an average error reduced from 2.65�7.89\% to 0.87�3.88\% between registered data and manual gold standard. We conclude that this fully automatic ICA-based method shows an excellent accuracy, robustness and computation speed, adequate for use in a clinical environment.}, author = {Milles, J. and van der Geest, R. and Jerosch-Herold, M. and Reiber, J. and Lelieveldt, B.}, citeulike-article-id = {6071865}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/978-3-540-73273-0_45}, citeulike-linkout-1 = {http://www.springerlink.com/content/j010l16412458254}, doi = {10.1007/978-3-540-73273-0_45}, journal = {Information Processing in Medical Imaging}, keywords = {image-registration, petmri}, pages = {544--555}, posted-at = {2009-11-05 00:07:21}, priority = {2}, title = {Fully Automated Registration of First-Pass Myocardial Perfusion MRI Using Independent Component Analysis}, url = {http://dx.doi.org/10.1007/978-3-540-73273-0_45}, year = {2007} }

TY - CHAP ID - citeulike:6071865 L3 - citeulike-article-id:6071865 N2 - This paper presents a novel method for registration of cardiac perfusion MRI. The presented method successfully corrects for breathing motion without any manual interaction using Independent Component Analysis to extract physiologically relevant features together with their time-intensity behavior. A time-varying reference image mimicking intensity changes in the data of interest is computed based on the results of ICA, and used to compute the displacement caused by breathing for each frame. Qualitative and quantitative validation of the method is carried out using 46 clinical quality, short-axis, perfusion MR datasets comprising 100 images each. Validation experiments showed a reduction of the average LV motion from 1.26�0.87 to 0.64�0.46 pixels. Time-intensity curves are also improved after registration with an average error reduced from 2.65�7.89% to 0.87�3.88% between registered data and manual gold standard. We conclude that this fully automatic ICA-based method shows an excellent accuracy, robustness and computation speed, adequate for use in a clinical environment. JF - Information Processing in Medical Imaging EP - 555 TI - Fully Automated Registration of First-Pass Myocardial Perfusion MRI Using Independent Component Analysis SP - 544 KW - image-registration KW - petmri AU - Milles, J AU - van der Geest, R AU - Jerosch-Herold, M AU - Reiber, J AU - Lelieveldt, B PY - 2007/// UR - http://dx.doi.org/10.1007/978-3-540-73273-0_45 ER -