Automatic extraction of SPAMM grids in left ventricular myocardium from MR tagging images
Ohyama, W. Wakabayashi, T. Kimura, F. Tsuruoka, S. Sekioka, K.
Graduate School of Engineering, Mie University Graduate School of Regional Innovation Studies, Mie University Sekioka Clinic
Graduate School of Regional Innovation Studies, Mie University
Proceedings of the First International Workshop on Regional Innovation Studies : Biomedical Engineering (IWRIS2009)
MRI Left Ventricular Myocardium Active Net
We propose a novel algorithm to extract SPAMM (Spatial Modulation of Magnetization) grids in left Ventricular Myocardium form MR Tagging Images. In our method, the myocardium is extracted by making average pixel value among 5 subtraction frames. And extract SPAMM grids from myocardium with Active Net. We can initialize the Active Net automatically, and can improve accuracy of tracking by using myocardial characteristics. By using RMS difference with manual extractions, the experimental results show that the performance of the proposed method is empirically superior to conventional methods.
Conference Paper / 会議発表論文
October8, 2009. Media Hall, Mie University, Tsu, Mie, Japan