Meeting Banner
Abstract #0410

MR-based PET Attenuation Correction for Brain PET-MR Using Support Vector Machines

Yicheng Chen 1 , Di Cui 1,2 , Yingmao Chen 3 , Jinsong Ouyang 4 , Georges El Fakhri 4 , and Kui Ying 1

1 Key Laboratory of Particle and Radiation Imaging, Ministry of Education, Department of Engineering Physics, Tsinghua University, Beijing, Beijing, China, 2 Department of Diagnostic Radiology, The University of Hong Kong, Hong Kong, China, 3 Department of Nuclear Medicine, The general hospital of Chinese People's Liberation, Beijing, China, 4 Department of Radiology, Division of Nuclear Medicine and Molecular Imaging, Harvard Medical School and Massachusetts General Hospital, Boston, Massachusetts, United States

In this study, a novel method using support vector machine (SVM) regression to predict continuous pseudo-CT from MR T2 and UTE information for PET attenuation correction is proposed. The SVM regression model is trained and tested with patient data. Compared to Gaussian mixture regression (GMR) model method, a pseudo-CT attenuation correction approach, the proposed method provides higher fidelity to the gold standard CT with our limited data set.

This abstract and the presentation materials are available to members only; a login is required.

Join Here