Meeting Banner
Abstract #2815

MR Based Attenuation Correction Including Cortical Bone for PET/MR Hybrid Imaging

Bharath K. Navalpakkam1, Harald Braun2, Joachim Hornegger1, Torsten Kuwert3, Harald H. Quick2

1Pattern Recognition Lab, Friedrich-Alexander-University Erlangen-Nrnberg, Erlangen, Bavaria, Germany; 2Institute of Medical Physics, Friedrich-Alexander-University Erlangen-Nrnberg, Erlangen, Bavaria, Germany; 3Clinic of Nuclear Medicine, Friedrich-Alexander-University Erlangen-Nrnberg, Erlangen, Bavaria, Germany

An MR-based attenuation correction approach for PET/MR that includes cortical bone information is proposed. An epsilon insensitive Support Vector Regression model is trained and validated on head regions for five patients. The reconstructed PET data is evaluated for the proposed approach (PETMRAC) against other approaches that include (PETboneAC) and disregard bone class (PETnoboneAC). For the complete brain, PETMRAC yielded a mean absolute error of 2.403.59%, 10.153.31% for PETnoboneAC and 3.963.71% for PETboneAC. For atlas segmented landmarks, the errors for the same were 2.161.77%, 11.032.26% and 4.223.91%, respectively. An initial result of an MR-based pseudo-CT for a whole-body application is illustrated.

Abstract PDF

Keywords

abdominal absolute activities adjustable analyzed anatomical application applied approximated assigned atlas attenuation audience basis bias biograph body bone bones brain class classes classification clinic close closely closer coefficient coefficients collective complete computed continuous corrected correction cortical currently densities detection determination differentiate difficulty dimensional discard done emission epsilon error errors estimations evaluated extension feature field five function generated generation global head hence hybrid identity ignored included inclusion inherent initial injected insensitive institute intensities investigated kernel lacs landmarks larger learn limitation limited linear local many mapping maps medical medicine model nuclear optimized others patient patients pattern periphery physicians physics plots predicted prediction prior process project proposed pseudo quantification quick radial radioactivity reason recognition reconstructed reduces regression relation reported represent researchers resembles respective respectively retrospectively scanned sector segmentation segmentations segmented skull slope slopes space support systems target tissue towards training ultrashort underestimation units validation vary vastly vector vibe visible visualize volunteer water whole window