Abstract #1403
Bayesian segmentation of dual-echo UTE images for PET/MR attenuation correction
Gaspar Delso 1 , Michael Carl 1 , Florian Wiesinger 2 , Martin Hllner 3 , and Patrick Veit-Haibach 3
1
Global MR Applications & Workflow, GE
Healthcare, Waukesha, WI, United States,
2
GE
Global Research, Munich, Germany,
3
University
Hospital, Zurich, Switzerland
MR-based attenuation correction is a critical component
of integrated PET/MR scanners. This is generally
achieved by segmenting MR images into a set of tissue
classes with known attenuation properties (e.g. bone,
fat, soft tissue, lung, air). Ultra-short echo time
(UTE) sequences capable of imaging tissues with short
T2* times (<1 ms) have been proposed in the past as a
means to locate bone tissue1-4. In this study, we used
tri-modality PET/CT+MR data from oncology patients to
develop an improved classification algorithm for the
localization of bone tissue in the head and neck area.
This abstract and the presentation materials are available to members only;
a login is required.
Join Here
