Individual refinement of attenuation correction maps for hybrid PET/MR based on multi-resolution regional learning

Highlights • Individual refinement of PET/MR attenuation correction. • Multi-resolution regional learning. • Robust with different training and initial setting. • Flexible combination with certified. • Methods or new development.

Saved in:
Bibliographic Details
Published in:Computerized medical imaging and graphics 2017-09, Vol.60, p.50-57
Main Authors: Shi, Kuangyu, Fürst, Sebastian, Sun, Liang, Lukas, Mathias, Navab, Nassir, Förster, Stefan, Ziegler, Sibylle I
Format: Article
Language:English
Subjects:
Accuracy
Adult
Algorithms
Attenuation
Attenuation correction
Brain - diagnostic imaging
Computed tomography
Female
Fluorine isotopes
Humans
Image processing
Image Processing, Computer-Assisted
Image segmentation
Internal Medicine
Machine learning
Magnetic Resonance Imaging
Male
Middle Aged
Multi-resolution
Multimodal Imaging - methods
NMR
Nuclear magnetic resonance
Other
PET/MR
Positron emission
Positron Emission Tomography Computed Tomography
Positron-Emission Tomography
Therapeutic applications
Tomography
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Highlights • Individual refinement of PET/MR attenuation correction. • Multi-resolution regional learning. • Robust with different training and initial setting. • Flexible combination with certified. • Methods or new development.
ISSN:0895-6111
1879-0771
DOI:10.1016/j.compmedimag.2016.11.005