Comparison of Nonlinear Position Estimators For Continuous Scintillator Detectors In PET

Author

Bruyndonckx, Peter ; Lemaitre, Cedric ; van der Laan, D.J. ; Maas, Marnix ; Schaart, Dennis ; Devroede, Olivier ; Krieguer, Magalie ; Tavernier, Stefaan

Author_Institution

Vrije Universiteit Brussel

Volume

4

fYear

2006

fDate

Oct. 29 2006-Nov. 1 2006

Firstpage

2518

Lastpage

2522

Abstract

Several positioning algorithms are tested to extract position information from the measured scintillation light distribution generated in monolithic LSO blocks of various shapes and read out by a Hamamatsu S8550 APD array. The intrinsic detector resolutions of photons impinging at different angles e.g. 0deg, plusmn 10deg, plusmn 20deg, plusmn 30deg are studied. To this end, we evaluate the following positioning algorithms : Neural Networks trained with error back propagation (Levenberg-Marquardt), Neural Networks trained with an algebraic method and Support Vector Machines (SVM).

Keywords

learning (artificial intelligence); medical computing; neural nets; position measurement; position sensitive particle detectors; positron emission tomography; scintillation counters; Hamamatsu S8550 APD array; PET; algebraic method; continuous scintillator detectors; error back propagation; impinging photons; intrinsic detector resolutions; monolithic LSO blocks; neural network training; nonlinear position estimators; position information; positioning algorithms; scintillation light distribution; support vector machines; Detectors; Energy resolution; Geometry; Machine learning algorithms; Neural networks; Position measurement; Positron emission tomography; Sensor arrays; Spatial resolution; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Nuclear Science Symposium Conference Record, 2006. IEEE

Conference_Location

San Diego, CA

ISSN

1095-7863

Print_ISBN

1-4244-0560-2

Electronic_ISBN

1095-7863

Type

conf

DOI

10.1109/NSSMIC.2006.354422

Filename

4179536