Premium
An artificial neural net and error backpropagation to reconstruct single photon emission computerized tomography data
Author(s) -
Knoll Peter,
Mirzaei Siroos,
Müllner Angelika,
Leitha Thomas,
Koriska Karl,
Köhn Horst,
Neumann Martin
Publication year - 1999
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.598511
Subject(s) - single photon emission computed tomography , iterative reconstruction , backpropagation , computer science , artificial neural network , artificial intelligence , imaging phantom , emission computed tomography , image quality , computer vision , image processing , medical imaging , reconstruction algorithm , positron emission tomography , algorithm , pattern recognition (psychology) , physics , nuclear medicine , image (mathematics) , optics , medicine
At present, algorithms used in nuclear medicine to reconstruct single photon emission computerized tomography (SPECT) data are usually based on one of two principles: filtered backprojection and iterative methods. In this paper a different algorithm, applying an artificial neural network (multilayer perception) and error backpropagation as training method are used to reconstruct transaxial slices from SPECT data. The algorithm was implemented on an Elscint XPERT workstation (i486, 50 MHz), used as a routine digital image processing tool in our departments. Reconstruction time for a 64 × 64 matrix is approximately 45 s/transaxial slice. The algorithm has been validated by a mathematical model and tested on heart and Jaszczak phantoms. Phantom studies and very first clinical results ( 111 In octreotide SPECT,99 mTc MDP bone SPECT) show in comparison with filtered backprojection an enhancement in image quality.