Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Artificial neural network Radon inversion for image reconstruction
Autore:
Rodriguez, AF; Blass, WE; Missimer, JH; Leenders, KL;
Indirizzi:
Paul Scherrer Inst, PET Program, CH-5232 Villigen, Switzerland Paul Scherrer Inst Villigen Switzerland CH-5232 32 Villigen, Switzerland Inst Tecnol & Estuidos Super Monterrey, Dept Comp Sci, Mexico City, DF, Mexico Inst Tecnol & Estuidos Super Monterrey Mexico City DF Mexico DF, Mexico Univ Tennessee, Dept Phys & Astron, Knoxville, TN 37996 USA Univ Tennessee Knoxville TN USA 37996 s & Astron, Knoxville, TN 37996 USA
Titolo Testata:
MEDICAL PHYSICS
fascicolo: 4, volume: 28, anno: 2001,
pagine: 508 - 514
SICI:
0094-2405(200104)28:4<508:ANNRIF>2.0.ZU;2-V
Fonte:
ISI
Lingua:
ENG
Keywords:
artificial neural network; positron emission tomography (PET); image reconstruction; inverse Radon transform;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Clinical Medicine
Life Sciences
Citazioni:
17
Recensione:
Indirizzi per estratti:
Indirizzo: Missimer, JH Paul Scherrer Inst, PET Program, CH-5232 Villigen, Switzerland Paul Scherrer Inst Villigen Switzerland CH-5232 Switzerland
Citazione:
A.F. Rodriguez et al., "Artificial neural network Radon inversion for image reconstruction", MED PHYS, 28(4), 2001, pp. 508-514

Abstract

Image reconstruction techniques are essential to computer tomography. Algorithms such as filtered backprojection (FBP) or algebraic techniques are most frequently used. This paper presents an attempt to apply a feed-forward back-propagation supervised artificial neural network (BPN) to tomographic image reconstruction, specifically to positron emission tomography (PET). The main result is that the network trained with Gaussian test images provedto be successful at reconstructing images from projection sets derived from arbitrary objects. Additional results relate to the design of the networkand the full width at half maximum (FWHM) of the Gaussians in the trainingsets. First, the optimal number of nodes in the middle layer is about an order of magnitude less than the number of input or output nodes. Second, the number of iterations required to achieve a required training set tolerance appeared to decrease exponentially with the number of nodes in the middlelayer. Finally, for training sets containing Gaussians of a single width, the optimal accuracy of reconstructing the control set is obtained with a FWHM of three pixels. Intended to explore feasibility, the BPN presented in the following does not provide reconstruction accuracy adequate for immediate application to PET. However, the trained network does reconstruct general images independent of the data with which it was trained. Proposed in theconcluding section are several possible refinements that should permit thedevelopment of a network capable of fast reconstruction of three-dimensional images from the discrete, noisy projection data characteristic of PET. (C) 2001 American Association of Physicists in Medicine.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 20/01/20 alle ore 10:30:34