Fully three-dimensional tomographic evolutionary reconstruction in nuclear medicine

Authors:
Aurélie Bousquet;Jean Louchet;Jean-Marie Rocchisani
Affiliations:
INRIA Rocquencourt, COMPLEX, Le Chesnay, France;INRIA Rocquencourt, COMPLEX, Le Chesnay, France;INRIA Rocquencourt, COMPLEX, Le Chesnay, France and Paris XIII University, UFR, SMBH & Avicenne hospital, Bobigny, France
Venue:
EA'07 Proceedings of the Evolution artificielle, 8th international conference on Artificial evolution
Year:
2007

Citing 1
Cited 3

Monte Carlo methods. Vol. 1: basics

Monte Carlo methods. Vol. 1: basics

Artificial evolution for 3D PET reconstruction

EA'09 Proceedings of the 9th international conference on Artificial evolution
Threshold selection, mitosis and dual mutation in cooperative co-evolution: application to medical 3D tomography

PPSN'10 Proceedings of the 11th international conference on Parallel problem solving from nature: Part I
New genetic operators in the fly algorithm: application to medical PET image reconstruction

EvoApplicatons'10 Proceedings of the 2010 international conference on Applications of Evolutionary Computation - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

3-D reconstruction in Nuclear Medicine imaging using completeMonte-Carlo simulation of trajectories usually requires high computingpower. We are currently developing a Parisian Evolution Strategy in order toreduce the computing cost of reconstruction without degrading the quality ofresults. Our approach derives from the Fly algorithm which proved successfulon real-time stereo image sequence processing. Flies are considered here asphoton emitters. We developed the marginal fitness technique to calculate thefitness function, an approach usable in Parisian Evolution whenever eachindividual's fitness cannot be calculated independently of the rest of thepopulation.