Comparison of evolutionary and deterministic multiobjective algorithms for dose optimization in brachytherapy

Milickovic, N; Lahanas, M; Baltas, D; Zamboglou, N

dc.contributor.author	Milickovic, N	en
dc.contributor.author	Lahanas, M	en
dc.contributor.author	Baltas, D	en
dc.contributor.author	Zamboglou, N	en
dc.date.accessioned	2014-03-01T01:16:14Z
dc.date.available	2014-03-01T01:16:14Z
dc.date.issued	2001	en
dc.identifier.issn	0302-9743	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/13990
dc.subject	Evolutionary Algorithm	en
dc.subject	multiobjective evolutionary algorithm	en
dc.subject	Optimal Method	en
dc.subject	Optimization Problem	en
dc.subject	pareto front	en
dc.subject	pareto optimality	en
dc.subject	Search Method	en
dc.subject	Search Space	en
dc.subject	High Dose Rate	en
dc.subject.classification	Computer Science, Theory & Methods	en
dc.subject.other	GENETIC ALGORITHM	en
dc.subject.other	PROSTATE IMPLANTS	en
dc.title	Comparison of evolutionary and deterministic multiobjective algorithms for dose optimization in brachytherapy	en
heal.type	journalArticle	en
heal.identifier.primary	10.1007/3-540-44719-9_12	en
heal.identifier.secondary	http://dx.doi.org/10.1007/3-540-44719-9_12	en
heal.language	English	en
heal.publicationDate	2001	en
heal.abstract	We compare two multiobjective evolutionary algorithms, with deterministic gradient based optimization methods for the dose optimization problem in high-dose rate (HDR) brachytherapy. The optimization considers up to 300 parameters. The objectives are expressed in terms of statistical parameters, from dose distributions. These parameters are approximated from dose values from a small number of points. For these objectives it is known that the deterministic algorithms converge to the global Pareto front. The evolutionary algorithms produce only local Pareto-optimal fronts. The performance of the multiobjective evolutionary algorithms is improved if a small part of the population is initialized with solutions from deterministic algorithms. An explanation is that only a very small part of the search space is close to the global Pareto front. We estimate the performance of the algorithms in some cases in terms of probability compared to a random optimum search method.	en
heal.publisher	SPRINGER-VERLAG BERLIN	en
heal.journalName	EVOLUTIONARY MULTI-CRITERION OPTIMIZATION, PROCEEDINGS	en
heal.bookName	LECTURE NOTES IN COMPUTER SCIENCE	en
dc.identifier.doi	10.1007/3-540-44719-9_12	en
dc.identifier.isi	ISI:000175042500012	en
dc.identifier.volume	1993	en
dc.identifier.spage	167	en
dc.identifier.epage	180	en