z-logo
Premium
SU‐E‐T‐869: Direct Aperture Optimization Based on Multi‐Objective Evolutionary Algorithm in Intensity Modulated Radiation Therapy
Author(s) -
Cao R,
Pei X,
Wang J,
Wu Y
Publication year - 2011
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 - 10.1118/1.3612833
Subject(s) - multi objective optimization , sorting , mathematical optimization , aperture (computer memory) , optimization problem , evolutionary algorithm , set (abstract data type) , radiation treatment planning , inverse , genetic algorithm , inverse problem , pareto principle , computer science , mathematics , dosimetry , algorithm , radiation therapy , nuclear medicine , physics , acoustics , medicine , programming language , mathematical analysis , geometry
Purpose: Direct Aperture Optimization (DAO) is an Intensity Modulated Radiation Therapy (IMRT) inverse planning technique whereby the shapes and relative weights of the apertures in the plan are optimized directly. As DAO is capable of producing treatment plans that are comparable to plans produced using the traditional inverse planning approach while using significantly fewer segments, DAO is studied more and more in recent years. Inverse planning optimization is a multi‐objective optimization problem whose solution is known as Pareto solution set. So, the multi‐objective direct aperture optimization based on Pareto solution set was studied in this paper.Method: The clinical requirements for a treatment plan were transformed into a multi‐objective optimization problem with multiple constraints, in which the parameters are the shapes and relative weights of the apertures. And then the fast and elitist multi‐objective Non‐dominated Sorting Genetic Algorithm (NSGA‐II) was introduced to optimize the problem. The aim of NSGA‐II based optimization algorithm is to provide a representative set of non‐dominated solutions for problems where many conflicting objectives and many constraints need to be considered simultaneously instead of a single solution. Results: A clinical example was tested using the method. The results showed that a set of non‐dominated solutions obtained distributed uniformly, and the corresponding dose distribution of each solution not only approached to the expected dose distribution but also met the dose‐volume constraints. Conclusions: It was indicated that the clinical requirements were better satisfied by the method and planner could select the optimal treatment plan. Supported by the National Natural Science Foundation under grant No.30900386 and the Anhui Provincial Natural Science Foundation under grant No. 090413095 and 11040606Q55.

This content is not available in your region!

Continue researching here.

Having issues? You can contact us here