A hierarchical evolutionary algorithm for multiobjective optimization in IMRT.

PURPOSE The current inverse planning methods for intensity modulated radiation therapy (IMRT) are limited because they are not designed to explore the trade-offs between the competing objectives of tumor and normal tissues. The goal was to develop an efficient multiobjective optimization algorithm that was flexible enough to handle any form of objective function and that resulted in a set of Pareto optimal plans. METHODS A hierarchical evolutionary multiobjective algorithm designed to quickly generate a small diverse Pareto optimal set of IMRT plans that meet all clinical constraints and reflect the optimal trade-offs in any radiation therapy plan was developed. The top level of the hierarchical algorithm is a multiobjective evolutionary algorithm (MOEA). The genes of the individuals generated in the MOEA are the parameters that define the penalty function minimized during an accelerated deterministic IMRT optimization that represents the bottom level of the hierarchy. The MOEA incorporates clinical criteria to restrict the search space through protocol objectives and then uses Pareto optimality among the fitness objectives to select individuals. The population size is not fixed, but a specialized niche effect, domination advantage, is used to control the population and plan diversity. The number of fitness objectives is kept to a minimum for greater selective pressure, but the number of genes is expanded for flexibility that allows a better approximation of the Pareto front. RESULTS The MOEA improvements were evaluated for two example prostate cases with one target and two organs at risk (OARs). The population of plans generated by the modified MOEA was closer to the Pareto front than populations of plans generated using a standard genetic algorithm package. Statistical significance of the method was established by compiling the results of 25 multiobjective optimizations using each method. From these sets of 12-15 plans, any random plan selected from a MOEA population had a 11.3% +/- 0.7% chance of dominating any random plan selected by a standard genetic package with 0.04% +/- 0.02% chance of domination in reverse. By implementing domination advantage and protocol objectives, small and diverse populations of clinically acceptable plans that approximated the Pareto front could be generated in a fraction of 1 h. Acceleration techniques implemented on both levels of the hierarchical algorithm resulted in short, practical runtimes for multiobjective optimizations. CONCLUSIONS The MOEA produces a diverse Pareto optimal set of plans that meet all dosimetric protocol criteria in a feasible amount of time. The final goal is to improve practical aspects of the algorithm and integrate it with a decision analysis tool or human interface for selection of the IMRT plan with the best possible balance of successful treatment of the target with low OAR dose and low risk of complication for any specific patient situation.

[1]  Y. Yu,et al.  Multiobjective decision theory for computational optimization in radiation therapy. , 1997, Medical physics.

[2]  Andrzej Osyczka,et al.  Evolutionary Algorithms for Single and Multicriteria Design Optimization , 2001 .

[3]  J. Llacer,et al.  Absence of multiple local minima effects in intensity modulated optimization with dose-volume constraints. , 2003, Physics in medicine and biology.

[4]  David Craft,et al.  An approach for practical multiobjective IMRT treatment planning. , 2007, International journal of radiation oncology, biology, physics.

[5]  David L Craft,et al.  Approximating convex pareto surfaces in multiobjective radiotherapy planning. , 2006, Medical physics.

[6]  A. Niemierko.  Reporting and analyzing dose distributions: a concept of equivalent uniform dose. , 1997, Medical physics.

[7]  Dezhong Yao,et al.  Genetic algorithm based deliverable segments optimization for static intensity-modulated radiotherapy. , 2003, Physics in medicine and biology.

[8]  Fredrik Carlsson,et al.  Multicriteria optimization in intensity-modulated radiation therapy treatment planning for locally advanced cancer of the pancreatic head. , 2008, International journal of radiation oncology, biology, physics.

[9]  Michael Lahanas,et al.  Intensity Modulated Beam Radiation Therapy Dose Optimization with Multiobjective Evolutionary Algorithms , 2003, EMO.

[10]  M. Phillips,et al.  A macropencil beam model: clinical implementation for conformal and intensity modulated radiation therapy. , 1999, Physics in medicine and biology.

[11]  P. Siarry,et al.  Multiobjective Optimization: Principles and Case Studies , 2004 .

[12]  M Monz,et al.  Pareto navigation—algorithmic foundation of interactive multi-criteria IMRT planning , 2008, Physics in medicine and biology.

[13]  Paul J Keall,et al.  A new formula for normal tissue complication probability (NTCP) as a function of equivalent uniform dose (EUD) , 2008, Physics in medicine and biology.

[14]  D. McShan,et al.  Lexicographic ordering: intuitive multicriteria optimization for IMRT , 2007, Physics in medicine and biology.

[15]  G A Ezzell,et al.  Genetic and geometric optimization of three-dimensional radiation therapy treatment planning. , 1996, Medical physics.

[16]  Y. Li,et al.  Automatic beam angle selection in IMRT planning using genetic algorithm. , 2004, Physics in medicine and biology.

[17]  Gary B. Lamont,et al.  Evolutionary Algorithms for Solving Multi-Objective Problems , 2002, Genetic Algorithms and Evolutionary Computation.

[18]  H. Romeijn,et al.  A novel linear programming approach to fluence map optimization for intensity modulated radiation therapy treatment planning. , 2003, Physics in medicine and biology.

[19]  X. Wu,et al.  An optimization method for importance factors and beam weights based on genetic algorithms for radiotherapy treatment planning. , 2001, Physics in medicine and biology.

[20]  C. Cotrutz,et al.  Segment-based dose optimization using a genetic algorithm. , 2003, Physics in medicine and biology.

[21]  Michael Lahanas,et al.  Multiobjective inverse planning for intensity modulated radiotherapy with constraint-free gradient-based optimization algorithms. , 2003, Physics in medicine and biology.

[22]  I J Kalet,et al.  Prism: a new approach to radiotherapy planning software. , 1996, International journal of radiation oncology, biology, physics.

[23]  L. Xing,et al.  Multiobjective evolutionary optimization of the number of beams, their orientations and weights for intensity-modulated radiation therapy , 2004, Physics in Medicine and Biology.

[24]  Q. Hou,et al.  Beam orientation optimization for IMRT by a hybrid method of the genetic algorithm and the simulated dynamics. , 2003, Medical physics.

[25]  J. Mixter.  Fast , 2012 .

[26]  Sebastiaan Breedveld,et al.  Fast, multiple optimizations of quadratic dose objective functions in IMRT , 2006, Physics in medicine and biology.

[27]  I. Lagaris,et al.  BOXCQP : AN ALGORITHM FOR BOUND CONSTRAINED CONVEX QUADRATIC PROBLEMS , 2004 .

[28]  Fernando Alonso,et al.  A new concept for interactive radiotherapy planning with multicriteria optimization: first clinical evaluation. , 2007, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[29]  Jürgen Meyer,et al.  Application of influence diagrams to prostate intensity-modulated radiation therapy plan selection , 2004, Physics in medicine and biology.

[30]  Ira J. Kalet,et al.  A decision aid for intensity-modulated radiation-therapy plan selection in prostate cancer based on a prognostic Bayesian network and a Markov model , 2009, Artif. Intell. Medicine.