Multi-objective optimization in radiotherapy: applications to stereotacticradiosurgery and prostate brachytherapy

Treatment planning for radiation therapy is a multi-objective optimization process. Here we present a machine intelligent scheme for treatment plannin g based on multi-objective decision analysis (MODA) and genetic algorithm ( GA) optimization. Multi-objective ranking strategies are represented in the L-p metric under the displaced ideal model. Goal setting, protocol satisfi cing and fuzzy ranking of objective importance can be incorporated into the decision scheme to assimilate clinical decision making. For distance measu res in the L-p metric, a dynamic gauge function is defined based on the sta te energy of the decision system, which is assumed to undergo thermodynamic cooling with iteration time. The MODA scheme interacts with a robust GA en gine, which adaptively evolves in the multi-modal landscape that defines th e treatment plan quality. A conventionally challenging case of stereotactic radiosurgery of a brain lesion was selected for GA optimization. The resul ting dose distributions are compared to human-developed plans, which are co mmonly regarded as clinically relevant and empirically optimal. The GA-opti mized plans achieve substantially better sparing of critical normal neuroan atomy surrounding the brain lesion while respecting the preset constraints on tumor dose uniformity. In addition, machine optimization tends to produc e novel treatment strategies which complements expert knowledge. The run ti me for producing an optimal plan is considerably shorter than the typical p lanning time for human experts, thus GA can also be used to aid the human t reatment planning process. In prostate brachytherapy, MODA-GA was specifica lly applied to non-ideal conditions in which typical surgical uncertainties in seed implant positioning occur, where noisy objectives were introduced into the optimization scheme. The noisy system is found to be manageable by MODA-GA at uncertainty levels corresponding to reasonably proficient surge ry teams. In contrast, noisy objectives would be very difficult to explore by human expert planners. Potential use of noisy optimization with time ser ies analysis is being explored for error-corrective computer guidance in th e operating room for prostate seed implantation. In conclusion, the combina tion of MODA and GA optimization offers both a solution to practical treatm ent planning tasks and the potential fur real time applications in radiothe rapy. (C) 2000 Elsevier Science B.V. All rights reserved.