A new genetic algorithm technique in optimization of permanent I-125 prostate implants

Real time optimized treatment planning at the time of the implant is desira ble for ultrasound-guided transperineal I-125 permanent prostate implants. Currently available optimization algorithms are too slow to be used in the operating room. The goal of this work is to develop a robust optimization a lgorithm, which is suitable for such application. Three different genetic a lgorithms (sGA, sureGA and securGA) were developed and compared in terms of the number of function evaluations and the corresponding fitness. The opti mized dose distribution was achieved by searching the best seed distributio n through the minimization of a cost function. The cost function included c onstraints on the periphery dose of the planned target volume, the dose uni formity within the target volume, and the dose to the critical structure. A djustment between the peripheral dose, the dose uniformity and critical str ucture dose can be achieved by varying the weighting factors in the cost fu nction. All plans were evaluated in terms of the dose nonuniformity ratio, the conformation number and the dose volume histograms. Among these three G A algorithms, the securGA provided the best performance. Within 2500 functi on evaluations, the near optimum results were obtained. For a large target volume (5 cmx4 cmx4.5 cm) including urethra with 20 needles, the computer t ime needed for the optimization was less than 5 min on a HP735 workstation. The results showed that once the best set of parameters was found, they we re applicable for all sizes of prostate volume. For a fixed needle geometry , the optimized plan showed much better dose distribution than that of nono ptimized plan. If the critical structure was considered in the optimization , the dose to the critical structure could be minimized. In the cases of ir regular and skewed needle geometry, the optimized treatment plans were almo st as good as ideal needle geometry. It is concluded that this new genetic algorithm (securGA) allows for an efficient and rapid optimization of dose distribution, which is suitable for real time treatment planning optimizati on for ultrasound-guided prostate implant. (C) 1998 American Association of Physicists in Medicine. [S0094-2405(98)02412-2].