Department of Physics, Engineering Physics and Optics and Cancer Research Center, Université Laval, Quebec City, QC, G1V 0A6, Canada. Department of Radiation Oncology and Research Center of CHU de Québec-Université Laval, Quebec City, QC, G1R 2J6, Canada. Co-first authorship.
Phys Med Biol. 2019 May 8;64(10):105005. doi: 10.1088/1361-6560/ab1817.
Currently in HDR brachytherapy planning, a manual fine-tuning of an objective function is necessary to obtain case-specific valid plans. This study intends to facilitate this process by proposing a patient-specific inverse planning algorithm for HDR prostate brachytherapy: GPU-based multi-criteria optimization (gMCO). Two GPU-based optimization engines including simulated annealing (gSA) and a quasi-Newton optimizer (gL-BFGS) were implemented to compute multiple plans in parallel. After evaluating the equivalence and the computation performance of these two optimization engines, one preferred optimization engine was selected for the gMCO algorithm. Five hundred sixty-two previously treated prostate HDR cases were divided into validation set (100) and test set (462). In the validation set, the number of Pareto optimal plans to achieve the best plan quality was determined for the gMCO algorithm. In the test set, gMCO plans were compared with the physician-approved clinical plans. Our results indicated that the optimization process is equivalent between gL-BFGS and gSA, and that the computational performance of gL-BFGS is up to 67 times faster than gSA. Over 462 cases, the number of clinically valid plans was 428 (92.6%) for clinical plans and 461 (99.8%) for gMCO plans. The number of valid plans with target [Formula: see text] coverage greater than 95% was 288 (62.3%) for clinical plans and 414 (89.6%) for gMCO plans. The mean planning time was 9.4 s for the gMCO algorithm to generate 1000 Pareto optimal plans. In conclusion, gL-BFGS is able to compute thousands of SA equivalent treatment plans within a short time frame. Powered by gL-BFGS, an ultra-fast and robust multi-criteria optimization algorithm was implemented for HDR prostate brachytherapy. Plan pools with various trade-offs can be created with this algorithm. A large-scale comparison against physician approved clinical plans showed that treatment plan quality could be improved and planning time could be significantly reduced with the proposed gMCO algorithm.
目前在 HDR 近距离放射治疗计划中，需要对目标函数进行手动微调，以获得针对具体病例的有效计划。本研究旨在通过提出一种用于 HDR 前列腺近距离放射治疗的患者特异性逆规划算法来简化该过程：基于 GPU 的多准则优化（gMCO）。实现了两种基于 GPU 的优化引擎，包括模拟退火（gSA）和拟牛顿优化器（gL-BFGS），以并行计算多个计划。在评估了这两种优化引擎的等效性和计算性能后，选择了一种首选的优化引擎用于 gMCO 算法。将 562 例先前接受过 HDR 前列腺治疗的病例分为验证集（100 例）和测试集（462 例）。在验证集中，确定了 gMCO 算法达到最佳计划质量的 Pareto 最优计划数量。在测试集中，将 gMCO 计划与医师批准的临床计划进行比较。我们的结果表明，gL-BFGS 和 gSA 之间的优化过程等效，并且 gL-BFGS 的计算性能比 gSA 快 67 倍。在 462 例病例中，临床计划中有 428 例（92.6%）是临床有效计划，gMCO 计划中有 461 例（99.8%）是临床有效计划。目标[Formula: see text]覆盖率大于 95%的有效计划数量，临床计划有 288 例（62.3%），gMCO 计划有 414 例（89.6%）。gMCO 算法生成 1000 个 Pareto 最优计划的平均规划时间为 9.4 秒。总之，gL-BFGS 能够在短时间内计算数千个等效于 SA 的治疗计划。在 gL-BFGS 的支持下，实现了一种用于 HDR 前列腺近距离放射治疗的超快速和稳健的多准则优化算法。使用该算法可以创建具有各种权衡的计划池。与医师批准的临床计划进行的大规模比较表明，使用所提出的 gMCO 算法可以提高治疗计划质量并显著减少规划时间。
