Department of Radiation Oncology, LMU University Hospital, LMU Munich, Munich, Germany.
Department of Medical Physics, LMU Munich, Munich, Germany.
Phys Med Biol. 2024 Oct 21;69(21). doi: 10.1088/1361-6560/ad7f1e.
To present a long short-term memory (LSTM) network-based dose calculation method for magnetic resonance (MR)-guided proton therapy.35 planning computed tomography (CT) images of prostate cancer patients were collected for Monte Carlo (MC) dose calculation under a perpendicular 1.5 T magnetic field. Proton pencil beams (PB) at three energies (150, 175, and 200 MeV) were simulated (7560 PBs at each energy). A 3D relative stopping power cuboid covering the extent of the PB dose was extracted and given as input to the LSTM model, yielding a 3D predicted PB dose. Three single-energy (SE) LSTM models were trained separately on the corresponding 150/175/200 MeV datasets and a multi-energy (ME) LSTM model with an energy embedding layer was trained on either the combined dataset with three energies or a continuous energy (CE) dataset with 1 MeV steps ranging from 125 to 200 MeV. For each model, training and validation involved 25 patients and 10 patients were for testing. Two single field uniform dose prostate treatment plans were optimized and recalculated with MC and the CE model.Test results of all PBs from the three SE models showed a mean gamma passing rate (2%/2 mm, 10% dose cutoff) above 99.9% with an average center-of-mass (COM) discrepancy below 0.4 mm between predicted and simulated trajectories. The ME model showed a mean gamma passing rate exceeding 99.8% and a COM discrepancy of less than 0.5 mm at the three energies. Treatment plan recalculation by the CE model yielded gamma passing rates of 99.6% and 97.9%. The inference time of the models was 9-10 ms per PB.LSTM models for proton dose calculation in a magnetic field were developed and showed promising accuracy and efficiency for prostate cancer patients.
为了提出一种基于长短期记忆（LSTM）网络的磁共振（MR）引导质子治疗剂量计算方法。收集了前列腺癌患者的蒙特卡罗（MC）剂量计算规划计算机断层扫描（CT）图像，在垂直 1.5 T 磁场下进行。模拟了三个能量（150、175 和 200 MeV）的质子铅笔束（PB）（每个能量 7560 个 PB）。提取并作为输入提供给 LSTM 模型的是一个 3D 相对阻止功率长方体，该长方体覆盖了 PB 剂量的范围，产生了 3D 预测 PB 剂量。三个单能（SE）LSTM 模型分别在相应的 150/175/200 MeV 数据集上进行训练，一个具有能量嵌入层的多能（ME）LSTM 模型在三个能量的组合数据集或从 125 到 200 MeV 的 1 MeV 步长的连续能量（CE）数据集上进行训练。对于每个模型，训练和验证涉及 25 名患者，10 名患者用于测试。优化并重新计算了两个单场均匀剂量前列腺治疗计划，使用 MC 和 CE 模型进行计算。三个 SE 模型的所有 PB 的测试结果均显示，2%/2mm，10%剂量截止的平均伽马通过率（gamma passing rate）超过 99.9%，预测和模拟轨迹之间的平均质心（COM）差异小于 0.4mm。ME 模型在三个能量下的平均伽马通过率超过 99.8%，COM 差异小于 0.5mm。CE 模型的治疗计划重新计算产生了 99.6%和 97.9%的伽马通过率。模型的推断时间为每个 PB 9-10ms。在磁场中进行质子剂量计算的 LSTM 模型已经开发出来，并显示出对前列腺癌患者有很好的准确性和效率。
