Prediction of lung tumor motion with combinational use of High-order repetitive control and Long-Short term memory
Prediction of lung tumor motion with combinational use of High-order repetitive control and Long-Short term memory
复制标题
结合使用高阶重复控制和长短期记忆来预测肺肿瘤运动
DOI：
10.1109/smc42975.2020.9283414
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Shiinoki Takehiro
中科院分区：
文献类型：
--
作者：
Okusako Shota;Fujii Fumitake;Shiinoki Takehiro
动态肿瘤跟踪放射治疗（DTT-RT）是一种尝试对运动的肿瘤进行连续跟踪和照射的前沿技术。预测50 - 500 ms的未来位置的肿瘤是必要的DTT-RT的成功实施，以补偿定位滞后的多叶准直器（MLC）。众所周知，肺肿瘤表现出呼吸诱导运动。已知肺肿瘤运动的精确预测是一个非常困难的问题，因为它在轨迹的幅度和相位上都表现出很大的变化，尽管它是由患者的接近周期性的呼吸引起的。本文提出了一种肺部肿瘤运动的预测模型。该模型利用高阶重复控制来产生对应于轨迹周期基线的预测，并利用长短期记忆来科普剩余部分。我们已经开发了9个个性化的预测模型，9例患者在山口大学医院接受呼吸门控立体定向体部放射治疗，预测666 ms的3D肿瘤位置为每个患者。9例患者的平均3D RMS位置误差为2.18 mm（±1.66）。
The dynamic tumor tracking radiotherapy (DTT-RT) is the cutting-edge technology that attempts to track and irradiates the moving tumor continuously. Prediction of the 50 -500 ms future position of the tumor is necessary for successful implementation of DTT-RT to compensate for the positioning lag of the multi-leaf collimator (MLC). It is known that lung tumor exhibits respiratory induced motion. Precise prediction of lung tumor motion is known to be a very difficult problem since it exhibits large variation both on the amplitude and the phase of the trajectory, although it is induced by respiration of a patient that is nearly periodic. This paper proposes a prediction model of a lung tumor motion. The proposed model utilizes the high-order repetitive control to generate prediction corresponding to periodic baseline of the trajectory and the long-short term memory to cope with the remaining portion. We have developed nine personalized prediction models for nine patients who underwent respiratory gated stereotactic body radiotherapy in Yamaguchi University Hospital to predict 666 ms ahead 3D tumor position for each patient. The average 3D RMS position error for the nine patients was 2.18 mm (±1.66).