基于长短期记忆网络的运动预测在实时肿瘤追踪放射治疗中的成像剂量降低中的应用。

Application of motion prediction based on a long short-term memory network for imaging dose reduction in real-time tumor-tracking radiation therapy.

机构信息

Graduate School of Biomedical Science and Engineering, Hokkaido University, North 13, West 8, Kita-ku, Sapporo, Hokkaido 060-8628, Japan.

Faculty of Engineering, Hokkaido University, North 13, West 8, Kita-ku, Sapporo, Hokkaido 060-8638, Japan; Department of Medical Physics, Hokkaido University Hospital, North 14, West 5, Kita-ku, Sapporo, Hokkaido 060-8648, Japan.

出版信息

Phys Med. 2024 Sep;125:104507. doi: 10.1016/j.ejmp.2024.104507. Epub 2024 Aug 31.

DOI:10.1016/j.ejmp.2024.104507

PMID:39217787

Abstract

PURPOSE

To demonstrate the possibility of using a lower imaging rate while maintaining acceptable accuracy by applying motion prediction to minimize the imaging dose in real-time image-guided radiation therapy.

METHODS

Time-series of three-dimensional internal marker positions obtained from 98 patients in liver stereotactic body radiation therapy were used to train and test the long-short-term memory (LSTM) network. For real-time imaging, the root mean squared error (RMSE) of the prediction on three-dimensional marker position made by LSTM, the residual motion of the target under respiratory-gated irradiation, and irradiation efficiency were evaluated. In the evaluation of the residual motion, the system-specific latency was assumed to be 100 ms.

RESULTS

Except for outliers in the superior-inferior (SI) direction, the median/maximum values of the RMSE for imaging rates of 7.5, 5.0, and 2.5 frames per second (fps) were 0.8/1.3, 0.9/1.6, and 1.2/2.4 mm, respectively. The median/maximum residual motion in the SI direction at an imaging rate of 15.0 fps without prediction of the marker position, which is a typical clinical setting, was 2.3/3.6 mm. For rates of 7.5, 5.0, and 2.5 fps with prediction, the corresponding values were 2.0/2.6, 2.2/3.3, and 2.4/3.9 mm, respectively. There was no significant difference between the irradiation efficiency with and that without prediction of the marker position. The geometrical accuracy at lower frame rates with prediction applied was superior or comparable to that at 15 fps without prediction. In comparison with the current clinical setting for real-time image-guided radiation therapy, which uses an imaging rate of 15.0 fps without prediction, it may be possible to reduce the imaging dose by half or more.

CONCLUSIONS

Motion prediction can effectively lower the frame rate and minimize the imaging dose in real-time image-guided radiation therapy.

摘要

目的

通过应用运动预测来最小化实时图像引导放射治疗中的成像剂量，展示在保持可接受精度的同时使用较低成像率的可能性。

方法

使用来自 98 例肝脏立体定向体放射治疗患者的三维内部标记位置时间序列来训练和测试长短期记忆（LSTM）网络。对于实时成像，评估 LSTM 对三维标记位置预测的均方根误差（RMSE）、在呼吸门控照射下目标的残余运动和照射效率。在评估残余运动时，假设系统特定的滞后时间为 100 ms。

结果

除了在上下（SI）方向上的异常值外，成像率为 7.5、5.0 和 2.5 帧/秒（fps）的 RMSE 的中位数/最大值分别为 0.8/1.3、0.9/1.6 和 1.2/2.4 mm。在没有标记位置预测的典型临床设置下，成像率为 15.0 fps 时 SI 方向的中位数/最大值残余运动为 2.3/3.6 mm。对于预测的 7.5、5.0 和 2.5 fps 的速率，相应的值分别为 2.0/2.6、2.2/3.3 和 2.4/3.9 mm。有无标记位置预测的照射效率之间没有显著差异。应用预测时较低帧率的几何精度优于或可与无预测时 15 fps 的精度相媲美。与当前实时图像引导放射治疗的临床设置（无预测时成像率为 15.0 fps）相比，可能可以将成像剂量减半或更多。