|
|
|
| The Study on Predicting Respiratory Motion via MemoryBased Learning in Radiotherapy |
1 Institute of Biomedical Engineering，Southern Medical University，Guangzhou 510515, China
2 Guangdong Sunwah Tech Consulting Group，Guangzhou 510515, China
3 Radiotherapy Center of PLA 303 Hospital, Nanning 530021, China |
|
|
|
|
Abstract Prediction is necessary to compensate the system latency in the realtime tracking radiation therapy for thoracic and abdominal cancers. However, because of the complexity of the breathing motion, conventional methods are far from clinical requirements. This paper proposed a memorybased learning method to predict respiratory motion. The method stores the training data in memory, then finds relevant data to answer a particular query. Furthermore, the paper adopts dynamic update the training data method and ridge regression aimed at “illcondition matrix” to greatly improve the accuracy and robustness of the algorithm. Our experiment collected ten respiratory motion data with average amplitude of 20 mm (9.2～37.8 mm) from humans’ body surface using POLARIS infrared positioning system. Using our methods (prediction horizon is 1s), mean absolute error (MAE) was reduced to 0.3 mm (0.08～0.8 mm), per estimate takes 1 ms. The results confirm that the proposed method is able to capture highly complex breathing movement accurately in real time.
|
|
|
|
|
|
［1］Jin JY, Yin FF. Time delay measurement for linac based treatment delivery in synchronized respiratory gating radiotherapy ［J］. Medical Physics, 2005, 32(5): 1293-1296.
［2］Murphy MJ. Tracking moving organs in real time ［J］. Semin Radiat Oncol, 2004, 14(1): 91-100.
［3］Gierga DP, Brewer J, Sharp G, et al. The correlation between internal and external markers for abdominal tumors: Implications for respiratory gating ［J］. Radiation Oncology Biol Phys, 2005, 61(5): 1551-1558.
［4］Krauss A, Nill S, Oelfke U. The comparative performance of four respiratory motion preditors for realtime tumour tracking ［J］. Phys Med Biol, 2011, 56(16): 5303-5317.
［5］Li Ruijiang, Lewis JH, Berbeco RI, et al. Realtime tumor motion estimation using respiratory surrogate via memorybased learning ［J］. Phys Med Biol, 2012, 57(15): 4771-4786.
［6］Ruan D, Fessler JA, Balter JM. Realtime prediction of respiratory motion based on local regression methods ［J］. Phys Med Biol, 2007, 52(23): 7137-7152.
［7］莫惠栋. 脊回归技术及其应用 ［J］. 作物学报, 2002, 28(4): 433- 438.
［8］莫惠栋. 回归分析中的病态矩阵及其改进 ［J］. 作物学报, 2006, 32(1): 1- 6.
［9］Ernst F, Dürichen R, Schlaefer A, et al. Evaluating and Comparing Algorithms for Respiratory Motion Prediction ［J］. Phys Med Biol, 2013, 58(11): 3911-3929.
|
|
|
|
