Abstract
In chest and abdomen robotic radiosurgery, due to the motion delay of the robotic manipulator, the tumor position tracking process has a period of delay. This delay ultimately affects the accuracy of radiosurgery treatment. To address the influence of the delay in robotic radiosurgery, a Long-and-Short-Term Memory (LSTM) network as a deep Recurrent Neural Network (RNN) has been applied in a prediction network model for respiratory motion tracking in recent years. However, patients' respiratory state may change in the process of treatment, which may influence the accuracy of prediction. Therefore, it is necessary to update the prediction network through additional data, such as the actual position of the tumor obtained by X-ray imaging. However, the LSTM network has a long update time, and it may not be able to complete the prediction model update in a cycle of X-ray acquisition. To solve this problem, a fast prediction model based on Bidirectional Gated Recurrent Unit (Bi-GRU), is proposed in this paper. This method can reduce the average updating time of the network model by 30%.
Highlights
The precision of radiotherapy at specific sites, such as the lung, liver, breast and pancreas [1], is strongly affected by the patient’s respiratory movement
Five-minute data are taken for each group of respiratory data, and the first 20% is used as training sets to generate prediction models
In experiments with training the respiratory motion data set, it was found that the training speed of the Bidirectional Gated Recurrent Unit (Bi-GRU) model is 30% faster than that of the Long-and-Short-Term Memory (LSTM) network under the most similar network structure
Summary
The precision of radiotherapy at specific sites, such as the lung, liver, breast and pancreas [1], is strongly affected by the patient’s respiratory movement. The modern radiotherapy system aims to detect and predict restricted respiratory movements in advance and accommodate radiotherapy planning. Many motion management methods have been studied, such as (1) breath-holding and gating methods have been used to reduce the treatment range and minimize the amount of unnecessary Organs At Risk (OAR); and (2) dynamic tracking methods for real-time target tracking have been explored to improve delivery efficiency. A disadvantage of breath-hold is patient compliance. Some patients were identified to respond to coaching of breath-holding more than others [2]. Breath-hold is likewise more labor intensive, requiring more staff time in planning, treatment, and verification of patient treatments [3]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
