Search

Background The dynamic tracking of tumors with radiation beams in radiation therapy requires the prediction of real-time target locations prior to beam delivery, as treatment involving radiation beams and gating tracking results in time latency. Objective In this study, a deep learning model that was based on a temporal convolutional neural network was developed to predict internal target locations by using multiple external markers. Methods Respiratory signals from 69 treatment fractions of 21 patients with cancer who were treated with the CyberKnife Synchrony device (Accuray Incorporated) were used to train and test the model. The reported model’s performance was evaluated by comparing the model to a long short-term memory model in terms of the root mean square errors (RMSEs) of real and predicted respiratory signals. The effect of the number of external markers was also investigated. Results The average RMSEs of predicted (ahead time=400 ms) respiratory motion in the superior-inferior, anterior-posterior, and left-right directions and in 3D space were 0.49 mm, 0.28 mm, 0.25 mm, and 0.67 mm, respectively. Conclusions The experiment results demonstrated that the temporal convolutional neural network–based respiratory prediction model could predict respiratory signals with submillimeter accuracy.

BACKGROUND The dynamic tracking of tumors with radiation beams in radiation therapy requires the prediction of real-time target locations prior to beam delivery, as treatment involving radiation beams and gating tracking results in time latency. OBJECTIVE In this study, a deep learning model that was based on a temporal convolutional neural network was developed to predict internal target locations by using multiple external markers. METHODS Respiratory signals from 69 treatment fractions of 21 patients with cancer who were treated with the CyberKnife Synchrony device (Accuray Incorporated) were used to train and test the model. The reported model’s performance was evaluated by comparing the model to a long short-term memory model in terms of the root mean square errors (RMSEs) of real and predicted respiratory signals. The effect of the number of external markers was also investigated. RESULTS The average RMSEs of predicted (ahead time=400 ms) respiratory motion in the superior-inferior, anterior-posterior, and left-right directions and in 3D space were 0.49 mm, 0.28 mm, 0.25 mm, and 0.67 mm, respectively. CONCLUSIONS The experiment results demonstrated that the temporal convolutional neural network–based respiratory prediction model could predict respiratory signals with submillimeter accuracy.

Supplementary A: Feature selection methods. Supplementary B: Machine learning methods. Supplementary C: The values selected for the hyper-parameters on each validation fold. Supplementary D: P-values of the log-rank test for all the feature selection and ML methods on each validation fold. (PDF 625 kb)

Respiratory motion may cause the change of some organs and tissues, such as lung and liver tumors in radiation therapy, which may influence the treatment effect and increase the damage to normal tissues and organs. Hence, it is an essential work to estimate the real-time movement of target in radiation therapy. BP-NN has been widely used in respiratory motion prediction due to its superior non-linear fitting capability. However, BP-NN is easy to fall into local minimum. In this study anovel method using PSO to optimize the BP-NN was proposed to avoid its drawbacks and improve prediction accuracy. The preliminaryresultsof 6 patients demonstrate that the proposed method (PSO-NN) has the ability of improving the prediction accuracy of BP-NN method.