Real-Time Respiratory Tumor Motion Prediction Based on a Temporal Convolutional Neural Network: Prediction Model Development Study
BackgroundThe 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. ObjectiveIn this st...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2021-08-01
|
| Series: | Journal of Medical Internet Research |
| Online Access: | https://www.jmir.org/2021/8/e27235 |
| _version_ | 1797735771581448192 |
|---|---|
| author | Panchun Chang Jun Dang Jianrong Dai Wenzheng Sun |
| author_facet | Panchun Chang Jun Dang Jianrong Dai Wenzheng Sun |
| author_sort | Panchun Chang |
| collection | DOAJ |
| description |
BackgroundThe 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.
ObjectiveIn 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.
MethodsRespiratory 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.
ResultsThe 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.
ConclusionsThe experiment results demonstrated that the temporal convolutional neural network–based respiratory prediction model could predict respiratory signals with submillimeter accuracy. |
| first_indexed | 2024-03-12T13:03:55Z |
| format | Article |
| id | doaj.art-e80c697c24b343139da70de5e5748a79 |
| institution | Directory Open Access Journal |
| issn | 1438-8871 |
| language | English |
| last_indexed | 2024-03-12T13:03:55Z |
| publishDate | 2021-08-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | Journal of Medical Internet Research |
| spelling | doaj.art-e80c697c24b343139da70de5e5748a792023-08-28T18:34:59ZengJMIR PublicationsJournal of Medical Internet Research1438-88712021-08-01238e2723510.2196/27235Real-Time Respiratory Tumor Motion Prediction Based on a Temporal Convolutional Neural Network: Prediction Model Development StudyPanchun Changhttps://orcid.org/0000-0003-0909-638XJun Danghttps://orcid.org/0000-0002-9077-6544Jianrong Daihttps://orcid.org/0000-0002-3249-440XWenzheng Sunhttps://orcid.org/0000-0003-2629-744X BackgroundThe 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. ObjectiveIn 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. MethodsRespiratory 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. ResultsThe 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. ConclusionsThe experiment results demonstrated that the temporal convolutional neural network–based respiratory prediction model could predict respiratory signals with submillimeter accuracy.https://www.jmir.org/2021/8/e27235 |
| spellingShingle | Panchun Chang Jun Dang Jianrong Dai Wenzheng Sun Real-Time Respiratory Tumor Motion Prediction Based on a Temporal Convolutional Neural Network: Prediction Model Development Study Journal of Medical Internet Research |
| title | Real-Time Respiratory Tumor Motion Prediction Based on a Temporal Convolutional Neural Network: Prediction Model Development Study |
| title_full | Real-Time Respiratory Tumor Motion Prediction Based on a Temporal Convolutional Neural Network: Prediction Model Development Study |
| title_fullStr | Real-Time Respiratory Tumor Motion Prediction Based on a Temporal Convolutional Neural Network: Prediction Model Development Study |
| title_full_unstemmed | Real-Time Respiratory Tumor Motion Prediction Based on a Temporal Convolutional Neural Network: Prediction Model Development Study |
| title_short | Real-Time Respiratory Tumor Motion Prediction Based on a Temporal Convolutional Neural Network: Prediction Model Development Study |
| title_sort | real time respiratory tumor motion prediction based on a temporal convolutional neural network prediction model development study |
| url | https://www.jmir.org/2021/8/e27235 |
| work_keys_str_mv | AT panchunchang realtimerespiratorytumormotionpredictionbasedonatemporalconvolutionalneuralnetworkpredictionmodeldevelopmentstudy AT jundang realtimerespiratorytumormotionpredictionbasedonatemporalconvolutionalneuralnetworkpredictionmodeldevelopmentstudy AT jianrongdai realtimerespiratorytumormotionpredictionbasedonatemporalconvolutionalneuralnetworkpredictionmodeldevelopmentstudy AT wenzhengsun realtimerespiratorytumormotionpredictionbasedonatemporalconvolutionalneuralnetworkpredictionmodeldevelopmentstudy |