Real-Time Respiratory Tumor Motion Prediction Based on a Temporal Convolutional Neural Network: Prediction Model Development Study

Chang, Panchun; Dang, Jun; Dai, Jianrong; Sun, Wenchuan

doi:10.2196/27235

Cited by 10 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our proposed model, as a deep learning approach, is essentially a data-driven framework that offers the potential to build the mapping relationship between the external surrogate signal and the internal position of the delay interval for external surrogate signals to predict internal tumor locations as other studies. 46 But the current network may need further modification such as adding some fusion modules to ensemble the predictive outcome of several external markers. Accurate prediction of internal tumor locations from external surrogate signals is the focus of our next study.…”

Section: Discussionmentioning

confidence: 99%

LGEANet: LSTM‐global temporal convolution‐external attention network for respiratory motion prediction

et al. 2023

View full text Add to dashboard Cite

To develop a deep learning network that treats the three-dimensional respiratory motion signals as a whole and considers the inter-dimensional correlation between signals of different directions for accurate respiratory tumor motion prediction. Methods: We propose a deep learning framework, named as LSTM-Global Temporal Convolution-External Attention Network (LGEANet). In LGEANet, we first feed each of the univariate time series into the Long Short-Term Memory (LSTM) module respectively and utilize the strength of the global temporal convolutional layer to discover the temporal pattern of the univariate signals from hidden states of the LSTM. Then, External attention is adopted to capture the dynamic dependence of the multiple time series. Also, a traditional autoregressive linear model in parallel to the non-linear neural network part was integrated to mitigate the scale insensitivity of the networks. A total of 304 motion traces for 31 patients are acquired from a public dataset in the experiments and four representative cases were selected for model evaluation. The respiratory signals were sampled at intervals of about 37.5 ms (26 frames per second) for an average duration of 71 min. Results: The proposed LGEANet achieved better performance with higher empirical correlation coefficient value (CORRs) and lower mean absolute error value (MAEs) and relative squared error value (RSEs) than other investigated models. For the four representative datasets, when the response time is less than 231 ms, the model can achieve CORRs more than 0.96. And the averaged position error reduction by using the proposed model was about 67% in the superior-inferior (SI) direction, 41% in the anterior-posterior (AP) direction and 38% in the right-left (RL) direction compared to that without prediction. The proposed network achieved the greatest error reduction in the SI direction, which is the main direction of tumor motion. Conclusions:The LGEANet achieves promising performance in minimizing the prediction error due to system latencies during real-time tumor motion tracking.

show abstract

Section: Discussionmentioning

confidence: 99%

LGEANet: LSTM‐global temporal convolution‐external attention network for respiratory motion prediction

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Current machine learning methods often require acquisition of a minute to several minutes of motion signals to properly train a neural network for the required computational precision 22 , 32 , 38 . Clinic practice requires a maximum desirable training time of less than 30 s. This is because the radiation beam needs to be shuttered during neural network training and beam re-alignment needs to be verified.…”

Section: Rc Algorithms For Real-time Tumor Position Predictionmentioning

confidence: 99%

“…Neural network training time is another challenge in learning-based respiratory motion prediction. One group reported training times > 12 h using a temporal CNN 22 . RNNs are generally thought to be better suited for temporal signal processing with feedback from earlier inputs; however, classic RNNs are notoriously difficult to train 23 .…”

Section: Introductionmentioning

confidence: 99%

Real-time respiratory motion prediction using photonic reservoir computing

Liang

Zhang

Shi

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Respiration induced motion is a well-recognized challenge in many clinical practices including upper body imaging, lung tumor motion tracking and radiation therapy. In this work, we present a recurrent neural network algorithm that was implemented in a photonic delay-line reservoir computer (RC) for real-time respiratory motion prediction. The respiratory motion signals are quasi-periodic waveforms subject to a variety of non-linear distortions. In this work, we demonstrated for the first time that RC can be effective in predicting short to medium range of respiratory motions within practical timescales. A double-sliding window technology is explored to enable the real-time establishment of an individually trained model for each patient and the real-time processing of live-streamed respiratory motion data. A breathing dataset from a total of 76 patients with breathing speeds ranging from 3 to 20 breaths per minute (BPM) is studied. Motion prediction of look-ahead times of 66.6, 166.6, and 333 ms are investigated. With a 333 ms look-ahead time, the real-time RC model achieves an average normalized mean square error (NMSE) of 0.025, an average mean absolute error (MAE) of 0.34 mm, an average root mean square error (RMSE) of 0.45 mm, an average therapeutic beam efficiency (TBE) of 94.14% for an absolute error (AE) < 1 mm, and 99.89% for AE < 3 mm. This study demonstrates that real-time RC is an efficient computing framework for high precision respiratory motion prediction.

show abstract

“…During radiation therapy treatment delivery process, tumor in certain organs, such as the lung, would be subject to substantial motion due to patient respiration (1)(2)(3)(4)(5). This motion may lead to the leakage of radiation dose from the tumor target to nearby normal tissues, which would sharply degrade the accuracy and quality of the radiation therapy treatment.…”

Section: Introductionmentioning

confidence: 99%

Comparison of initial learning algorithms for long short-term memory method on real-time respiratory signal prediction

et al. 2023

Self Cite

View full text Add to dashboard Cite

AimThis study aimed to examine the effect of the weight initializers on the respiratory signal prediction performance using the long short-term memory (LSTM) model.MethodsRespiratory signals collected with the CyberKnife Synchrony device during 304 breathing motion traces were used in this study. The effectiveness of four weight initializers (Glorot, He, Orthogonal, and Narrow-normal) on the prediction performance of the LSTM model was investigated. The prediction performance was evaluated by the normalized root mean square error (NRMSE) between the ground truth and predicted respiratory signal.ResultsAmong the four initializers, the He initializer showed the best performance. The mean NRMSE with 385-ms ahead time using the He initializer was superior by 7.5%, 8.3%, and 11.3% as compared to that using the Glorot, Orthogonal, and Narrow-normal initializer, respectively. The confidence interval of NRMSE using Glorot, He, Orthogonal, and Narrow-normal initializer were [0.099, 0.175], [0.097, 0.147], [0.101, 0.176], and [0.107, 0.178], respectively.ConclusionsThe experiment results in this study indicated that He could be a valuable initializer in the LSTM model for the respiratory signal prediction.

show abstract

Real-Time Respiratory Tumor Motion Prediction Based on a Temporal Convolutional Neural Network: Prediction Model Development Study

Cited by 10 publications

References 24 publications

LGEANet: LSTM‐global temporal convolution‐external attention network for respiratory motion prediction

LGEANet: LSTM‐global temporal convolution‐external attention network for respiratory motion prediction

Real-time respiratory motion prediction using photonic reservoir computing

Comparison of initial learning algorithms for long short-term memory method on real-time respiratory signal prediction

Contact Info

Product

Resources

About