Ensemble framework based real-time respiratory motion prediction for adaptive radiotherapy applications

Tatinati, Sivanagaraja; Nazarpour, Kianoush; Ang, Wei Tech; Veluvolu, Kalyana C.

doi:10.1016/j.medengphy.2016.04.021

Cited by 9 publications

(6 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A large number of prediction filters are presented in literature. A wide variety of techniques for prediction filters have been proposed, including Kalman filters, autoregressive moving average models, wavelet decomposition, fuzzy logic models, neural nets, support vector regression, nonlinear dynamics identification, and combinations thereof . Prediction filters have also been compared to each other: The support vector regression approach was compared to the neural network approach and found to be superior.…”

Section: Introductionmentioning

confidence: 99%

Performance comparison of prediction filters for respiratory motion tracking in radiotherapy

et al. 2019

View full text Add to dashboard Cite

Purpose In precision radiotherapy, the intrafractional motion causes substantial uncertainty. Traditionally, the target volume is expanded to cover the tumor in all positions. Alternative approaches are gating and adaptive tracking, which require a time delay as small as possible between the actual tumor motion and the reaction to effectively compensate the motion. Current treatment machines often exhibit large time delays. Prediction filters offer a promising means to mitigate these time delays by predicting the future respiratory motion. Methods A total of 18 prediction filters were implemented and their hyperparameters optimized for various time delays and noise levels. A set of 93 traces were standardized to a sampling frequency of 25 Hz and smoothed using the Fourier transform with a 3 Hz cutoff frequency. The hyperparameter optimization was carried out with ten traces, and the optimal hyperparameters were evaluated on the remaining 83 traces. Results For smooth traces, the wavelet least mean squares prediction filter and the linear filter reached normalized root mean square errors of below 0.05 for time delays of 160 and 480 ms, respectively. For noisy signals, the performance of the prediction filters deteriorated and led to similar results. Conclusions Linear methods for prediction filters are sufficient for respiratory motion signals. Reducing the measurement noise generally improves the performance of the prediction filters investigated in this study, even during breathing irregularities.

show abstract

Section: Introductionmentioning

confidence: 99%

Performance comparison of prediction filters for respiratory motion tracking in radiotherapy

et al. 2019

View full text Add to dashboard Cite

show abstract

“…90 In addition, learning frameworks combining individual predictors have been shown to significantly improve performance beyond the best existing methods. 91…”

Section: Machine Learning In Planningmentioning

confidence: 99%

Applications and limitations of machine learning in radiation oncology

Jarrett

Stride

Vallis

et al. 2019

The British Journal of Radiology

128

View full text Add to dashboard Cite

Machine learning approaches to problem-solving are growing rapidly within healthcare, and radiation oncology is no exception. With the burgeoning interest in machine learning comes the significant risk of misaligned expectations as to what it can and cannot accomplish. This paper evaluates the role of machine learning and the problems it solves within the context of current clinical challenges in radiation oncology. The role of learning algorithms within the workflow for external beam radiation therapy are surveyed, considering simulation imaging, multimodal fusion, image segmentation, treatment planning, quality assurance, and treatment delivery and adaptation. For each aspect, the clinical challenges faced, the learning algorithms proposed, and the successes and limitations of various approaches are analyzed. It is observed that machine learning has largely thrived on reproducibly mimicking conventional human-driven solutions with more efficiency and consistency. On the other hand, since algorithms are generally trained using expert opinion as ground truth, machine learning is of limited utility where problems or ground truths are not well-defined, or if suitable measures of correctness are not available. As a result, machines may excel at replicating, automating and standardizing human behaviour on manual chores, meanwhile the conceptual clinical challenges relating to definition, evaluation, and judgement remain in the realm of human intelligence and insight.

show abstract

“…In contrast, hybrid algorithms use integrated methods to combine model‐based and model‐free algorithms to predict the respiratory signals. In this context, a review of previous studies reveals the challenges faced by researchers, such as low accuracy and poor performance of models for irregular respiratory patterns, as well as ignorance of the respiratory signal's time dependence 12–14,18–21 . To tackle the issue of ignorance of temporal dependence, a deep recurrent neural network (RNN) was proposed 22 .…”

Section: Introductionmentioning

confidence: 99%

“…In this context, a review of previous studies reveals the challenges faced by researchers, such as low accuracy and poor performance of models for irregular respiratory patterns, as well as ignorance of the respiratory signal's time dependence. [12][13][14][18][19][20][21] To tackle the issue of ignorance of temporal dependence, a deep recurrent neural network (RNN) was proposed. 22 However, deep RNN networks suffer from the problem of exploding and vanishing gradients, which makes it challenging to train long-term sequences.…”

Section: Introductionmentioning

confidence: 99%

Respiratory motion prediction based on deep artificial neural networks in CyberKnife system: A comparative study

Miandoab

Saramad

Setayeshi

2022

J Applied Clin Med Phys

View full text Add to dashboard Cite

Background: In external beam radiotherapy, a prediction model is required to compensate for the temporal system latency that affects the accuracy of radiation dose delivery. This study focused on a thorough comparison of seven deep artificial neural networks to propose an accurate and reliable prediction model. Methods: Seven deep predictor models are trained and tested with 800 breathing signals. In this regard, a nonsequential-correlated hyperparameter optimization algorithm is developed to find the best configuration of parameters for all models. The root mean square error (RMSE), mean absolute error, normalized RMSE, and statistical F-test are also used to evaluate network performance. Results: Overall, tuning the hyperparameters results in a 25%-30% improvement for all models compared to previous studies. The comparison between all models also shows that the gated recurrent unit (GRU) with RMSE = 0.108 ± 0.068 mm predicts respiratory signals with higher accuracy and better performance. Conclusion: Overall, tuning the hyperparameters in the GRU model demonstrates a better result than the hybrid predictor model used in the CyberKnife VSI system to compensate for the 115 ms system latency. Additionally, it is demonstrated that the tuned parameters have a significant impact on the prediction accuracy of each model.

show abstract

Ensemble framework based real-time respiratory motion prediction for adaptive radiotherapy applications

Cited by 9 publications

References 34 publications

Performance comparison of prediction filters for respiratory motion tracking in radiotherapy

Performance comparison of prediction filters for respiratory motion tracking in radiotherapy

Applications and limitations of machine learning in radiation oncology

Respiratory motion prediction based on deep artificial neural networks in CyberKnife system: A comparative study

Contact Info

Product

Resources

About