Potential of a probabilistic framework for target prediction from surrogate respiratory motion during lung radiotherapy

Abstract

Purpose. Respiration-induced motion introduces significant positioning uncertainties in radiotherapy treatments for thoracic sites. Accounting for this motion is a non-trivial task commonly addressed with surrogate-based strategies and latency compensating techniques. This study investigates the potential of a new unified probabilistic framework to predict both future target motion in real-time from a surrogate signal and associated uncertainty. Method. A Bayesian approach is developed, based on a Kalman filter theory adapted specifically for surrogate measurements. Breathing motions are collected simultaneously from a lung target, two external surrogates (abdominal and thoracic markers) and an internal surrogate (liver structure) for 9 volunteers during 4 min, in which severe breathing changes occur to assess the robustness of the method. A comparison with an artificial non-linear neural network (NN) is performed, although no confidence interval prediction is provided. A static worst-case scenario and a simple static design are investigated. Results. Although the NN can reduce the prediction errors from thoracic surrogate in some cases, the Bayesian framework outperforms in most cases the NN when using the other surrogates: bias on predictions is reduced by 38% and 16% on average when using respectively the liver and the abdomen for the simple scenario, and by respectively 40% and 31% for the worst-case scenario. The standard deviation of residuals is reduced on average by up to 42%. The Bayesian method is also found to be more robust to increasing latencies. The thoracic marker appears to be less reliable to predict the target position, while the liver shows to be a better surrogate. A statistical test confirms the significance of both observations. Conclusion. The proposed framework predicts both the future target position and the associated uncertainty, which can be valuably used to further assist motion management decisions. Further investigation is required to improve the predictions by using an adaptive version of the proposed framework.

Adaptive confidence regions for indirect tracking of moving tumors in radiotherapy

“…Details about the data collection are reported in Ref. 22. To overcome the technical constraints imposing interleaved target and surrogate sagittal slices and an average time sampling of 1 Hz, interpolation (described in the next section) is performed.…”

“…In a previous study, the potential of a Bayesian framework to predict future target motion from a surrogate signal was demonstrated. 22 The power of this approach, based on Kalman filter theory (KFT), is that all available information from the initial time-step,including the uncertainties of the models, is exploited to improve the predictions. For the sake of understanding, a brief summary of the theory is provided.…”

“…Previous research has investigated a Bayesian framework that combines temporal prediction and target-surrogate correlation while deriving uncertainty information. 22 Rather than predicting a unique estimate value, this method outputs a probability density function (PDF) of the future target position conditioned on a series of past surrogate measurements. In particular, while the first statistical moment is used as an estimate of the future target position, the second central moment reflects the uncertainty of the prediction, which can be expressed via a confidence region (CR).…”

“…Previous research has investigated a Bayesian framework that combines temporal prediction and target–surrogate correlation while deriving uncertainty information 22 . Rather than predicting a unique estimate value, this method outputs a probability density function (PDF) of the future target position conditioned on a series of past surrogate measurements.…”

Liver Tumor Motion Estimation Based on Respiration-Induced Skin Change Using Principal Component Analysis and Nearest Neighbor Method

“…It affects target coverage and treatment effectiveness adversely. To compensate this motion, estimating the internal target from external signal (called surrogate) is a potential solution [4][5][6].…”