Adaptive confidence regions for indirect tracking of moving tumors in radiotherapy

Abstract

Background Target motion in the course of radiotherapy is one of the largest factors affecting the treatment quality of highly dynamic sites such as lung. A critical component of real‐time motion management is not only the prediction of tumor location at a future point in time but assessment of positional uncertainty for the purposes of margin adjustment and optimization of validation schemes. Purpose In this study, we propose to investigate the ability of a confidence estimator to accurately reflect the reliability of individual target position predictions and prospectively detect large prediction errors by relying exclusively on a surrogate signal. Methods This work uses a Bayesian framework for indirect tracking. While constant covariance estimates are commonly used to express the uncertainty of the models involved, in this study new adaptive estimates are derived from the surrogate behavior to reflect increasing uncertainty when the breathing conditions differ from the reference conditions observed during the training step. The accuracy of the resulting 95% predicted confidence regions (CRs) is evaluated on nine breathing sequences involving changes of respiratory types (free, thoracic, abdominal, deep). The breathing motions are collected simultaneously from a lung target and two different surrogate signals (an external marker and an anatomical location within the liver). Receiver operating characteristic (ROC) analysis is performed to evaluate the ability of the predicted uncertainty to prospectively detect large prediction errors. Results Higher CR accuracy is obtained when using the proposed adaptive estimates over using constant estimations: on average over the cohort, the proportion of actual target positions lying within the 95% CR is increased by 40 and 35 p.p. with the internal and external surrogates. The time‐dependent inflation of the CR width tends to match the magnitude variation of the prediction errors: the adaptive CR effectively enlarges when the target position cannot be predicted reliably, which corresponds to potentially high prediction errors. More precisely, the ROC analysis indicates that the proposed uncertainty estimate can detect if prediction errors are greater than 5 mm with on average high sensitivity (90%) and modest specificity (54% and 47% from internal and external surrogates, respectively). Conclusions While relying exclusively on the surrogate motion characteristics being continuously monitored, the Bayesian framework coupled to adaptive uncertainty estimations can provide reliable CR able to detect large prediction errors. The findings of this study could be further used to automatically trigger risk management mechanisms prospectively.

Uncertainty-driven determination of target measurement times for indirect tracking validation in adaptive radiotherapy

“…Since the choice of the surrogate affect the accuracy of the predictions, one external surrogate (abdominal marker) and one internal surrogate (liver structure) are considered. While external markers are commonly used (Bertholet et al 2019), internal surrogates such as the liver can be monitored in realtime and non-invasively during the treatment via ultrasound imaging (O'Shea et al 2016) and can present a stronger and more stable correlation with the lung target over time (Remy et al 2021, Remy andBouchard 2022). Throughout the paper, liver refers to the internal surrogate, while abdomen refers to the external surrogate.…”

“…This way, the data generated presents a stochastic behavior while being representative of human respiratory motion. More details can be found in a previous study (Remy and Bouchard 2022).…”

“…The Bayesian algorithm consists of prediction and correction steps applied recursively. Details and mathematical calculations about the framework can be found in a previous study (Remy and Bouchard 2022).…”

“…No target localization validation is performed. This static version was previously used (Remy and Bouchard 2022). Conversely, a new adaptive framework is proposed in the next section.…”

“…Recent work has proposed a surrogate-based Bayesian framework that combines both spatial correlation and latency compensation tasks while providing confidence regions along with the predictions (Remy and Bouchard 2022). This confidence information can be used to detect when the predictions cannot be inferred with sufficient reliability, and therefore to identify breathing points with a high probability of large prediction error.…”