Predictive modeling of respiratory tumor motion for real-time prediction of baseline shifts

Abstract

Baseline shifts in respiratory patterns can result in significant spatiotemporal changes in patient anatomy (compared to that captured during simulation), in turn, causing geometric and dosimetric errors in the administration of thoracic and abdominal radiotherapy. We propose predictive modeling of the tumor motion trajectories for predicting a baseline shift ahead of its occurrence. The key idea is to use the features of the tumor motion trajectory over a 1 min window, and predict the occurrence of a baseline shift in the 5 s that immediately follow (lookahead window). In this study, we explored a preliminary trend-based analysis with multi-class annotations as well as a more focused binary classification analysis. In both analyses, a number of different inter-fraction and intra-fraction training strategies were studied, both offline as well as online, along with data sufficiency and skew compensation for class imbalances. The performance of different training strategies were compared across multiple machine learning classification algorithms, including nearest neighbor, Naïve Bayes, linear discriminant and ensemble Adaboost. The prediction performance is evaluated using metrics such as accuracy, precision, recall and the area under the curve (AUC) for repeater operating characteristics curve. The key results of the trend-based analysis indicate that (i) intra-fraction training strategies achieve highest prediction accuracies (90.5-91.4%); (ii) the predictive modeling yields lowest accuracies (50-60%) when the training data does not include any information from the test patient; (iii) the prediction latencies are as low as a few hundred milliseconds, and thus conducive for real-time prediction. The binary classification performance is promising, indicated by high AUCs (0.96-0.98). It also confirms the utility of prior data from previous patients, and also the necessity of training the classifier on some initial data from the new patient for reasonable prediction performance. The ability to predict a baseline shift with a sufficient look-ahead window will enable clinical systems or even human users to hold the treatment beam in such situations, thereby reducing the probability of serious geometric and dosimetric errors.

Figure 1

Baseline shifts as exhibited in three-dimensional motion trajectories recorded from lung cancer patients using the Synchrony system used as patient representative motion in this study (Suh et al 2008).

Figure 2

Schematic showing proposed methodology for prediction of baseline shifts.

Figure 3

Variation of classification performance with variation in oversampling parameter (number of replications of weak positive example set).

Figure 4

Distribution of baseline shift instances across patient fractions.

Figure 5

Comparing F-scores of two classifiers in two iterations of leave-one-patient-out analysis—first with only patients exhibiting baseline shifts, and the second with all patients.

Figure 6

Binary classification performance: ROC curves for three classifiers for 100 iterations of 5-fold cross validation. Mean AUC for linear discriminant = 0.9878; ensemble Adaboost = 0.9794; and Naïve Bayes = 0.9648.