A high-dimensional respiratory motion modeling method based on machine learning

Purpose: Respiratory motion of the human body remains a major challenge in procedures for percutaneous puncture intervention. A solution is to develop a respiratory motion model. The aim of this study is to construct a respiratory motion model that can accommodate extreme respiratory conditions. Methods: Principal component analysis (PCA) and the support vector regression (SVR) method were employed as the framework to build the respiratory motion model. In the first stage, internal respiratory signals and respiratory surrogate signals are extracted. In the second stage, the respiratory motion model based on SVR is established. This study proposes a unique data augmentation method to improve the model robustness and the corresponding response capacity under extreme respiratory conditions. Finally, relevant evaluation indicators are used to evaluate the motion prediction accuracy of a reference model and the model in this study. Results: When estimating the motion of the end-inspiratory phase (T00), the mean target registration error (TRE) of the motion estimate of the model after data augmentation was 1.28 +/- 0.24 mm, while that of the model before data augmentation and that of the reference model were 1.67 +/- 0.55 mm and 2.29 +/- 1.06 mm, respectively. When estimating the motion of all phases, the mean TRE of the model after data augmentation was 1.26 +/- 0.23 mm, which was also lower than that of the model before data augmentation. The data augmentation method improves the accuracy of the model and is statistically significant. Conclusion: Displaying excellent performance under extrapolation conditions, the proposed model effectively improves both accuracy and robustness.