We conclude that the LDeform algorithm can facilitate the adaptive decision-making process during lung cancer radiotherapy.
Conventional radiotherapy for large lung tumors is given over several weeks, during which the tumor typically regresses in a highly nonuniform and variable manner. Adaptive radiotherapy would ideally follow these shape changes, but we need an accurate method to extrapolate tumor shape changes. We propose a computationally efficient algorithm to quantitate tumor surface shape changes that makes minimal assumptions, identifies fixed points, and can be used to predict future tumor geometrical response.
We tested and validated our technique on 31 longitudinal CT/MRI subjects, with five to nine time points each. Based on this tumor deformation analysis, regions of local growth, shrinkage, and anchoring are identified and tracked across multiple time points. This categorization in turn represents a rational biomarker of local response. Results demonstrate useful predictive power, with an averaged Dice coefficient and surface mean-squared error of 0.85 and 2.8 mm, respectively, over all images.
A novel combination of nonrigid iterative closest point (ICP) and local shape-preserving map algorithms, LDeform, is developed to enable visualization, prediction, and categorization of both diffeomorphic and nondiffeomorphic tumor deformations during an extended course of radiotherapy.
This website uses cookies to ensure you get the best experience on our website.