Deformable registration using edge‐preserving scale space for adaptive image‐guided radiation therapy
نویسندگان
چکیده
Incorporating of daily cone-beam computer tomography (CBCT) image into online radiation therapy process can achieve adaptive image-guided radiation therapy (AIGRT). Registration of planning CT (PCT) and daily CBCT are the key issues in this process. In our work, a new multiscale deformable registration method is proposed by combining edge-preserving scale space with the multilevel free-form deformation (FFD) grids for CBCT-based AIGRT system. The edge-preserving scale space, which is able to select edges and contours of images according to their geometric size, is derived from the total variation model with the L1 norm (TV-L1). At each scale, despite the noise and contrast resolution differences between the PCT and CBCT, the selected edges and contours are sufficiently strong to drive the deformation using the FFD grid, and the edge-preserving property ensures more meaningful spatial information for mutual information (MI)-based registration. At last, the deformation fields are gained by a coarse to fine manner. Furthermore, in consideration of clinical application we designed an optimal estimation of the TV-L1 parameters by minimizing the defined offset function for automated registration. Six types of patients are studied in our work, including rectum, prostate, lung, H&N (head and neck), breast, and chest cancer patients. The experiment results demonstrate the significance of the proposed method both quantitatively with ground truth known and qualitatively with ground truth unknown. The applications for AIGRT, including adaptive deformable recontouring and redosing, and DVH (dose volume histogram) analysis in the course of radiation therapy are also studied.
منابع مشابه
A Software Toolkit for Multi-Image Registration and Segmentation in IGRT and ART
Introduction An essential step in radiation therapy is accurate three-dimensional segmentation of the target and organs at risk. Traditionally, this has been done by manual contouring on a slice-by-slice basis, but modern adaptive radiation therapy (ART) protocols can require segmentation of multiple daily images for each patient [1], increasing the pressure to develop automated methods for seg...
متن کاملA Study on Robustness of Various Deformable Image Registration Algorithms on Image Reconstruction Using 4DCT Thoracic Images
Background: Medical image interpolation is recently introduced as a helpful tool to obtain further information via initial available images taken by tomography systems. To do this, deformable image registration algorithms are mainly utilized to perform image interpolation using tomography images.Materials and Methods: In this work, 4DCT thoracic images of five real patients provided by DI...
متن کاملLarge deformation three-dimensional image registration in image-guided radiation therapy.
In this paper, we present and validate a framework, based on deformable image registration, for automatic processing of serial three-dimensional CT images used in image-guided radiation therapy. A major assumption in deformable image registration has been that, if two images are being registered, every point of one image corresponds appropriately to some point in the other. For intra-treatment ...
متن کاملQuantitative evaluation of a cone‐beam computed tomography–planning computed tomography deformable image registration method for adaptive radiation therapy
Deformable (non-rigid) registration is an essential tool in both adaptive radiation therapy and image-guided radiation therapy to account for soft-tissue changes during the course of treatment. The evaluation method most commonly used to assess the accuracy of deformable image registration is qualitative human evaluation. Here,we propose a method for systematically measuring the accuracy of an ...
متن کاملDeformable Image Registration with Inclusion of Autodetected Homologous Tissue Features
A novel deformable registration algorithm is proposed in the application of radiation therapy. The algorithm starts with autodetection of a number of points with distinct tissue features. The feature points are then matched by using the scale invariance features transform (SIFT) method. The associated feature point pairs are served as landmarks for the subsequent thin plate spline (TPS) interpo...
متن کامل