SU-F-J-77: Variations in the Displacement Vector Fields Calculated by Different Deformable Image Registration Algorithms Used in Helical, Axial and Cone-Beam CT Images of a Mobile

2016 ◽  
Vol 43 (6Part9) ◽  
pp. 3424-3424
Author(s):  
I Ali ◽  
J Jaskowiak ◽  
N Alsbou ◽  
S Ahmad
Keyword(s):  
Image Registration ◽  
Vector Fields ◽  
Displacement Vector ◽  
Cone Beam Ct ◽  
Deformable Image Registration ◽  
Ct Images ◽  
Cone Beam

Correlation of displacement vector fields calculated by different deformable image registration algorithms with motion parameters in helical, axial and cone beam CT imaging

2019 ◽  
Vol 19 (3) ◽  
pp. 219-225
Author(s):  
Nesreen Alsbou ◽  
Salahuddin Ahmad ◽  
Imad Ali
Keyword(s):  
Computed Tomography ◽  
Image Registration ◽  
Vector Fields ◽  
Displacement Vector ◽  
Deformable Image Registration ◽  
Ct Images ◽  
Ct Imaging ◽  
Cone Beam ◽  
Helical Computed Tomography ◽  
Motion Parameters

AbstractAim:The purpose of this study is to investigate quantitatively the correlation of displacement vector fields (DVFs) from different deformable image registration (DIR) algorithms to register images from helical computed tomography (HCT), axial computed tomography (ACT) and cone beam computed tomography (CBCT) with motion parameters.Materials and methods:CT images obtained from scanning of the mobile phantom were registered with the stationary CT images using four DIR algorithms from the DIRART software: Demons, Fast-Demons, Horn–Schunck and Lucas–Kanade. HCT, ACT and CBCT imaging techniques were used to image a mobile phantom, which included three targets with different sizes (small, medium and large) that were manufactured from a water-equivalent material and embedded in low-density foam to simulate lung lesions. The phantom was moved with controlled cyclic motion patterns where a range of motion amplitudes (0–20 mm) and frequencies (0·125–0·5 Hz) were used.Results:The DVF obtained from different algorithms correlated well with motion amplitudes applied on the mobile phantom for CBCT and HCT, where the maximal DVF increased linearly with the motion amplitudes of the mobile phantom. In ACT, the DVF correlated less with motion amplitudes where motion-induced strong image artefacts and the DIR algorithms were not able to deform the ACT image of the mobile targets to the stationary targets. Three DIR algorithms produce comparable values and patterns of the DVF for certain CT imaging modality. However, DVF from Fast-Demons deviated strongly from other algorithms at large motion amplitudes.Conclusions:The local DVFs provide direct quantitative values for the actual internal tumour shifts that can be used to determine margins for the internal target volume that consider tumour motion during treatment planning. Furthermore, the DVF distributions can be used to extract motion parameters such as motion amplitude that can be extracted from the maximal or minimal DVF calculated by the different DIR algorithms and used in the management of the patient motion.

SU-EE-A3-06: Deformable Image Registration in Cone-Beam CT Images for Image-Guided Adaptive Radiotherapy

2006 ◽  
Vol 33 (6Part2) ◽  
pp. 1995-1995
Author(s):  
L Zhang ◽  
L Dong ◽  
X Zhu ◽  
A Garden ◽  
A Ahamad ◽  
...  
Keyword(s):  
Image Registration ◽  
Cone Beam Ct ◽  
Deformable Image Registration ◽  
Ct Images ◽  
Adaptive Radiotherapy ◽  
Cone Beam ◽  
Image Guided

A quantitative evaluation of deformable image registration based on MV cone beam CT images: Impact of deformation magnitudes and image modalities

2020 ◽  
Vol 71 ◽  
pp. 82-87 ◽  
Author(s):  
Yuliang Huang ◽  
Chenguang Li ◽  
Haiyang Wang ◽  
Qiaoqiao Hu ◽  
Ruoxi Wang ◽  
...  
Keyword(s):  
Image Registration ◽  
Quantitative Evaluation ◽  
Cone Beam Ct ◽  
Deformable Image Registration ◽  
Ct Images ◽  
Cone Beam

scholarly journals Fully Convolutional Network for Consistent Voxel-Wise Correspondence

2020 ◽  
Vol 34 (07) ◽  
pp. 12935-12942 ◽  
Author(s):  
Yungeng Zhang ◽  
Yuru Pei ◽  
Yuke Guo ◽  
Gengyu Ma ◽  
Tianmin Xu ◽  
...  
Keyword(s):  
Vector Fields ◽  
State Of The Art ◽  
Displacement Vector ◽  
Cone Beam Ct ◽  
Deformable Registration ◽  
Cone Beam ◽  
Nonlinear Mapping ◽  
Convolutional Network ◽  
Mapping Functions ◽  
Fully Convolutional Network

In this paper, we propose a fully convolutional network-based dense map from voxels to invertible pair of displacement vector fields regarding a template grid for the consistent voxel-wise correspondence. We parameterize the volumetric mapping using a convolutional network and train it in an unsupervised way by leveraging the spatial transformer to minimize the gap between the warped volumetric image and the template grid. Instead of learning the unidirectional map, we learn the nonlinear mapping functions for both forward and backward transformations. We introduce the combinational inverse constraints for the volumetric one-to-one maps, where the pairwise and triple constraints are utilized to learn the cycle-consistent correspondence maps between volumes. Experiments on both synthetic and clinically captured volumetric cone-beam CT (CBCT) images show that the proposed framework is effective and competitive against state-of-the-art deformable registration techniques.

Sign in / Sign up

Export Citation Format

Share Document