scholarly journals A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance

2011 ◽  
Author(s):  
Yifei Lou ◽  
Xun Jia ◽  
Xuejun Gu ◽  
Allen Tannenbaum
Keyword(s):  
Image Registration ◽  
Mutual Information ◽  
Input Data ◽  
Fluid Model ◽  
Source Code ◽  
Deformable Image Registration ◽  
Bhattacharyya Distance ◽  
Output Data ◽  
Registration Method ◽  
Viscous Fluid Model

This paper describes a multimodal deformable image registration method on the GPU. It is a CUDA-based implementation of a paper by E. D’Agostino et. al, ‘’A viscous fluid model for multimodal non-rigid image registration using mutual information’’. In addition, we incorporate an alternative metric as opposed to mutual information, called Bhattacharyya Distance, in the recent work of Lou and Tannenbaum. This paper is accompanied with the source code, input data, parameters and output data that the authors used for validating the algorithm.

A viscous fluid model for multimodal non-rigid image registration using mutual information

2003 ◽  
Vol 7 (4) ◽  
pp. 565-575 ◽  
Author(s):  
Emiliano D'Agostino ◽  
Frederik Maes ◽  
Dirk Vandermeulen ◽  
Paul Suetens
Keyword(s):  
Image Registration ◽  
Mutual Information ◽  
Viscous Fluid ◽  
Fluid Model ◽  
Viscous Fluid Model

scholarly journals N-Dimensional Computation of Strain Tensor Images in the Insight Toolkit

2017 ◽  
Author(s):  
Matthew Mccormick
Keyword(s):  
Image Registration ◽  
Constitutive Model ◽  
Displacement Field ◽  
Input Data ◽  
Source Code ◽  
Strain Tensor ◽  
Fundamental Principle ◽  
Local Deformation ◽  
Output Data ◽  
Scientific Publications

Strain quantifies local deformation of a solid body. In medical imaging, strain reflects how tissue deforms under load. Or, it can quantify growth or atrophy of tissue, such as the growth of a tumor. Additionally, strain from the transformation that results from image-to-image registration can be applied as an input to a biomechanical constitutive model.This document describes N-dimensional computation of strain tensor images in the Insight Toolkit (ITK), www.itk.org. Two filters are described. The first filter computes a strain tensor image from a displacement field image. The second filter computes a strain tensor image from a general spatial transform. In both cases, infinitesimal, Green-Lagrangian, or Eulerian-Almansi strain can be generated.This paper is accompanied with the source code, input data, parameters and output data that the authors used for validating the algorithm described in this paper. This adheres to the fundamental principle that scientific publications must facilitate reproducibility of the reported results.

scholarly journals An image sampling framework for the ITK

2010 ◽  
Author(s):  
Marius Staring ◽  
Stefan Klein
Keyword(s):  
Image Registration ◽  
Similarity Measure ◽  
Input Data ◽  
Source Code ◽  
Input Image ◽  
Output Data ◽  
Image Intensity ◽  
Image Sampling ◽  
A Value ◽  
Voxel Grid

This document describes the implementation of image samplers using the Insight Toolkit ITK url{www.itk.org}. Image samplers take a set of `picks’ from an image and store them in an array. A sample consists of the location of the pick (a point) and the corresponding image intensity (a value). Image samplers are useful for image registration, where samples are drawn from the fixed image in order to compute the similarity measure. Together with an image sampler base class, we introduce the following image samplers: 1) a full sampler that draws all voxel coordinates from the input image, 2) a grid sampler that draws samples from a user-specified regular voxel grid, 3 and 4) two random samplers that uniformly draw a user-specified number of samples from the input image.This paper is accompanied with the source code, input data, parameters and output data that the authors used for validating the algorithm described in this paper.

scholarly journals LungRegNet: An unsupervised deformable image registration method for 4D‐CT lung

2020 ◽  
Vol 47 (4) ◽  
pp. 1763-1774 ◽  
Author(s):  
Yabo Fu ◽  
Yang Lei ◽  
Tonghe Wang ◽  
Kristin Higgins ◽  
Jeffrey D. Bradley ◽  
...  
Keyword(s):  
Image Registration ◽  
Deformable Image Registration ◽  
Registration Method ◽  
4D Ct

Dose accumulation with deformable image registration method using helical tomotherapy images for prostate cancer

2019 ◽  
Vol 19 (1) ◽  
pp. 25-29
Author(s):  
Warit Thongsuk ◽  
Imjai Chitapanarux ◽  
Somsak Wanwilairat ◽  
Wannapha Nobnop
Keyword(s):  
Prostate Cancer ◽  
Computed Tomography ◽  
Image Registration ◽  
Cancer Patients ◽  
Helical Tomotherapy ◽  
Deformable Image Registration ◽  
High Dose ◽  
Registration Method ◽  
Dose Accumulation ◽  
Dose Volume

AbstractPurpose:To evaluate changes of accumulated doses from an initial plan in each fraction by deformable image registration (DIR) with daily megavoltage computed tomography (MVCT) images from helical tomotherapy for prostate cancer patients.Materials and methods:The MVCT images of five prostate cancer patients were acquired by using a helical tomotherapy unit before the daily treatment fraction began. All images data were exported to DIR procedures by MIM software, in which the planned kilovoltage computed tomography (kVCT) images were acting as the source images with the daily MVCT acquired as the target images for registration. The automatic deformed structure was used to access the volume variation and daily dose accumulation to each structure. All dose-volume parameters were compared to the initial planned dose.Results:The actual median doses of the planning target volume (PTV) received 70 Gy and 50.4 Gy were decreased at the end of the treatment with an average 1·0 ± 0·67% and 2·1 ± 1·54%, respectively. As regards organs at risk (OARs), the bladder and rectum dose-volume parameters tended to increase from the initial plan. The high-dose regions of the bladder and rectum, however, were decreased from the initial plan at the end of the treatment.Conclusions:The daily actual dose differs from the initial planned dose. The accumulated dose of target tends to be lower than the initial plan, but tends to be higher than the initial plan for the OARs. Therefore, inter-fractional anatomic changes should be considered by the DIR methods, which would be useful as clinically informative and beneficial for adaptive treatment strategies.

scholarly journals IMAGE REGISTRATION BASED ON MAXIMIZATION OF GRADIENT CODE MUTUAL INFORMATION

2011 ◽  
Vol 24 (1) ◽  
pp. 1 ◽  
Author(s):  
Xiaoxiang Wang ◽  
Jie Tian
Keyword(s):  
Image Registration ◽  
Mutual Information ◽  
Search Space ◽  
Image Resolution ◽  
Hill Climbing ◽  
Global Maximum ◽  
Registration Method ◽  
Pixel Intensity ◽  
Biological Images ◽  
Reference Images

Herein one proposes a mutual information-based registration method using pixel gradient information rather than pixel intensity information. Special care is paid to finding the global maximum of the registration function. In particular, one uses simulated annealing method speeded up by including a statistical analysis to reduce the next search space across the cooling schedule. An additional speed up is obtained by combining this numerical strategy with hill-climbing method. Experimental results obtained on a limited database of biological images illustrate that the proposed method for image registration is relatively fast, and performs well as the overlap between the floating and reference images is decreased and/or the image resolution is coarsened.

Sign in / Sign up

Export Citation Format

Share Document