Semantically Guided 3D Abdominal Image Registration with Deep Pyramid Feature Learning

2021 ◽  
pp. 16-21
Author(s):  
Mona Schumacher ◽  
Daniela Frey ◽  
In Young Ha ◽  
Ragnar Bade ◽  
Andreas Genz ◽  
...  
Keyword(s):  
Image Registration ◽  
Feature Learning ◽  
Abdominal Image

EFFICIENT AND AUTOMATIC ABDOMINAL IMAGE REGISTRATION BASED ON ACTIVE CONTOUR

2006 ◽  
Vol 39 (18) ◽  
pp. 267-272
Author(s):  
Xiu Ying Wang ◽  
Cherry Ballangan ◽  
David Feng
Keyword(s):  
Image Registration ◽  
Active Contour ◽  
Abdominal Image

scholarly journals Bi-level Probabilistic Feature Learning for Deformable Image Registration

2020 ◽  
Author(s):  
Risheng Liu ◽  
Zi Li ◽  
Yuxi Zhang ◽  
Xin Fan ◽  
Zhongxuan Luo
Keyword(s):  
Image Registration ◽  
Optimization Model ◽  
State Of The Art ◽  
Feature Learning ◽  
Deformable Registration ◽  
Deep Networks ◽  
Level Model ◽  
Classification Tasks ◽  
Upper Level ◽  
Traditional Approaches

We address the challenging issue of deformable registration that robustly and efficiently builds dense correspondences between images. Traditional approaches upon iterative energy optimization typically invoke expensive computational load. Recent learning-based methods are able to efficiently predict deformation maps by incorporating learnable deep networks. Unfortunately, these deep networks are designated to learn deterministic features for classification tasks, which are not necessarily optimal for registration. In this paper, we propose a novel bi-level optimization model that enables jointly learning deformation maps and features for image registration. The bi-level model takes the energy for deformation computation as the upper-level optimization while formulates the maximum \emph{a posterior} (MAP) for features as the lower-level optimization. Further, we design learnable deep networks to simultaneously optimize the cooperative bi-level model, yielding robust and efficient registration. These deep networks derived from our bi-level optimization constitute an unsupervised end-to-end framework for learning both features and deformations. Extensive experiments of image-to-atlas and image-to-image deformable registration on 3D brain MR datasets demonstrate that we achieve state-of-the-art performance in terms of accuracy, efficiency, and robustness.

Comparative study of NOTES alone vs. NOTES guided by a new image registration system for navigation in the mediastinum: A study in a porcine model

Endoscopy ◽  
2012 ◽  
Vol 44 (10) ◽  
Author(s):  
H Córdova ◽  
R San José Estépar ◽  
A Rodríguez-D'Jesús ◽  
G Martínez-Pallí ◽  
P Arguis ◽  
...  
Keyword(s):  
Image Registration ◽  
Comparative Study ◽  
Porcine Model ◽  
Registration System

Improved 3D Scene Modeling for Image Registration in Change Detection

2019 ◽  
Vol 2019 (7) ◽  
pp. 465-1-465-7
Author(s):  
Sjors van Riel ◽  
Dennis van de Wouw ◽  
Peter de With
Keyword(s):  
Image Registration ◽  
Change Detection ◽  
Scene Modeling ◽  
3D Scene

Development of New Image Registration Techniques – A Research Framework

2018 ◽  
Vol 8 (3) ◽  
pp. 50
Author(s):  
Sindhu Madhuri G. ◽  
Indira Gandhi M P
Keyword(s):  
Image Processing ◽  
Image Registration ◽  
Digital Image Processing ◽  
Digital Image ◽  
Creative Thinking ◽  
Reference Image ◽  
Transformation Technique ◽  
Research Framework ◽  
Registration Process ◽  
Data Source

Image is a basic and fundamental data source for the digital image processing. This image data source is required to be processed into information or intelligence and further to knowledge levels where it is required to understand and migrate into knowledge economy systems. Image registration is one of such key and most important process already identified in the digital image processing domain. Image registration is a process of bringing the reference image and sensed image into a common co-ordinate system, and application of complex transformation techniques for necessary comparison of reference with sensed images obtained from different - views, times, spaces, etc., in order to extract the valuable information and intelligence embedded in them. Due to the complexity of overall image registration process, it is difficult to suggest a single transformation technique even for a specific application. In addition, it is highly impossible to suggest one single transformation technique for comparison of various sensed images with a reference image during the image registration process. This research gap calls for the development of new image registration techniques for the application of more than one transformation technique during the image registration process for the necessary comparisons with reference image & sensed images, those are obtained from the available heterogeneous sources or sensors, based on the requirement. In addition, it is a basic need to attempt for the measurement of effectiveness of the image registration process also. Therefore, a research framework is developed for image registration process and attempted for the measurement of its effectiveness also. This new research area is a novel idea, and is expected to emerge as a provision for the knowledge computations with creative thinking through the embedded intelligence extraction during the complex image registration process.

Sign in / Sign up

Export Citation Format

Share Document