liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A Global Linear Optimization Framework for Adaptive Filtering and Image Registration
Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology. (Medicinsk Bildanalys)
2015 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Digital medical atlases can contain anatomical information which is valuable for medical doctors in diagnosing and treating illnesses. The increased availability of such atlases has created an interest for computer algorithms which are capable of integrating such atlas information into patient specific dataprocessing. The field of medical image registration aim at calculating how to match one medical image to another. Here the atlas information could give important hints of which kinds of motion are plausible in different locations of the anatomy. Being able to incorporate such atlas specific information could potentially improve the matching of images and plausibility of image registration - ultimately providing a more correct information on which to base health care diagnosis and treatment decisions.

In this licentiate thesis a generic signal processing framework is derived : Global Linear Optimization (GLO). The power of the GLO framework is first demonstrated quantitatively in a very high performing image denoiser. Important proofs of concepts are then made deriving and implementing three important capabilities regarding adaptive filtering of vector fields in medica limage registration:

  1. Global regularization with local anisotropic certainty metric.
  2. Allowing sliding motion along organ and tissue boundaries.
  3. Enforcing an incompressible motion in specific areas or volumes.

In the three publications included in this thesis, the GLO framework is shown to be able to incorporate one each of these capabilities. In the third and final paper a demonstration is made how to integrate more and more of the capabilities above into the same GLO to perform adaptive processing on relevant clinical data. It is shown how each added capability improves the result of the image registration. In the end of the thesis there is a discussion which highlights the advantage of the contributions made as compared to previous methods in the scientific literature.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2015. , 61 p.
Series
Linköping Studies in Science and Technology. Thesis, ISSN 0280-7971 ; 1711
Keyword [en]
Global Linear Optimization, Linear Optimization, Regularization, Medical Image Registration, Structure Tensor
National Category
Medical Image Processing
Identifiers
URN: urn:nbn:se:liu:diva-117024DOI: 10.3384/diss.diva-117024ISBN: 978-91-7519-108-9 (print)OAI: oai:DiVA.org:liu-117024DiVA: diva2:802129
Presentation
2015-05-07, IMT1, plan 13, Campus US, Linköpings universitet, Linköping, 15:15 (English)
Opponent
Supervisors
Projects
Dynamic Context Atlases for Image Denoising and Patient Safety
Funder
Linnaeus research environment CADICSSwedish Research Council, 2011-5176
Available from: 2015-04-17 Created: 2015-04-10 Last updated: 2015-04-20Bibliographically approved
List of papers
1. Globally Optimal Displacement Fields Using Local Tensor Metric
Open this publication in new window or tab >>Globally Optimal Displacement Fields Using Local Tensor Metric
2012 (English)In: Image Processing (ICIP), 2012 19th IEEE International Conference on, 2012, 2957-2960 p.Conference paper, Poster (with or without abstract) (Other academic)
Abstract [en]

In this paper, we propose a novel algorithm for regularizing displacement fields in image registration. The method uses the local structure tensor and gradients of the displacement field to impose a local metric, which is then used optimizing a global cost function. The method allows for linear operators, such as tensors and differential operators modeling the underlying physical anatomy of the human body in medical images. The algorithm is tested using output from the Morphon image registration algorithm on MRI data as well as synthetic test data and the result is compared to the initial displacement field. The results clearly demonstrate the power of the method and the unique features brought forth through the global optimization approach.

Keyword
Image Processing, Image Registration, Regularization, Optimization, Tensor
National Category
Medical Image Processing Signal Processing
Identifiers
urn:nbn:se:liu:diva-81947 (URN)10.1109/ICIP.2012.6467520 (DOI)978-1-4673-2534-9 (ISBN)
Conference
2012 IEEE International Conference on Image Processing, September 30 - October 3, 2012, Orlando, Florida, USA
Projects
Dynamic Context Atlases for Image Denoising and Patient Safety
Funder
Swedish Research Council, 2011-5176Swedish Research Council, 2007-4786
Available from: 2012-09-26 Created: 2012-09-26 Last updated: 2015-04-17Bibliographically approved
2. Motion Field Regularization for Sliding Objects using Global Linear Optimization
Open this publication in new window or tab >>Motion Field Regularization for Sliding Objects using Global Linear Optimization
2015 (English)Conference paper, Oral presentation only (Refereed)
Abstract [en]

In image registration it is often necessary to employ  regularization in one form or another to be able to find a plausible  displacement field. In medical applications, it is useful to define  different constraints for different areas of the data. For instance  to measure if organs have moved as expected after a finished  treatment. One common problem is how to find plausible motion  vectors far away from known motion. This paper introduces a new  method to build and solve a Global Linear Optimizations (GLO)  problem with a novel set of terms which enable specification of  border areas to allow a sliding motion. The GLO approach is  important especially because it allows simultaneous incorporation of  several different constraints using information from medical atlases  such as localization and properties of organs. The power and  validity of the method is demonstrated using two simple, but  relevant 2D test images. Conceptual comparisons with previous  methods are also made to highlight the contributions made in this  paper. The discussion explains important future work and experiments  as well as exciting future improvements to the GLO framework.

Keyword
Image Registration, Missing Data, Medical Image Processing, Global Linear Optimization
National Category
Radiology, Nuclear Medicine and Medical Imaging
Identifiers
urn:nbn:se:liu:diva-112210 (URN)
Conference
The 4th International Conference on Pattern Recognition Applications and Methods, Januari 10-12, Lisbon, Portugal
Projects
Dynamic Context Atlases for Image Denoising and Patient SafetyGlobal Linear Optimization
Funder
Swedish Research Council, 2011-5176Linnaeus research environment CADICS
Available from: 2014-11-18 Created: 2014-11-18 Last updated: 2015-04-17Bibliographically approved
3. Regularization in Medical Image Registration using Global Linear Optimization
Open this publication in new window or tab >>Regularization in Medical Image Registration using Global Linear Optimization
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Common problems in image registration include having large parts of the images contain noisy, uncertain, missing or impossible motion. Regularization is the field that aims to overcome these problems. In this article, we propose a novel framework : Global Linear Optimization (GLO) which we demonstrate has the capabilities to simultaneously and globally regularize with respect to : (1) anisotropic certainty of prior motion field, (2) sliding of organ boundaries and (3) incompressibility of organ interiors. The power of the presented framework consists of being able to spatially adapt which subsets of the data each constraint should affect and then solve a large sparse linear equations system which automatically propagates a solution over the data set through an overlapping localized metric. We demonstrate the validity of the methods and the power of the GLO framework on relevant test cases and on medical data from the DIR-lab.

Keyword
Keywords—Image Registration, Medical Image Analysis, Regularization, Adaptive Filtering, Medical Atlases, Global Methods, Optimization, Global Linear Optimization, Structure Tensor, Anisotropic Filtering, Partial Differential Equations
National Category
Medical Image Processing Other Computer and Information Science
Identifiers
urn:nbn:se:liu:diva-117140 (URN)
Available from: 2015-04-17 Created: 2015-04-17 Last updated: 2015-04-17Bibliographically approved

Open Access in DiVA

fulltext(2036 kB)268 downloads
File information
File name FULLTEXT01.pdfFile size 2036 kBChecksum SHA-512
74cc06c4e4a1ef2ff6212cad89b3697663b2ad0f4b740c0c4fdf90a22903b3dd72131b0c13b3c2739ec26141dc5cca887a76556bf03358170aef6c1df9786546
Type fulltextMimetype application/pdf
omslag(4260 kB)37 downloads
File information
File name COVER02.pdfFile size 4260 kBChecksum SHA-512
97f95901f1250977d6072830bb48aa5d11b38ac08fc21c1be27e32b8bde445dac3a7c338cd4d54ad550e8350fa7bcd5f0305e893020c629a8478e51d86570d38
Type coverMimetype application/pdf

Other links

Publisher's full text

Authority records BETA

Johansson, Gustaf

Search in DiVA

By author/editor
Johansson, Gustaf
By organisation
Medical InformaticsThe Institute of Technology
Medical Image Processing

Search outside of DiVA

GoogleGoogle Scholar
Total: 268 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 1100 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf