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
Segmentation Methods for Medical Image Analysis: Blood vessels, multi-scale filtering and level set methods
Linköping University, Center for Medical Image Science and Visualization, CMIV. Linköping University, Department of Science and Technology, Digital Media. Linköping University, The Institute of Technology.ORCID iD: 0000-0002-6457-4914
2010 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Image segmentation is the problem of partitioning an image into meaningful parts, often consisting of an object and background. As an important part of many imaging applications, e.g. face recognition, tracking of moving cars and people etc, it is of general interest to design robust and fast segmentation algorithms. However, it is well accepted that there is no general method for solving all segmentation problems. Instead, the algorithms have to be highly adapted to the application in order to achieve good performance. In this thesis, we will study segmentation methods for blood vessels in medical images. The need for accurate segmentation tools in medical applications is driven by the increased capacity of the imaging devices. Common modalities such as CT and MRI generate images which simply cannot be examined manually, due to high resolutions and a large number of image slices. Furthermore, it is very difficult to visualize complex structures in three-dimensional image volumes without cutting away large portions of, perhaps important, data. Tools, such as segmentation, can aid the medical staff in browsing through such large images by highlighting objects of particular importance. In addition, segmentation in particular can output models of organs, tumors, and other structures for further analysis, quantification or simulation.

We have divided the segmentation of blood vessels into two parts. First, we model the vessels as a collection of lines and edges (linear structures) and use filtering techniques to detect such structures in an image. Second, the output from this filtering is used as input for segmentation tools. Our contributions mainly lie in the design of a multi-scale filtering and integration scheme for de- tecting vessels of varying widths and the modification of optimization schemes for finding better segmentations than traditional methods do. We validate our ideas on synthetical images mimicking typical blood vessel structures, and show proof-of-concept results on real medical images.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press , 2010. , 44 p.
Series
Linköping Studies in Science and Technology. Thesis, ISSN 0280-7971 ; 1434
Keyword [en]
Image segmentation, Medical image analysis, Level set method, Quadrature filter, Multi-scale
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:liu:diva-54181Local ID: LIU-TEK-LIC-2010:5ISBN: 978-91-7393-410-7 (print)OAI: oai:DiVA.org:liu-54181DiVA: diva2:310036
Presentation
2010-04-15, K3, Kåkenhus, Campus Norrköping, Linköpings universitet, Norrköping, 13:00 (English)
Opponent
Supervisors
Available from: 2010-04-20 Created: 2010-03-01 Last updated: 2016-08-31Bibliographically approved
List of papers
1. Flexible and Topologically Localized Segmentation
Open this publication in new window or tab >>Flexible and Topologically Localized Segmentation
2007 (English)In: EuroVis07 Joint Eurographics: IEEE VGTC Symposium on Visualization / [ed] Ken Museth, Torsten Möller, and Anders Ynnerman, Aire-la-Ville, Switzerland: Eurographics Association , 2007, , 179-186 p.179-186 p.Conference paper, Published paper (Refereed)
Abstract [en]

One of the most common visualization tasks is the extraction of significant boundaries, often performed with iso- surfaces or level set segmentation. Isosurface extraction is simple and can be guided by geometric and topological analysis, yet frequently does not extract the desired boundary. Level set segmentation is better at boundary extrac- tion, but either leads to global segmentation without edges, [CV01], that scales unfavorably in 3D or requires an initial estimate of the boundary from which to locally solve segmentation with edges. We propose a hybrid system in which topological analysis is used for semi-automatic initialization of a level set segmentation, and geometric information bounded topologically is used to guide and accelerate an iterative segmentation algorithm that com- bines several state-of-the-art level set terms. We thus combine and improve both the flexible isosurface interface and level set segmentation without edges.

Place, publisher, year, edition, pages
Aire-la-Ville, Switzerland: Eurographics Association, 2007. 179-186 p.
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-40841 (URN)54293 (Local ID)978-3-905673-45-6 (ISBN)54293 (Archive number)54293 (OAI)
Conference
Eurographics/ IEEE-VGTC Symposium on Visualization, 23-25 May, Norrköping, Sweden
Available from: 2009-10-10 Created: 2009-10-10 Last updated: 2013-09-19
2. Phase Based Level Set Segmentation of Blood Vessels
Open this publication in new window or tab >>Phase Based Level Set Segmentation of Blood Vessels
2008 (English)In: Proceedings of 19th International Conference on Pattern Recognition, IEEE Computer Society , 2008, 1-4 p.Conference paper, Published paper (Refereed)
Abstract [en]

The segmentation and analysis of blood vessels hasreceived much attention in the research community. Theresults aid numerous applications for diagnosis andtreatment of vascular diseases. Here we use level setpropagation with local phase information to capture theboundaries of vessels. The basic notion is that localphase, extracted using quadrature filters, allows us todistinguish between lines and edges in an image. Notingthat vessels appear either as lines or edge pairs, weintegrate multiple scales and capture information aboutvessels of varying width. The outcome is a “global”phase which can be used to drive a contour robustly towardsthe vessel edges. We show promising results in2D and 3D. Comparison with a related method givessimilar or even better results and at a computationalcost several orders of magnitude less. Even with verysparse initializations, our method captures a large portionof the vessel tree.

Place, publisher, year, edition, pages
IEEE Computer Society, 2008
Series
International Conference on Pattern Recognition, ISSN 1051-4651
National Category
Medical Laboratory and Measurements Technologies
Identifiers
urn:nbn:se:liu:diva-21054 (URN)10.1109/ICPR.2008.4760970 (DOI)000264729000023 ()978-1-4244-2175-6 (ISBN)978-1-4244-2174-9 (ISBN)
Conference
19th International Conference on Pattern Recognition (ICPR 2008), 8-11 December 2008, Tampa, Finland
Note

©2009 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE: Gunnar Läthén, Jimmy Jonasson and Magnus Borga, Phase Based Level Set Segmentation of Blood Vessels, 2008, Proceedings of 19th International Conference on Pattern Recognition. http://dx.doi.org/10.1109/ICPR.2008.4760970

Available from: 2009-09-28 Created: 2009-09-28 Last updated: 2015-10-09
3. Momentum Based Optimization Methods for Level Set Segmentation
Open this publication in new window or tab >>Momentum Based Optimization Methods for Level Set Segmentation
2009 (English)In: Momentum Based Optimization Methods for Level Set Segmentation: Second International Conference, SSVM 2009, Voss, Norway, June 1-5, 2009. Proceedings / [ed] Gerhard Goos, Juris Hartmanis, and Jan van Leeuwen, Berlin: Springer Berlin/Heidelberg, 2009, 124-136 p.Conference paper, Published paper (Refereed)
Abstract [en]

Segmentation of images is often posed as a variational problem. As such, it is solved by formulating an energy functional depending on a contour and other image derived terms. The solution of the segmentation problem is the contour which extremizes this functional. The standard way of solving this optimization problem is by gradient descent search in the solution space, which typically suffers from many unwanted local optima and poor convergence. Classically, these problems have been circumvented by modifying the energy functional. In contrast, the focus of this paper is on alternative methods for optimization. Inspired by ideas from the machine learning community, we propose segmentation based on gradient descent with momentum. Our results show that typical models hampered by local optima solutions can be further improved by this approach. We illustrate the performance improvements using the level set framework.

Place, publisher, year, edition, pages
Berlin: Springer Berlin/Heidelberg, 2009
Series
Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 5567
National Category
Medical Laboratory and Measurements Technologies
Identifiers
urn:nbn:se:liu:diva-21037 (URN)10.1007/978-3-642-02256-2_11 (DOI)000270543900011 ()3-642-02255-3 (ISBN)978-3-642-02255-5 (ISBN)e-978-3-642-02256-2 (ISBN)
Conference
Second International Conference, SSVM 2009, June 1-5, Voss, Norway
Note

Original Publication: Gunnar Läthén, Thord Andersson, Reiner Lenz and Magnus Borga, Momentum Based Optimization Methods for Level Set Segmentation, 2009, Lecture Notes in Computer Science 5567: Scale Space and Variational Methods in Computer Vision, 124-136. http://dx.doi.org/10.1007/978-3-642-02256-2_11 Copyright: Springer http://www.springerlink.com/

Available from: 2009-09-28 Created: 2009-09-28 Last updated: 2016-08-31Bibliographically approved
4. A Fast Optimization Method for Level Set Segmentation
Open this publication in new window or tab >>A Fast Optimization Method for Level Set Segmentation
2009 (English)In: Image Analysis: 16th Scandinavian Conference, SCIA 2009, Oslo, Norway, June 15-18, 2009. Proceedings / [ed] A.-B. Salberg, J.Y. Hardeberg, and R. Jenssen, Springer Berlin/Heidelberg, 2009, 400-409 p.Conference paper, Published paper (Refereed)
Abstract [en]

Level set methods are a popular way to solve the image segmentation problem in computer image analysis. A contour is implicitly represented by the zero level of a signed distance function, and evolved according to a motion equation in order to minimize a cost function. This function defines the objective of the segmentation problem and also includes regularization constraints. Gradient descent search is the de facto method used to solve this optimization problem. Basic gradient descent methods, however, are sensitive for local optima and often display slow convergence. Traditionally, the cost functions have been modified to avoid these problems. In this work, we instead propose using a modified gradient descent search based on resilient propagation (Rprop), a method commonly used in the machine learning community. Our results show faster convergence and less sensitivity to local optima, compared to traditional gradient descent.

Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2009
Series
Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 5575
Keyword
Image segmentation - level set method - optimization - gradient descent - Rprop - variational problems - active contours
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-19313 (URN)10.1007/978-3-642-02230-2_41 (DOI)000268661000041 ()978-3-642-02229-6 (ISBN)978-3-642-02230-2 (ISBN)
Conference
16th Scandinavian Conference on Image Analysis, June 15-18 2009, Oslo, Norway
Available from: 2009-07-09 Created: 2009-06-17 Last updated: 2016-08-31Bibliographically approved
5. Blood vessel segmentation using multi-scale quadrature filtering
Open this publication in new window or tab >>Blood vessel segmentation using multi-scale quadrature filtering
2010 (English)In: Pattern Recognition Letters, ISSN 0167-8655, Vol. 31, no 8, 762-767 p.Article in journal (Refereed) Published
Abstract [en]

The segmentation of blood vessels is a common problem in medical imagingand various applications are found in diagnostics, surgical planning, trainingand more. Among many dierent techniques, the use of multiple scales andline detectors is a popular approach. However, the typical line lters usedare sensitive to intensity variations and do not target the detection of vesselwalls explicitly. In this article, we combine both line and edge detection usingquadrature lters across multiple scales. The lter result gives well denedvessels as linear structures, while distinct edges facilitate a robust segmentation.We apply the lter output to energy optimization techniques for segmentationand show promising results in 2D and 3D to illustrate the behavior of ourmethod. The conference version of this article received the best paper award inthe bioinformatics and biomedical applications track at ICPR 2008.

Place, publisher, year, edition, pages
Elsevier, 2010
Keyword
Image segmentation, Blood vessels, Medical imaging, Multi-scale, Quadrature filter, Level set method
National Category
Medical Laboratory and Measurements Technologies
Identifiers
urn:nbn:se:liu:diva-21046 (URN)10.1016/j.patrec.2009.09.020 (DOI)000277552600014 ()
Note
Original Publication: Gunnar Läthén, Jimmy Jonasson and Magnus Borga, Blood vessel segmentation using multi-scale quadrature filtering, 2010, Pattern Recognition Letters, (31), 8, 762-767. http://dx.doi.org/10.1016/j.patrec.2009.09.020 Copyright: Elsevier Science B.V., Amsterdam. http://www.elsevier.com/ Available from: 2009-09-28 Created: 2009-09-28 Last updated: 2014-10-08

Open Access in DiVA

Segmentation Methods for Medical Image Analysis : Blood vessels, multi-scale filtering and level set methods(1248 kB)15434 downloads
File information
File name FULLTEXT02.pdfFile size 1248 kBChecksum SHA-512
6cd0636f8268556e1d76f91e6688bbb6d6eefdcc874abfe26a9ec7fea2b35a125b8df433ccf4a9c62813cce75505433eaa02d60396bb53a446f86ffe0abd7f88
Type fulltextMimetype application/pdf
Cover(230 kB)49 downloads
File information
File name COVER02.pdfFile size 230 kBChecksum SHA-512
902c6dd1d6207ea15e8ebfcbca685555b4145212cebc90ec8ddd7b7ffc822b2450d46f6e940c6ff603f7ae1b7a00265b3733fef97208d0a6b333bd1f679fa580
Type coverMimetype application/pdf

Authority records BETA

Läthén, Gunnar

Search in DiVA

By author/editor
Läthén, Gunnar
By organisation
Center for Medical Image Science and Visualization, CMIVDigital MediaThe Institute of Technology
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 15438 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

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 827 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