Change search
ReferencesLink to record
Permanent link

Direct link
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, 400-409Conference 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.

Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 5575
Keyword [en]
Image segmentation - level set method - optimization - gradient descent - Rprop - variational problems - active contours
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-19313DOI: 10.1007/978-3-642-02230-2_41ISI: 000268661000041ISBN: 978-3-642-02229-6 (print)ISBN: 978-3-642-02230-2 (online)OAI: diva2:224261
16th Scandinavian Conference on Image Analysis, June 15-18 2009, Oslo, Norway
Available from2009-07-09 Created:2009-06-17 Last updated:2014-10-08Bibliographically approved
In thesis
1. Segmentation Methods for Medical Image Analysis
Open this publication in new window or tab >>Segmentation Methods for Medical Image Analysis : Blood vessels, multi-scale filtering and level set methods
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.

Publisher, range
Linköping: Linköping University Electronic Press, 2010. 44 p.
Linköping Studies in Science and Technology. Thesis, ISSN 0280-7971 ; 1434
Image segmentation, Medical image analysis, Level set method, Quadrature filter, Multi-scale
National Category
Computer Vision and Robotics (Autonomous Systems)
urn:nbn:se:liu:diva-54181 (URN)LIU-TEK-LIC-2010:5 (Local ID)978-91-7393-410-7 (ISBN)LIU-TEK-LIC-2010:5 (Archive number)LIU-TEK-LIC-2010:5 (OAI)
2010-04-15, K3, Kåkenhus, Campus Norrköping, Linköpings universitet, Norrköping, 13:00 (English)
Available from2010-04-20 Created:2010-03-01 Last updated:2013-09-19Bibliographically approved

Open Access in DiVA

fulltext(615 kB)1022 downloads
File information
File name FULLTEXT01.pdfFile size 615 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Andersson, ThordLäthén, GunnarLenz, ReinerBorga, Magnus
By organisation
Medical InformaticsThe Institute of TechnologyCenter for Medical Image Science and Visualization (CMIV)Digital Media
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 1022 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

Altmetric score

Total: 569 hits
ReferencesLink to record
Permanent link

Direct link