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
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. Vol. 31, no 8, 762-767 p.
Image segmentation, Blood vessels, Medical imaging, Multi-scale, Quadrature filter, Level set method
Medical Laboratory and Measurements Technologies
IdentifiersURN: urn:nbn:se:liu:diva-21046DOI: 10.1016/j.patrec.2009.09.020ISI: 000277552600014OAI: oai:DiVA.org:liu-21046DiVA: diva2:240466
Gunnar Läthén, Jimmy Jonasson and Magnus Borga, Blood vessel segmentation using multi-scale quadrature filtering, 2010, Pattern Recognition Letters, (31), 8, 762-767.
Copyright: Elsevier Science B.V., Amsterdam.