Automatic Attribute Threshold Selection for Blood Vessel Enhancement

Fred N. Kiwanuka; Michael H. F. Wilkinson

doi:10.1109/ICPR.2010.566

Automatic Attribute Threshold Selection for Blood Vessel Enhancement

Fred N. Kiwanuka, Michael H. F. Wilkinson

Intelligent Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

3 Citations (Scopus)

301 Downloads (Pure)

Abstract

Attribute filters allow enhancement and extraction of features without distorting their borders, and never introduce new image features. These are highly desirable properties in biomedical imaging, where accurate shape analysis is paramount. However, setting the attribute-threshold parameters has to date only been done manually. This paper explores simple, fast and automated methods of computing attribute threshold parameters based on image segmentation, thresholding and data clustering techniques. Though several techniques perform well on blood-vessel filtering, the choice of technique appears to depend on the imaging mode.

Original language	English
Title of host publication	Proceedings of the 20th International Conference on Pattern Recognition
Publisher	IEEE
Number of pages	4
ISBN (Electronic)	978-1-4244-7541-4
ISBN (Print)	978-1-4244-7542-1
DOIs	https://doi.org/10.1109/ICPR.2010.566
Publication status	Published - 2010

Keywords

mathematical morphology
clustering
blood-vessel enhancement
automatic thresholding
attribute filters
connected filters

Access to Document

10.1109/ICPR.2010.566

Automatic Attribute Threshold Selection for Blood Vessel EnhancementFinal publisher's version, 973 KBLicence: Unspecified

Handle.net

Persistent link

Cite this

@inproceedings{6f197ffd85e04e5c930e98c9b6c9cc21,

title = "Automatic Attribute Threshold Selection for Blood Vessel Enhancement",

abstract = "Attribute filters allow enhancement and extraction of features without distorting their borders, and never introduce new image features. These are highly desirable properties in biomedical imaging, where accurate shape analysis is paramount. However, setting the attribute-threshold parameters has to date only been done manually. This paper explores simple, fast and automated methods of computing attribute threshold parameters based on image segmentation, thresholding and data clustering techniques. Though several techniques perform well on blood-vessel filtering, the choice of technique appears to depend on the imaging mode.",

keywords = "mathematical morphology, clustering, blood-vessel enhancement, automatic thresholding, attribute filters, connected filters",

author = "Kiwanuka, {Fred N.} and Wilkinson, {Michael H. F.}",

note = "Relation: http://www.rug.nl/informatica/onderzoek/bernoulli Rights: University of Groningen, Johann Bernoulli Institute for Mathematics and Computer Science",

year = "2010",

doi = "10.1109/ICPR.2010.566",

language = "English",

isbn = "978-1-4244-7542-1",

booktitle = "Proceedings of the 20th International Conference on Pattern Recognition",

publisher = "IEEE",

}

TY - GEN

T1 - Automatic Attribute Threshold Selection for Blood Vessel Enhancement

AU - Kiwanuka, Fred N.

AU - Wilkinson, Michael H. F.

N1 - Relation: http://www.rug.nl/informatica/onderzoek/bernoulli Rights: University of Groningen, Johann Bernoulli Institute for Mathematics and Computer Science

PY - 2010

Y1 - 2010

N2 - Attribute filters allow enhancement and extraction of features without distorting their borders, and never introduce new image features. These are highly desirable properties in biomedical imaging, where accurate shape analysis is paramount. However, setting the attribute-threshold parameters has to date only been done manually. This paper explores simple, fast and automated methods of computing attribute threshold parameters based on image segmentation, thresholding and data clustering techniques. Though several techniques perform well on blood-vessel filtering, the choice of technique appears to depend on the imaging mode.

AB - Attribute filters allow enhancement and extraction of features without distorting their borders, and never introduce new image features. These are highly desirable properties in biomedical imaging, where accurate shape analysis is paramount. However, setting the attribute-threshold parameters has to date only been done manually. This paper explores simple, fast and automated methods of computing attribute threshold parameters based on image segmentation, thresholding and data clustering techniques. Though several techniques perform well on blood-vessel filtering, the choice of technique appears to depend on the imaging mode.

KW - mathematical morphology

KW - clustering

KW - blood-vessel enhancement

KW - automatic thresholding

KW - attribute filters

KW - connected filters

U2 - 10.1109/ICPR.2010.566

DO - 10.1109/ICPR.2010.566

M3 - Conference contribution

SN - 978-1-4244-7542-1

BT - Proceedings of the 20th International Conference on Pattern Recognition

PB - IEEE

ER -

Automatic Attribute Threshold Selection for Blood Vessel Enhancement

Abstract

Keywords

Access to Document

Handle.net

Fingerprint

Cite this