Fast Unsupervised Segmentation of 3D Magnetic Resonance Angiography

Author

El-Baz, Ayman ; Farag, Aly ; Gimel´farb, Georgy ; El-Ghar, Mohamed Abou ; Eldiasty, T.

Author_Institution

CVIP Lab., Louisville Univ., KY, USA

fYear

2006

Firstpage

93

Lastpage

96

Abstract

A new physically justified adaptive probabilistic model of blood vessels on magnetic resonance angiography (MRA) images is proposed. The model accounts for both laminar (for normal subjects) and turbulent blood flow (in abnormal cases like anemia or stenosis) and results in a fast algorithm for extracting a 3D cerebrovascular system from the MRA data. Experiments with real data sets confirm the high accuracy of the proposed approach.

Keywords

biomedical MRI; blood vessels; haemodynamics; haemorheology; image segmentation; 3D magnetic resonance angiography; MRA images; adaptive probabilistic model; blood vessel; cerebrovascular system; laminar blood flow; turbulent blood flow; unsupervised segmentation; Angiography; Biomedical imaging; Blood flow; Blood vessels; Data mining; Deformable models; Image segmentation; Magnetic resonance; Principal component analysis; Probability; Expectation maximization; blood vessels; laminar blood flow; magnetic resonance angiography; turbulent blood flow;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2006 IEEE International Conference on

Conference_Location

Atlanta, GA

ISSN

1522-4880

Print_ISBN

1-4244-0480-0

Type

conf

DOI

10.1109/ICIP.2006.312370

Filename

4106474