Improved tissue segmentation by including an MR acquisition model

Dirk H. J. Poot, Marleen de Bruijne, Meike W. Vernooij, M. Arfan Ikram, Wiro J. Niessen

Abstract

This paper presents a new MR tissue segmentation method. In contrast to most previous methods the image formation model includes the point spread function of the image acquisition. This allows optimal combination of images acquired with different contrast weighting, resolutions, and orientations. The proposed method computes the regularized maximum likelihood partial volume segmentation from the images. The quality the resulting segmentation is studied with a simulation experiment and by testing the reproducibility of the segmentation on repeated brain MRI scans. Our results demonstrate improved segmentation quality, especially at tissue edges.

OriginalsprogEngelsk
TitelMultimodal Brain Image Analysis : First International Workshop, MBIA 2011, Held in Conjunction with MICCAI 2011, Toronto, Canada, September 18, 2011. Proceedings
RedaktørerTianming Liu, Dinggang Shen, Luis Ibanez, Xiaodong Tao
Antal sider8
ForlagSpringer
Publikationsdato2011
Sider152-159
ISBN (Trykt)978-3-642-24445-2
ISBN (Elektronisk)978-3-642-24446-9
DOI
StatusUdgivet - 2011
Begivenhed1st International Workshop on Multimodal Brain Image Analysis - Toronto, Canada
Varighed: 18 sep. 201118 sep. 2011
Konferencens nummer: 1

Konference

Konference1st International Workshop on Multimodal Brain Image Analysis
Nummer1
Land/OmrådeCanada
ByToronto
Periode18/09/201118/09/2011
NavnLecture notes in computer science
Vol/bind7012
ISSN0302-9743

Fingeraftryk

Dyk ned i forskningsemnerne om 'Improved tissue segmentation by including an MR acquisition model'. Sammen danner de et unikt fingeraftryk.

Citationsformater