Fusing speed and phase information for vascular segmentation of phase contrast MR angiograms

Albert C S Chung, J. Alison Noble, Paul Summers

Research output: Contribution to journalArticlepeer-review


This paper presents a statistical approach to aggregating speed and phase (directional) information for vascular segmentation of phase contrast magnetic resonance angiograms (PC-MRA). Rather than relying on speed information alone, as done by others and in our own work, we demonstrate that including phase information as a priori knowledge in a Markov random field (MRF) model can improve the quality of segmentation. This is particularly true in the region within an aneurysm where there is a heterogeneous intensity pattern and significant vascular signal loss. We propose to use a Maxwell-Gaussian mixture density to model the background signal distribution and combine this with a uniform distribution for modelling vascular signal to give a Maxwell-Gaussian-uniform (MGU) mixture model of image intensity. The MGU model parameters are estimated by the modified expectation-maximisation (EM) algorithm. In addition, it is shown that the Maxwell-Gaussian mixture distribution (a) models the background signal more accurately than a Maxwell distribution, (b) exhibits a better fit to clinical data and (c) gives fewer false positive voxels (misclassified vessel voxels) in segmentation. The new segmentation algorithm is tested on an aneurysm phantom data set and two clinical data sets. The experimental results show that the proposed method can provide a better quality of segmentation when both speed and phase information are utilised.

Original languageEnglish
Pages (from-to)109-128
Number of pages20
JournalMedical Image Analysis
Issue number2
Publication statusPublished - Jun 2002


  • Expectation-maximisation (EM) algorithm
  • Flow coherence
  • Magnetic resonance angiography (MRA)
  • Markov random fields (MRF)
  • MR signal modelling and statistical segmentation

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging


Dive into the research topics of 'Fusing speed and phase information for vascular segmentation of phase contrast MR angiograms'. Together they form a unique fingerprint.

Cite this