Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

White matter segmentation of Brain MRI during infancy

Péporté, Michèle, Ilea, Dana E., Twomey, Eilish and Whelan, Paul F. orcid logoORCID: 0000-0001-9230-7656 (2013) White matter segmentation of Brain MRI during infancy. In: BioPIC 2013 BioPhotonics and imagining conference, 25-27 March, Dublin, Ireland.

Abstract
The objective of this study is the development of an automatic segmentation framework to measure the volume changes in white matter tissue from premature infant MRI data. Due to the early stage of the developing brain which results in a high water content in brain tissue, several major computational challenges arise including artefacts, intensity variations and partial volume effect.The first component of the framework is the development of a novel brain extraction method [1][2]. Due to the overlapping of intensity values across different brain tissues, a primary challenge is the removal of non-brain tissue such as skull, fluid, fat and body parts.The second component involves the intensity inhomogeneities called bias field and has a significant effect on the segmentation. The intensity variations described as a low-frequency multiplicative artefact is a result of the inhomogeneity in the magnetic field during the MRI acquisition.The last component is a novel probabilistic model which segments and measures the white matter volume. The key element is the classification of the partial volume voxels which is achieved by an expectation-maximization algorithm combined with a probabilistic segmentation scheme. Examples of each step of this framework are presented in Fig. 1
Metadata
Item Type:Conference or Workshop Item (Poster)
Event Type:Conference
Refereed:No
Uncontrolled Keywords:computer vision; cerebral palsy; Neurodevelopment impairment; White matter; Image processing; Automated analysis
Subjects:UNSPECIFIED
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering
Research Initiatives and Centres > Research Institute for Networks and Communications Engineering (RINCE)
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
ID Code:18534
Deposited On:17 Jul 2013 09:43 by Mark Sweeney . Last Modified 18 Jan 2023 12:15
Documents

Full text available as:

[thumbnail of Whelan_2013_7.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
413kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record