Journal
IEEE TRANSACTIONS ON MEDICAL IMAGING
Volume 33, Issue 9, Pages 1818-1831Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2014.2322280
Keywords
Expectation-maximization; hierarchical modelling; image segmentation; model averaging; neonatal brain MRI; partial volume
Categories
Funding
- Department of Health via the National Institute for Health Research (NIHR) Comprehensive Biomedical Research Centre
- King's College London and King's College Hospital NHS Foundation Trust
- Imperial College Healthcare Comprehensive Biomedical Research Centre Funding Scheme
- Medical Research Council Foundation
- Medical Research Council (U.K.)
- Action Medical Research
- Department of Perinatal Imaging and Health at King's College London
- Medical Research Council [MR/K006355/1] Funding Source: researchfish
- National Institute for Health Research [RP-PG-0707-10154] Funding Source: researchfish
- MRC [MR/K006355/1] Funding Source: UKRI
- National Institutes of Health Research (NIHR) [RP-PG-0707-10154] Funding Source: National Institutes of Health Research (NIHR)
Ask authors/readers for more resources
Magnetic resonance (MR) imaging is increasingly being used to assess brain growth and development in infants. Such studies are often based on quantitative analysis of anatomical segmentations of brain MR images. However, the large changes in brain shape and appearance associated with development, the lower signal to noise ratio and partial volume effects in the neonatal brain present challenges for automatic segmentation of neonatal MR imaging data. In this study, we propose a framework for accurate intensity-based segmentation of the developing neonatal brain, from the early preterm period to term-equivalent age, into 50 brain regions. We present a novel segmentation algorithm that models the intensities across the whole brain by introducing a structural hierarchy and anatomical constraints. The proposed method is compared to standard atlas-based techniques and improves label overlaps with respect to manual reference segmentations. We demonstrate that the proposed technique achieves highly accurate results and is very robust across a wide range of gestational ages, from 24 weeks gestational age to term-equivalent age.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available