Automatic Whole Brain MRI Segmentation of the Developing Neonatal Brain

Antonios Makropoulos, Ioannis S. Gousias, Christian Ledig, Paul Aljabar, Ahmed Serag, Joseph Vilmos Hajnal, Anthony David Edwards, Serena Jane Counsell, D Rueckert

Research output: Contribution to journalArticlepeer-review

266 Citations (Scopus)

Abstract

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.
Original languageEnglish
Pages (from-to)1818 - 1831
JournalIEEE Transactions on Medical Imaging
Volume33
Issue number9
Early online date6 May 2014
DOIs
Publication statusPublished - Sept 2014

Fingerprint

Dive into the research topics of 'Automatic Whole Brain MRI Segmentation of the Developing Neonatal Brain'. Together they form a unique fingerprint.

Cite this