AUTHOR=Beare Richard J. , Chen Jian , Kelly Claire E. , Alexopoulos Dimitrios , Smyser Christopher D. , Rogers Cynthia E. , Loh Wai Y. , Matthews Lillian G. , Cheong Jeanie L. Y. , Spittle Alicia J. , Anderson Peter J. , Doyle Lex W. , Inder Terrie E. , Seal Marc L. , Thompson Deanne K. 

TITLE=Neonatal Brain Tissue Classification with Morphological Adaptation and Unified Segmentation

JOURNAL=Frontiers in Neuroinformatics

VOLUME=10

YEAR=2016

URL=https://www.frontiersin.org/journals/neuroinformatics/articles/10.3389/fninf.2016.00012

DOI=10.3389/fninf.2016.00012

ISSN=1662-5196

ABSTRACT=<p>Measuring the distribution of brain tissue types (tissue classification) in neonates is necessary for studying typical and atypical brain development, such as that associated with preterm birth, and may provide biomarkers for neurodevelopmental outcomes. Compared with magnetic resonance images of adults, neonatal images present specific challenges that require the development of specialized, population-specific methods. This paper introduces MANTiS (Morphologically Adaptive Neonatal Tissue Segmentation), which extends the unified segmentation approach to tissue classification implemented in Statistical Parametric Mapping (SPM) software to neonates. MANTiS utilizes a combination of unified segmentation, template adaptation via morphological segmentation tools and topological filtering, to segment the neonatal brain into eight tissue classes: cortical gray matter, white matter, deep nuclear gray matter, cerebellum, brainstem, cerebrospinal fluid (CSF), hippocampus and amygdala. We evaluated the performance of MANTiS using two independent datasets. The first dataset, provided by the NeoBrainS12 challenge, consisted of coronal <italic>T</italic><sub>2</sub>-weighted images of preterm infants (born ≤30 weeks' gestation) acquired at 30 weeks' corrected gestational age (<italic>n</italic> = 5), coronal <italic>T</italic><sub>2</sub>-weighted images of preterm infants acquired at 40 weeks' corrected gestational age (<italic>n</italic> = 5) and axial <italic>T</italic><sub>2</sub>-weighted images of preterm infants acquired at 40 weeks' corrected gestational age (<italic>n</italic> = 5). The second dataset, provided by the Washington University NeuroDevelopmental Research (WUNDeR) group, consisted of <italic>T</italic><sub>2</sub>-weighted images of preterm infants (born &lt;30 weeks' gestation) acquired shortly after birth (<italic>n</italic> = 12), preterm infants acquired at term-equivalent age (<italic>n</italic> = 12), and healthy term-born infants (born ≥38 weeks' gestation) acquired within the first 9 days of life (<italic>n</italic> = 12). For the NeoBrainS12 dataset, mean Dice scores comparing MANTiS with manual segmentations were all above 0.7, except for the cortical gray matter for coronal images acquired at 30 weeks. This demonstrates that MANTiS' performance is competitive with existing techniques. For the WUNDeR dataset, mean Dice scores comparing MANTiS with manually edited segmentations demonstrated good agreement, where all scores were above 0.75, except for the hippocampus and amygdala. The results show that MANTiS is able to segment neonatal brain tissues well, even in images that have brain abnormalities common in preterm infants. MANTiS is available for download as an SPM toolbox from <ext-link ext-link-type="uri" xlink:href="http://developmentalimagingmcri.github.io/mantis" xmlns:xlink="http://www.w3.org/1999/xlink">http://developmentalimagingmcri.github.io/mantis</ext-link>.</p>