Brain volume segmentation in newborn infants using multi-modal MRI with a low inter-slice resolution

Brain volume segmentation from neonatal magnetic resonance images (MRI) offers the possibility of exploring the developmental changes, measuring the brain growth, detecting early disorders and three-dimensional (3D) volume reconstruction. However, such segmentation is challenging mainly due to the fast growth process, complex anatomy of the developing brain and often poor MRI quality. Existing techniques are mainly developed for adult brain and are not applicable to neonates or require additional corrections. In this paper we present an algorithm for brain volume segmentation in neonates using T1-weighted (T1-w) and T2-weighted (T2-w) MRI with a low inter-slice resolution. The method incorporates both intensity and edge information and consists of three main steps: image pre-processing, brain segmentation and 3D brain reconstruction. Our algorithm is tested on real neonatal brain MRI with a gestational age between 39-41 weeks and achieves performance comparable to manual segmentation. Also, experimental segmentation results show that our method is effective and more accurate than segmentation methods originally developed for adults.