Adaptive Neonate Brain Segmentation

Babies born prematurely are at increased risk of adverse neurodevelopmental outcomes. Recent advances suggest that measurement of brain volumes can help in defining biomarkers for neurodevelopmental outcome. These techniques rely on an accurate segmentation of the MRI data. However, due to lack of contrast, partial volume (PV) effect, the existence of both hypo- and hyper-intensities and significant natural and pathological anatomical variability, the segmentation of neonatal brain MRI is challenging. We propose a pipeline for image segmentation that uses a novel multi-model Maximum a posteriori Expectation Maximisation (MAP-EM) segmentation algorithm with a prior over both intensities and the tissue proportions, a B0 inhomogeneity correction, and a spatial homogeneity term through the use of a Markov Random Field. This robust and adaptive technique enables the segmentation of images with high anatomical disparity from a normal population. Furthermore, the proposed method implicitly models Partial Volume, mitigating the problem of neonatal white/grey matter intensity inversion. Experiments performed on a clinical cohort show expected statistically significant correlations with gestational age at birth and birthweight. Furthermore, the proposed method obtains statistically significant improvements in Dice scores when compared to the a Maximum Likelihood EM algorithm.

[1]  Stephen M. Smith,et al.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm , 2001, IEEE Transactions on Medical Imaging.

[2]  Ponnada A. Narayana,et al.  Comprehensive Brain MRI Segmentation in High Risk Preterm Newborns , 2010, PloS one.

[3]  Daniel Rueckert,et al.  Automatic segmentation and reconstruction of the cortex from neonatal MRI , 2007, NeuroImage.

[4]  Daniel Rueckert,et al.  A common neonatal image phenotype predicts adverse neurodevelopmental outcome in children born preterm , 2010, NeuroImage.

[5]  Jennifer L. Cuzzocreo,et al.  Segmentation of Brain Images Using Adaptive Atlases with Application to Ventriculomegaly , 2011, IPMI.

[6]  Koenraad Van Leemput,et al.  A unifying framework for partial volume segmentation of brain MR images , 2003, IEEE Transactions on Medical Imaging.

[7]  Daniel Rueckert,et al.  A dynamic 4D probabilistic atlas of the developing brain , 2011, NeuroImage.

[8]  Simon K. Warfield,et al.  Automatic segmentation of newborn brain MRI , 2009, NeuroImage.

[9]  P. P. Berg,et al.  Neurologic and Developmental Disability at Six Years of Age After Extremely Preterm Birth , 2006 .

[10]  Jun Zhang,et al.  The Mean Field Theory In EM Procedures For Markov Random Fields , 1991, Proceedings of the Seventh Workshop on Multidimensional Signal Processing.

[11]  Koenraad Van Leemput,et al.  Automated model-based tissue classification of MR images of the brain , 1999, IEEE Transactions on Medical Imaging.

[12]  Sébastien Ourselin,et al.  Fast free-form deformation using graphics processing units , 2010, Comput. Methods Programs Biomed..

[13]  W. Eric L. Grimson,et al.  Adaptive Segmentation of MRI Data , 1995, CVRMed.

[14]  Suyash P. Awate,et al.  Clinical Neonatal Brain MRI Segmentation Using Adaptive Nonparametric Data Models and Intensity-Based Markov Priors , 2007, MICCAI.

[15]  Marc Modat,et al.  LoAd: A locally adaptive cortical segmentation algorithm , 2011, NeuroImage.

[16]  Sébastien Ourselin,et al.  Block Matching: A General Framework to Improve Robustness of Rigid Registration of Medical Images , 2000, MICCAI.

[17]  Mohamed-Jalal Fadili,et al.  Brain tissue classification of magnetic resonance images using partial volume modeling , 2000, IEEE Transactions on Medical Imaging.