Many studies using T1 magnetic resonance imaging (MRI) data have found associations between changes in global metrics (e.g. volume) of brain structures and preterm birth. In this work, we use the surface displacement feature extracted from the deformations of the surface models of the third ventricle, fourth ventricle and brainstem to capture the variation in shape in these structures at 8 years of age that may be due to differences in the trajectory of brain development as a result of very preterm birth (24-32 weeks gestation). Understanding the spatial patterns of shape alterations in these structures in children who were born very preterm as compared to those who were born at full term may lead to better insights into mechanisms of differing brain development between these two groups. The T1 MRI data for the brain was acquired from children born full term (FT, n=14, 8 males) and preterm (PT, n=51, 22 males) at age 8-years. Accurate segmentation labels for these structures were obtained via a multi-template fusion based segmentation method. A high dimensional non-rigid registration algorithm was utilized to register the target segmentation labels to a set of segmentation labels defined on an average-template. The surface displacement data for the brainstem and the third ventricle were found to be significantly different (<i>p</i> < 0.05) between the PT and FT groups. Further, spatially localized clusters with inward and outward deformation were found to be associated with lower gestational age. The results from this study present a shape analysis method for pediatric MRI data and reveal shape changes that may be due to preterm birth.
Manual segmentation of anatomy in brain MRI data taken to be the closest to the “gold standard” in quality is often used in automated registration-based segmentation paradigms for transfer of template labels onto the unlabeled MRI images. This study presents a library of template data with 16 subcortical structures in the central brain area which were manually labeled for MRI data from 22 children (8 male, mean age=8±0.6 years). The lateral ventricle, thalamus, caudate, putamen, hippocampus, cerebellum, third vevntricle, fourth ventricle, brainstem, and corpuscallosum were segmented by two expert raters. Cross-validation experiments with randomized template subset selection were conducted to test for their ability to accurately segment MRI data under an automated segmentation pipeline. A high value of the dice similarity coefficient (0.86±0.06, min=0.74, max=0.96) and small Hausdorff distance (3.33±4.24, min=0.63, max=25.24) of the automated segmentation against the manual labels was obtained on this template library data. Additionally, comparison with segmentation obtained from adult templates showed significant improvement in accuracy with the use of an age-matched library in this cohort. A manually delineated pediatric template library such as the one described here could provide a useful benchmark for testing segmentation algorithms.
Tumor segmentation from MRI data is a particularly challenging and time consuming task. Tumors have a large diversity in
shape and appearance with intensities overlapping the normal brain tissues. In addition, an expanding tumor can also deflect
and deform nearby tissue. Our work addresses these last two difficult problems. We use the available MRI modalities (T1,
T1c, T2) and their texture characteristics to construct a multi-dimensional feature set. Further, we extract clusters which
provide a compact representation of the essential information in these features. The main idea in this paper is to incorporate
these clustered features into the 3D variational segmentation framework. In contrast to the previous variational approaches,
we propose a segmentation method that evolves the contour in a supervised fashion. The segmentation boundary is driven
by the learned inside and outside region voxel probabilities in the cluster space. We incorporate prior knowledge about
the normal brain tissue appearance, during the estimation of these region statistics. In particular, we use a Dirichlet prior
that discourages the clusters in the ventricles to be in the tumor and hence better disambiguate the tumor from brain tissue.
We show the performance of our method on real MRI scans. The experimental dataset includes MRI scans, from patients
with difficult instances, with tumors that are inhomogeneous in appearance, small in size and in proximity to the major
structures in the brain. Our method shows good results on these test cases.