A spatio-temporal latent atlas for semi-supervised learning of fetal brain segmentations and morphological age estimation.

Prenatal neuroimaging requires reference models that reflect the normal spectrum of fetal brain development, and summarize observations from a representative sample of individuals. Collecting a sufficiently large data set of manually annotated data to construct a comprehensive in vivo atlas of rapidly developing structures is challenging but necessary for large population studies and clinical application. We propose a method for the semi-supervised learning of a spatio-temporal latent atlas of fetal brain development, and corresponding segmentations of emerging cerebral structures, such as the ventricles or cortex. The atlas is based on the annotation of a few examples, and a large number of imaging data without annotation. It models the morphological and developmental variability across the population. Furthermore, it serves as basis for the estimation of a structures' morphological age, and its deviation from the nominal gestational age during the assessment of pathologies. Experimental results covering the gestational period of 20-30 gestational weeks demonstrate segmentation accuracy achievable with minimal annotation, and precision of morphological age estimation. Age estimation results on fetuses suffering from lissencephaly demonstrate that they detect significant differences in the age offset compared to a control group.

Atlas learning in fetal brain development.

Magnetic resonance imaging has become an important noninvasive technique to gain insight into fetal brain development. Its capabilities go beyond ultrasound when diagnosing high-risk pregnancies. To summarize observations across a population in magnetic resonance imaging studies, reference systems such as atlases that establish correspondences across a cohort are key. In this article, we review the evolution of atlas-building methods in light of their relevance, limitations, and benefits for the modeling of human brain development. Starting with single anatomical templates to which brain scans where mapped to such as Talairach and Montreal Neurological Institute space, we explore the uses of atlases as a means to establish correspondences across a cohort and as a model that captures the population characteristics of the cases the atlas is built from. We discuss methods that capture features of increasingly heterogeneous populations and approaches that are able to generalize with only minimal annotation. The main focus of this review are methods that explicitly model the variability in the population with regard to time, such as in the modeling of disease progression and brain development. We highlight the applicability and limitations of state-of-the art approaches, how insights from the study of disease progression are helpful in developmental studies, and point to the directions of future research that is still necessary.