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.

The latent atlas is learned from partially annotated data representing different gestational ages. For any age it encodes variability across the population (top row), and longitudinal development (bottom row).Figure optionsDownload high-quality image (97 K)Download as PowerPoint slideHighlights
• A method for semi-supervised learning of a spatio-temporal latent fetal brain atlas.
• The method achieves segmentation of fetal brain structures between GW 20 and 30.
• The atlas is learnt from few annotations and a large set of non-annotated examples.
• The atlas encodes developmental and cross-sectional population variability.
• Results are reported on the segmentation of ventricles and cortex.