A spatiotemporal atlas of MR intensity, tissue probability and shape of the fetal brain with application to segmentation

Abstract

Modeling and analysis of MR images of the developing human brain is a challenge due to rapid changes in brain morphology and morphometry. We present an approach to the construction of a spatiotemporal atlas of the fetal brain with temporal models of MR intensity, tissue probability and shape changes. This spatiotemporal model is created from a set of reconstructed MR images of fetal subjects with different gestational ages. Groupwise registration of manual segmentations and voxelwise nonlinear modeling allow us to capture the appearance, disappearance and spatial variation of brain structures over time. Applying this model to atlas-based segmentation, we generate agespecific MR templates and tissue probability maps and use them to initialize automatic tissue delineation in new MR images. The choice of model parameters and the final performance are evaluated using clinical MR scans of young fetuses with gestational ages ranging from 20.57 to 24.71 weeks. Experimental results indicate that quadratic temporal models can correctly capture growthrelated changes in the fetal brain anatomy and provide improvement in accuracy of atlas-based tissue segmentation.

Quantitative in vivo MRI measurement of cortical development in the fetus

“…Image processing stage Quantification of in vivo fetal brain development is technically challenging (Limperopoulos and Clouchoux 2009;Rousseau et al 2006;Jiang et al 2007;Habas et al 2010). Ultrafast T2-weighted MR images provide good contrast between the different developing cerebral tissues, however, combined fetal and maternal motion during data acquisition results in image degradation (Jiang et al 2007;Rousseau et al 2006;Clouchoux et al 2010b;Gholipour et al 2010a).…”

“…Therefore, in this study, the white matter encompassed several lamination layers, including unmyelinated white matter, subplate, intermediate layer and myelinated white matter, depending on the gestational age (Kostovic and Judas 2002). In vivo fetal brain tissue segmentation is a very complex problem (Habas et al 2010), even with high-resolution image reconstruction, primarily because of the inherently low contrast between fetal brain tissue types. An atlas-based segmentation method based on manual delineation of fetal brain tissues has been described (Habas et al 2010), that facilitates in vivo fetal brain tissue segmentation.…”

A Combined Manifold Learning Analysis of Shape and Appearance to Characterize Neonatal Brain Development

“…the embedding coordinates, given by the manifold learning step. This application contrasts with the methods of, for example Habas et al [28] and Murgasova et al [29] which provide important qualitative snapshots of development directly from the image data, and our quantitative embedding coordinates, provided by combined measure manifold learning, may potentially be directly applied in a wider range of contexts, such as clustering or classification.…”

“…A common characterisation of the developing brain is obtained through spatio-temporal atlases of cross-sectional data acquired at different ages. Good examples are provided by Habas et al [28] and Murgasova et al [29] for fetal and neonatal data respectively. Adaptations of segmentation techniques to neonatal and fetal data have also been developed in the contexts of longitudinal analysis of neonatal and fetal data [30], [31] and of multi-region atlas-based segmentation [10].…”

Slic-Seg: Slice-by-Slice Segmentation Propagation of the Placenta in Fetal MRI Using One-Plane Scribbles and Online Learning

“…Automatic methods rarely work well with medical images due to ambiguous appearance cues. Prior-knowledge brought from different patients in the form of shape/appearance models or propagated atlases [6] may help make the segmentation more robust, but the position and orientation of the placenta within the uterus varies greatly between pregnancies (see Fig. 1(a) and Fig.…”