Atlas-based segmentation of developing tissues in the human brain with quantitative validation in young fetuses

Abstract

Imaging of the human fetus using magnetic resonance (MR) is an essential tool for quantitative studies of normal as well as abnormal brain development in utero. However, because of fundamental differences in tissue types, tissue properties and tissue distribution between the fetal and adult brain, automated tissue segmentation techniques developed for adult brain anatomy are unsuitable for this data. In this paper, we describe methodology for automatic atlas-based segmentation of individual tissue types in motion-corrected 3D volumes reconstructed from clinical MR scans of the fetal brain. To generate anatomically correct automatic segmentations, we create a set of accurate manual delineations and build an in utero 3D statistical atlas of tissue distribution incorporating developing gray and white matter as well as transient tissue types such as the germinal matrix. The probabilistic atlas is associated with an unbiased average shape and intensity template for registration of new subject images to the space of the atlas. Quantitative whole brain 3D validation of tissue labeling performed on a set of 14 fetal MR scans (20.57-22.86 weeks gestational age) demonstrates that this atlas-based EM segmentation approach achieves consistently high DSC performance for the main tissue types in the fetal brain. This work indicates that reliable measures of brain development can be automatically derived from clinical MR imaging and opens up possibility of further 3D volumetric and morphometric studies with multiple fetal subjects.

Figure 1

A coronal view from an average shape and intensity MR T2w image of the young fetal brain. In addition to developing cortical gray matter (GM) and white matter (WM), a layer of the germinal matrix (GMAT) is located around ventricles (VENT).

Figure 2

Distribution of voxel intensities in MR T2w image from Figure 1 modeled by fitted Gaussian probability density functions. Note large intensity variability and substantial intensity overlap between brain tissues, especially between developing gray matter (GM) and the germinal matrix (GMAT).

Figure 3

Building of the average shape and intensity model. Reconstructed and motion‐corrected subject images are warped to a reference image (A). The average shape model is obtained by averaging the spatial transformations between the subject images and the reference (B). The subject images with normalized intensities are transformed to the average shape space (C) and averaged to form an average intensity image (D). This image becomes a reference for the next iteration of the procedure (A).

Figure 4

Axial views of rigidly aligned reconstructed MR T2w images of 14 fetal subjects (20.57–22.86 weeks GA) demonstrating variability in brain size and shape.

Figure 5

Axial and coronal views of a reconstructed MR T2w image of a young fetal brain (22.14 weeks GA) with manually traced regions of developing gray matter, white matter, the germinal matrix and ventricles. [Color figure can be viewed in the online issue, which is available at wileyonlinelibrary.com.]

Figure 6

A probabilistic atlas for developing cortical gray matter (GM), white matter (WM), the germinal matrix (GMAT) and ventricles (VENT) constructed by spatial normalization of manual segmentations of MR T2w images of 14 fetal subjects at 20.57–22.86 weeks gestational age. The average shape and intensity image (MR T2w) is used as a high‐quality template for warping of new subject images to the space of the atlas.

Figure 7

A reconstructed MR T2w image of a young fetal brain (21.57 weeks GA) (A) and results of its automatic segmentation in the EM(P_n) mode (B), the EM(P_a) mode (C), and the EM(P_a,P_n) mode (D). Label colors are: blue = gray matter, green = white matter, red = germinal matrix, yellow = ventricles. [Color figure can be viewed in the online issue, which is available at wileyonlinelibrary.com.]

Figure 8

The effect of the neighborhood prior on automatic segmentation of fetal brain images in the area of the occipital lobe: (A and B) axial views of tissue label maps produces in the EM(P_a) and EM(P_a,P_n) modes, respectively, (C and D) coronal views of the same label maps. Label colors are: blue = gray matter, green = white matter, red = germinal matrix, yellow = ventricles. Arrows indicate examples of mislabeled partial volume voxels in the EM(P_a) mode. [Color figure can be viewed in the online issue, which is available at wileyonlinelibrary.com.]

Figure 9

Automatic segmentation of a reconstructed MR T2w image with substantial intensity inhomogeneity: (A) original MR image y(x), (B) bias field estimation b(x), (C) bias‐corrected MR image y_c(x), and (D) labels c(x) from segmentation in the EM(P_a,P_n) mode. Label colors are: blue = gray matter, green = white matter, red = germinal matrix, yellow = ventricles. [Color figure can be viewed in the online issue, which is available at wileyonlinelibrary.com.]

Figure 10

3D visualization of the main tissue types in the young fetal brain obtained from automatic segmentation of the average shape and intensity image. [Color figure can be viewed in the online issue, which is available at wileyonlinelibrary.com.]