Cortical folding alterations in fetuses with isolated non-severe ventriculomegaly

Abstract

Neuroimaging of brain diseases plays a crucial role in understanding brain abnormalities and early diagnosis. Of great importance is the study of brain abnormalities in utero and the assessment of deviations in case of maldevelopment. In this work, brain magnetic resonance images from 23 isolated non-severe ventriculomegaly (INSVM) fetuses and 25 healthy controls between 26 and 29 gestational weeks were used to identify INSVM-related cortical folding deviations from normative development. Since these alterations may reflect abnormal neurodevelopment, our working hypothesis is that markers of cortical folding can provide cues to improve the prediction of later neurodevelopmental problems in INSVM subjects. We analyzed the relationship of ventricular enlargement with cortical folding alterations in a regional basis using several curvature-based measures describing the folding of each cortical region. Statistical analysis (global and hemispheric) and sparse linear regression approaches were then used to find the cortical regions whose folding is associated with ventricular dilation. Results from both approaches were in great accordance, showing a significant cortical folding decrease in the insula, posterior part of the temporal lobe and occipital lobe. Moreover, compared to the global analysis, stronger ipsilateral associations of ventricular enlargement with reduced cortical folding were encountered by the hemispheric analysis. Our findings confirm and extend previous studies by identifying various cortical regions and emphasizing ipsilateral effects of ventricular enlargement in altered folding. This suggests that INSVM is an indicator of altered cortical development, and moreover, cortical regions with reduced folding constitute potential prognostic biomarkers to be used in follow-up studies to decipher the outcome of INSVM fetuses.

Keywords: Cortical folding; Fetal brain; Lasso; MRI; Statistical analysis; Ventriculomegaly.

Fig. 1

Brain MRI of a 26 GW-old healthy control reconstructed from 8 stacks of 2.5 mm slice thickness. From top to bottom: axial, coronal and sagittal views of axial (A) and coronal (B) raw stacks, and final reconstruction (C).

Fig. 2

Fetal brain MRI segmentation: 26.4 GW-old fetus with right INSVM (A) and corresponding segmentation (B), with different labels for left and right WM, cortex and lateral ventricles.

Fig. 3

Inner cortical surface parcellation.

Fig. 4

Total ventricular volume with increasing GA.

Fig. 5

Scatter plots of PGC, NGC, PMC and CI versus GA for each hemisphere, with linear fits for controls and subjects with left or right INSVM, depending on the hemisphere. Note that fetuses with bilateral ventricular enlargement appear as INSVM in both hemispheres.

Fig. 6

Leave-one-out cross-validated mean absolute error evolution using different regularization values. Comparison of Lasso with Group Lasso.

Fig. 7

Total ventricular volume mean absolute error in normal and INSVM cohorts: Comparison between Lasso and Group Lasso. Results are obtained with the optimal cross-validated λ for each method.

Fig. 8

Number of features selected from cortical regions considered by left and right hemisphere. Note that Group Lasso selects all curvature features from a particular region.

Fig. 9

Feature selection counts corresponding to the number of cortical regions where a particular curvature feature was selected.

Fig. 10

Examples of folding measures (selected by our sparse models) against ventricular volume. Linear fit is included to show relationship of measures with increasing ventricular volume.