Prediction of CSF Intervention in Fetal Ventriculomegaly via Artificial Intelligence-Powered Normative Modeling

Fetal ventriculomegaly (VM) is common and largely benign when isolated. However, it can occasionally progress to hydrocephalus, a more severe condition associated with increased mortality and neurodevelopmental delay that may require surgical postnatal intervention. Accurate differentiation between VM and hydrocephalus is essential but remains challenging, relying on subjective assessment and limited 2D measurements. Deep learning-based segmentation offers a promising solution for objective and reproducible volumetric analysis. This work presents an artificial intelligence-powered method for segmentation, volume quantification, and classification of the ventricles in fetal brain MRI to predict the need for postnatal intervention.

This retrospective study included 222 patients with singleton pregnancies. An nnUNet was trained to segment the fetal ventricles on 20 manually segmented, institutional fetal brain MRIs combined with 80 studies from a publicly available data set. The validated model was then applied to 138 normal fetal brain MRIs to generate a normative reference range across a range of gestational ages (18-36 weeks). Finally, it was applied to 64 fetal brains with VM (14 of which required postnatal intervention). Receiver operating characteristic curves and area under curve (AUC) to predict VM and a need for postnatal intervention were calculated.

The nnUNet predicted segmentation of the fetal ventricles in the reference data set were of high quality and accurate (median Dice score: 0.96; interquartile range: 0.93-0.99). A normative reference range of ventricular volumes across gestational ages was developed by using automated segmentation volumes. The optimal threshold for identifying VM was 2 SD from normal with a sensitivity of 92% and a specificity of 93% (AUC 0.97; 95% CI: 0.91-0.98). When normalized to intracranial volume, fetal ventricular volume was higher and subarachnoid volume lower among those who required postnatal intervention (P < .001, P = .003). The optimal threshold for identifying the need for postnatal intervention was 11 SD from normal, with a sensitivity of 86% and a specificity of 100% (AUC: 0.97; 95% CI: 0.86-1.00).

This work introduces a deep learning-based method for fast and accurate quantification of ventricular volumes in fetal brain MRI. A normative reference standard derived by using this method can predict VM and a need for postnatal CSF intervention. Increased ventricular volume is a strong predictor of postnatal intervention.