Background and objective: The prediction of childbirth-related complications requires realistic patient-specific childbirth simulations with articulated foetal bodies. However, the foetal models used in current simulations are oversimplified and generally based on scaled generic models. This study presents the development and evaluation of a full-body (hands and feet excluded) foetal statistical shape model (SSM) based on CT scans to generate fast and accurate foetal geometries and lower the simulation errors due to linear scaling.
Methods: The developed SSM was based on a dataset of 96 subjects under one year of age. All scans were segmented and articulated to put the subjects in a similar posture. Then, the bone contours were extracted using an alpha-shape algorithm to decrease the model's complexity. Bones were individually fitted to a template mesh to obtain point correspondences, and a PCA was conducted on the concatenated skeletons to capture the morphological variations between subjects. A PLSR was trained to allow skeletal geometry prediction using a set of anthropometrical data and bone measurements.
Results: Our shape model predicted the bone geometry with a root mean square error (RMSE) of 2.10 ± 1.42 mm for the head-only model and with an RMSE = 6.69 ± 3.85 mm for the full-body model. For all models, the SSM performed better at predicting the bone geometries than the mean shape obtained by PCA, considered as a baseline.
Conclusions: The present study proposed a first complete foetal SSM, allowing a fast and accurate prediction of the bone geometries using a reduced set of easily accessible predictors. This opens new avenues in the realistic childbirth modeling with articulated foetus for predicting physiological delivery and associated complication scenarios.
Keywords: Childbirth simulations; Fetal bone shape prediction; Foetal modelling; Statistical shape modelling.
Copyright © 2025 Elsevier B.V. All rights reserved.