Virtual cohort of fetal cases with suspected coarctation of the aorta from fetal three-dimensional magnetic resonance images

The present dataset is a supplementary dataset to the paper: Hermida, U., van Poppel, M.P.M., Lloyd, D.F.A. et al. Learning the Hidden Signature of Fetal Arch Anatomy: a Three-Dimensional Shape Analysis in Suspected Coarctation of the Aorta. J. of Cardiovasc. Trans. Res. (2022). https://doi.org/10.1007/s12265-022-10335-9

Dataset Description:

We present a database of fetal great arch anatomical models derived from a statistical shape model (SSM) of fetuses with suspected coarctation of the aorta (CoA). The dataset consists of 1000 meshes including the fetal ascending aorta, arterial duct and descending aorta. For each synthetic case, the corresponding PCA coefficients for the 10 first PCA modes, as well as their CoA risk score, are shared. PCA scores are provided both as raw scores and Z-scores. 

To build the SSM, a dataset of 112 motion-corrected 3D fetal cardiovascular magnetic resonance (CMR) images and their corresponding segmentations from cases with suspected CoA was used. Data included confirmed CoA cases as well as false positive (FP) cases. Centerlines were extracted and aligned to build the SSM of the fetal great arches. 

Source of funding

This work was supported by the Wellcome Trust IEH Award [102431] (iFIND project), by core funding from the Wellcome/EPSRC Centre for Medical Engineering [WT203148/Z/16/Z] and by the Rosetrees Trust [A2725]. The research was funded by the National Institute for Health Research (NIHR) Biomedical Research Centre based at Guy’s and St Thomas’ NHS Foundation Trust and King’s College London and supported by the NIHR Clinical Research Facility. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health. D.F.A. Lloyd acknowledges support from the Rothschild Foundation (2020/2017). P. Lamata holds a Wellcome Trust Senior Research Fellowship (209450/Z/17/Z).