PT  - JOURNAL ARTICLE
AU  - Paula Ramirez Gilliland
AU  - Alena Uus
AU  - Milou P.M. van Poppel
AU  - Irina Grigorescu
AU  - Johannes K. Steinweg
AU  - David F.A. Lloyd
AU  - Kuberan Pushparajah
AU  - Andrew P. King
AU  - Maria Deprez
TI  - Automated atlas-based multi-label fetal cardiac vessel segmentation in Congenital Heart Disease
AID  - 10.1101/2022.01.14.476320
DP  - 2022 Jan 01
TA  - bioRxiv
PG  - 2022.01.14.476320
4099  - http://biorxiv.org/content/early/2022/01/17/2022.01.14.476320.short
4100  - http://biorxiv.org/content/early/2022/01/17/2022.01.14.476320.full
AB  - Congenital heart disease (CHD) is the most commonly diagnosed birth defect. T2w black blood MRI provides optimal vessel visualisation, aiding prenatal CHD diagnosis. Common clinical practice involves manual segmentation of fetal heart and vessels for visualisation and reporting purposes.We propose an automated multi-label fetal cardiac vessels deep learning segmentation approach for T2w black blood MRI. Our network is trained using single-label manual segmentations obtained through current clinical practice, combined with a multi-label anatomical atlas with desired multi-label segmentation protocol. Our framework combines deep learning label propagation with 3D residual U-Net segmentation to produce high-quality multi-label output well adapted to the individual subject anatomy.We train and evaluate the network using forty fetal subjects with suspected coarctation of the aorta, achieving a dice score of 0.79 ± 0.02 for the fetal cardiac vessels region. The proposed network outperforms the label propagation and achieves a statistically equivalent performance to a 3D residual U-Net trained exclusively on manual single-label data (p-value>0.05). This multi-label framework therefore represents an advancement over the single-label approach, providing label-specific anatomical information, particularly useful for assessing specific anomaly areas in CHD.Competing Interest StatementThe authors have declared no competing interest.