Synthetically trained convolutional neural networks for time-resolved aortic segmentation of four-dimensional flow...

Supervised learning-based approaches are increasingly used for vessel segmentation in four-dimensional (4D) flow cardiovascular magnetic resonance (CMR). However, their widespread adoption is challenged by the need for diverse, reliably annotated datasets, sensitivity to acquisition and reconstruction settings, and the lack of fully defined ground truth.

In this study, we investigated the use of realistic, fluid mechanics-informed synthetic 4D flow CMR data to train convolutional neural networks for time-resolved aortic segmentation. The availability of fully defined ground-truth vessel geometries in synthetic data enabled quantitative evaluation before evaluation on in vivo data acquired across three scanners with varying field strengths and protocols. Four training strategies were evaluated: one using in vivo data only (R-28) and three based on increasing amounts and diversity of synthetic data (S-28, S-multi, and S-full). Performance was assessed using voxel- and surface-based metrics, including Dice similarity coefficient (DSC), Hausdorff distance (HD), and Bland-Altman analysis.

The S-full model achieved the best performance on the in vivo test dataset, with a DSC of 0.956 ± 0.017 and a HD of (1.7 ± 1.5) mm, relative to reference annotations. Bland-Altman analysis of cross-sectional areas showed small biases and narrow limits of agreement, with 1.1% [-10.9, 13.1]% for the ascending aorta and -1.0% [-13.1, 11.1]% for the descending aorta. For the in vivo trained model (R-28) evaluated on synthetic data, relative cross-sectional area measurements yielded biases of 3.1% [-10.9, 17.0]% in the ascending aorta and 4.0% [-8.2, 16.2]% in the descending aorta, relative to synthetic ground truth.

This work demonstrates that purely synthetic 4D flow CMR can be used to train neural networks for time-resolved aortic segmentation of in vivo 4D flow CMR data, enabling fully automatic inference and quantitative evaluation against fully defined ground truth.