Automatic Segmentation of the Aorta and Supra-Aortic Trunks from 4D Flow MRI

Motivation: Few studies have explored segmenting both the supra-aortic trunks and the thoracic aorta, which is essential for analyzing hemodynamics in 4D flow. Goal(s): The automatic segmentation of the aorta and the supra-aortic trunks from 4D flow MRI. Approach: We trained a model to segment the aorta in systolic and diastolic phases and the supra-aortic trunks in systolic phase from both magnitude and phase images. Results: Segmentation of the entire aorta was consistent across systolic and diastolic phases. For supra-aortic trunks, the Dice coefficient was 0.72±0.07 and the Hausdorff distance was 5.42±2.53 mm, which are acceptable given the trunks' small size and complex shape. Impact: We proposed an automatic approach to segment the aorta on different time steps from magnitude images from 4D flow MRI. Additionally, we presented the outcomes of segmenting the supra-aortic trunks using phase and magnitude from the systolic period.