Automatic Time-Resolved Cardiovascular Segmentation of 4D Flow MRI Using Deep Learning.

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Cardiovascular Research

Background:

• 4D flow MRI segmentation of the heart is complex due to motion and low contrast.
• Manual segmentation is time-consuming and challenging.

Purpose of the Study:

• To develop and validate a deep learning (DL) model for automated segmentation of cardiac chambers and great vessels in 4D flow MRI.
• To assess the DL model's performance against manual segmentation.

Main Methods:

• A 3D U-net based neural network was trained on 4D flow MRI data from 205 subjects.
• The model segmented four cardiac chambers, aorta, and pulmonary artery.
• Segmentation accuracy was evaluated using Dice score, Hausdorff distance, and other metrics. Volumetric parameters were compared using Bland-Altman analysis.

Main Results:

• The DL model achieved a mean Dice score of 0.908 ± 0.023.
• High accuracy was observed for Hausdorff distance (1.253 ± 0.293 mm) and average surface distance (0.466 ± 0.136 mm).
• Bland-Altman analysis demonstrated good agreement for end-diastolic and end-systolic volumes between DL and manual segmentations.

Conclusions:

• Deep learning-based segmentation of 4D flow MRI is accurate and efficient.
• This automated approach can expedite cardiac assessment and enhance the clinical utility of 4D flow MRI.