Fast and automatic coronary artery segmentation using nnU-Net for non-contrast enhanced magnetic resonance coronary angiography

Non-contrast enhanced magnetic resonance coronary angiography (MRCA) is a promising coronary heart disease screening modality. However, its clinical application is hindered by inherent limitations, including low spatial resolution and insufficient contrast between coronary arteries and surrounding tissues. These technical challenges impede fast and automatic coronary artery segmentation. To tackle these issues, we propose a self-configuring deep learning-based approach for automating the segmentation of coronary arteries in MRCA images. The nnU-Net model was trained on MRCA data from 134 subjects and tested on data from 114 subjects. Two radiologists qualitatively evaluated all segmented arteries as good to excellent. Using coronary computed tomography angiography (CCTA) data from the 114 tested subjects as the gold standard. Specifically, we compared the number of branches, the total branch length, and the distance from the base of the coronary sinus to the origin of the corresponding main coronary artery obtained from manual and artificial intelligence measurements in MRCA images with those obtained from CCTA. Experiment results demonstrated that in validation nnU-Net can accurately segment from MRCA images with the Dice score of 0.903 and 0.962 for major coronary arteries and aorta, respectively.In Testing, nnU-Net achieved the Dice score of 0.726 and 0.890 for major coronary arteries and aorta, respectively. Integrating MRCA with nnU-Net to extract coronary arteries offers a non-invasive screening tool for the detection of coronary heart disease, potentially enhancing early detection and reducing reliance from CCTA.