Deep Learning-Based Automatic Segmentation of Non-contrast Coronary Magnetic Resonance Angiography Images

Coronary Magnetic Resonance Angiography (CMRA) is the only non-invasive coronary artery imaging method without radiation exposure and contrast media, and its application in clinical practice has been increasing. However, image post-processing for clinical diagnosis is time-consuming and requires expertise for radiologists. We proposed a three-dimensional U-Net-based automatic method for CMRA images by transfer learning from a pre-trained model of coronary computed tomography angiography(CCTA) to obtain accurate segmentation of coronary arteries.