The purpose of this study is to develop an automatic method to identify plaque components using a single 3D Simultaneous Non-Contrast Angiography and intraPlaque hemorrhage (SNAP) acquisition. Using artifact neural network classifier with the intensities of multiple images generated from SNAP and the morphology information, the automatic identified components area has a high correlation with manual segmentation on 2D multi-contrast MR images: 0.82 (necrotic core), 0.79 (calcification) and 0.88 (fibrous tissue). This study further enhanced ability of 3D SNAP sequence in plaque components identification, suggesting SNAP would be a practical clinical solution for carotid atherosclerotic plaque evaluation.
This abstract and the presentation materials are available to members only; a login is required.