Learning-Based US-MR Liver Image Registration with Spatial Priors

Registration of multi-modality images is necessary for the assessment of liver disease. In this work, we present an image registration workflow which is designed to achieve reliable alignment for subject-specific magnetic resonance (MR) and intercostal 3D ultrasound (US) images of the liver. Spatial priors modeled from the right rib segmentation are utilized to generate the initial alignment between the MR and US scans without the need of any additional tracking information. For rigid alignment, tissue segmentation models are extracted from the MR and US data with a learning-based approach to apply surface point cloud registration. Local alignment accuracy is further improved via the LC2 image similarity metric-based non-rigid registration technique. This workflow was validated with in vivo liver image data for 18 subjects. The best average THE of rigid and non-rigid registration obtained with our dataset was at 6.27 +/- 2.82 mm and 3.63 +/- 1.87 mm, respectively.