SAMConvex: Fast Discrete Optimization for CT Registration using Self-supervised Anatomical Embedding and Correlation Pyramid
This work addresses computational efficiency and accuracy in medical image registration for CT scans, which is incremental as it builds on existing cost volume and optimization methods.
The paper tackles the problem of excessive computation and lack of global semantic information in CT image registration by proposing SAMConvex, a fast coarse-to-fine discrete optimization method that uses self-supervised anatomical embedding and correlation pyramids, achieving state-of-the-art performance on inter-patient and intra-patient datasets with registration times of ~2s to ~5s per image pair.
Estimating displacement vector field via a cost volume computed in the feature space has shown great success in image registration, but it suffers excessive computation burdens. Moreover, existing feature descriptors only extract local features incapable of representing the global semantic information, which is especially important for solving large transformations. To address the discussed issues, we propose SAMConvex, a fast coarse-to-fine discrete optimization method for CT registration that includes a decoupled convex optimization procedure to obtain deformation fields based on a self-supervised anatomical embedding (SAM) feature extractor that captures both local and global information. To be specific, SAMConvex extracts per-voxel features and builds 6D correlation volumes based on SAM features, and iteratively updates a flow field by performing lookups on the correlation volumes with a coarse-to-fine scheme. SAMConvex outperforms the state-of-the-art learning-based methods and optimization-based methods over two inter-patient registration datasets (Abdomen CT and HeadNeck CT) and one intra-patient registration dataset (Lung CT). Moreover, as an optimization-based method, SAMConvex only takes $\sim2$s ($\sim5s$ with instance optimization) for one paired images.