To Learn or Not to Learn Features for Deformable Registration?
This work addresses the problem of feature selection for medical image registration, but it is incremental as it compares existing methods without introducing a new paradigm.
The paper investigated whether deep learning features improve deformable registration compared to traditional features like Self-Similarity Context, finding that DL features and SSC yield comparable and stable performance across datasets, while low-level features do not.
Feature-based registration has been popular with a variety of features ranging from voxel intensity to Self-Similarity Context (SSC). In this paper, we examine the question on how features learnt using various Deep Learning (DL) frameworks can be used for deformable registration and whether this feature learning is necessary or not. We investigate the use of features learned by different DL methods in the current state-of-the-art discrete registration framework and analyze its performance on 2 publicly available datasets. We draw insights into the type of DL framework useful for feature learning and the impact, if any, of the complexity of different DL models and brain parcellation methods on the performance of discrete registration. Our results indicate that the registration performance with DL features and SSC are comparable and stable across datasets whereas this does not hold for low level features.