A New Image Similarity Metric for Improving Deformation Consistency in Graph Based Groupwise Image Registration
Image similarity metric (ISM) is used to construct the graph of input images in graph based groupwise image registration (G-GIR). Most existing G-GIR methods adopt image intensity-based ISM. However, image intensity is not directly related to deformation directions in image registration, and inconsistent deformation along the shortest paths in the resulting graph is inevitable, making G-GIR inefficient and inaccurate. We propose a new ISM to build the graph with deformation consistency. Our ISM reduces inconsistent deformation and improves registration outcome.
Deformable Image Registration Using Cue-aware Deep Regression Network
We propose a novel deformable registration method of using the deep neural network to directly learn the mapping from an image pair to the corresponding deformation field. This highly non-linear mapping is modeled by the novel cue-aware deep regression network, in which we adopt contextual cue to better guide the learning process…