Three-stage approach for 2D/3D diffeomorphic multi-modality image registration with textural control : diffeomorphic multi-modality image registration

Chen, Ke and Han, Huan (2024) Three-stage approach for 2D/3D diffeomorphic multi-modality image registration with textural control : diffeomorphic multi-modality image registration. SIAM Journal on Imaging Sciences. ISSN 1936-4954 (In Press)

[thumbnail of Chen-Han-SIAM-JIS-2024-Three-stage-approach-for-2D-3D-diffeomorphic-multi-modality-image-registration] Text. Filename: Chen-Han-SIAM-JIS-2024-Three-stage-approach-for-2D-3D-diffeomorphic-multi-modality-image-registration.pdf
Accepted Author Manuscript
Restricted to Repository staff only until 1 January 2099.
License: Creative Commons Attribution 4.0 logo

Download (3MB) | Request a copy

Abstract

Intensity inhomogeneity is a challenging task in image registration. Few past works have addressed the case of intensity inhomogeneity due to texture noise. To address this difficulty, we propose a novel three-stage approach for 2D/3D diffeomorphic multi-modality image registration. The proposed approach contains three stages: (I) H-1+H0+H2 decomposition which decomposes the image pairs into texture, noise and smooth component; (II) Blake-Zisserman homogenization which transforms the geometric features from different modalities into approximately the same modality in terms of the first-order and second-order edge information; (III) Image registration which combines the homogenized geometric features and mutual information. Based on the proposed approach, the greedy matching for multi-modality image registration is discussed and a coarse-to-fine algorithm is also proposed. Furthermore, several numerical tests are performed to validate the efficiency of the proposed approach.