Principal Warps: Thin-Plate Splines and the Decomposition of Deformations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Unsupervised texture segmentation using Gabor filters
Pattern Recognition
Texture Features for Browsing and Retrieval of Image Data
IEEE Transactions on Pattern Analysis and Machine Intelligence
Saliency, Scale and Image Description
International Journal of Computer Vision
Medical Image Processing, Analysis & Visualization in Clinical Research
CBMS '01 Proceedings of the Fourteenth IEEE Symposium on Computer-Based Medical Systems
A new point matching algorithm for non-rigid registration
Computer Vision and Image Understanding - Special issue on nonrigid image registration
Learning best features and deformation statistics for hierarchical registration of MR brain images
IPMI'07 Proceedings of the 20th international conference on Information processing in medical imaging
Non-parametric diffeomorphic image registration with the demons algorithm
MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention
Landmark matching via large deformation diffeomorphisms
IEEE Transactions on Image Processing
A robust hybrid method for nonrigid image registration
Pattern Recognition
Simultaneous geometric - iconic registration
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part II
Non-local shape descriptor: a new similarity metric for deformable multi-modal registration
MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part II
Similarity-Based appearance-prior for fitting a subdivision mesh in gene expression images
MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
| Hi-index | 0.00 |
A general-purpose deformable registration algorithm referred to as "DRAMMS" is presented in this paper. DRAMMS adds to the literature of registration methods that bridge between the traditional voxel-wise methods and landmark/feature-based methods. In particular, DRAMMS extracts Gabor attributes at each voxel and selects the optimal components, so that they form a highly distinctive morphological signature reflecting the anatomical context around each voxel in a multi-scale and multi-resolution fashion. Compared with intensity or mutual-information based methods, the high-dimensional optimal Gabor attributes render different anatomical regions relatively distinctively identifiable and therefore help establish more accurate and reliable correspondence. Moreover, the optimal Gabor attribute vector is constructed in a way that generalizes well, i.e., it can be applied to different registration tasks, regardless of the image contents under registration. A second characteristic of DRAMMS is that it is based on a cost function that weights different voxel pairs according to a metric referred to as "mutual-saliency", which reflects the uniqueness (reliability) of anatomical correspondences implied by the tentative transformation. As a result, image voxels do not contribute equally to the optimization process, as in most voxel-wise methods, or in a binary selection fashion, as in most landmark/feature-based methods. Instead, they contribute according to a continuously-valued mutual-saliency map, which is dynamically updated during the algorithm's evolution. The general applicability and accuracy of DRAMMS are demonstrated by experiments in simulated images, inter-subject images, single-/multi-modality images, and longitudinal images, from human and mouse brains, breast, heart, and prostate.