Iconic Feature Registration with Sparse Wavelet Coefficients

  title={Iconic Feature Registration with Sparse Wavelet Coefficients},
  author={Pascal Cathier},
  journal={Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention},
  volume={9 Pt 2},
  • P. Cathier
  • Published 1 October 2006
  • Computer Science
  • Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
With the growing acceptance of nonrigid registration as a useful tool to perform clinical research, and in particular group studies, the storage space needed to hold the resulting transforms is deemed to become a concern for vector field based approaches, on top of the traditional computation time issue. In a recent study we lead, which involved the registration of more than 22,000 pairs of T1 MR volumes, this constrain appeared critical indeed. In this paper, we propose to decompose the vector… 
A transformation model based on dual-tree complex wavelet transform for non-rigid registration of 3D MRI images
The present study aimed to introduce a new transformation model based on dual-tree complex wavelet transform (DT-CWT) that will help improve the quality of image registration in medical procedures.
Deformable Medical Image Registration: A Survey
This paper attempts to give an overview of deformable registration methods, putting emphasis on the most recent advances in the domain, and provides an extensive account of registration techniques in a systematic manner.
A new method for non-rigid registration of MRI images
In this paper, the parametric registration methods based on function expansion theory are revised and by using the wavelet transform a general and simple framework for non-rigid image registration is


Iconic feature based nonrigid registration: the PASHA algorithm
Fast parametric elastic image registration
An algorithm for fast elastic multidimensional intensity-based image registration with a parametric model of the deformation that is computationally more efficient than other alternatives and capable of accepting expert hints in the form of soft landmark constraints.
Automatic construction of 3-D statistical deformation models of the brain using nonrigid registration
This paper shows how the concept of statistical deformation models (SDMs) can be used for the construction of average models of the anatomy and their variability and demonstrates that SDMs can be constructed so as to minimize the bias toward the chosen reference subject.
3D non-rigid registration by gradient descent on a Gaussian-windowed similarity measure using convolutions
  • P. Cachier, X. Pennec
  • Computer Science, Physics
    Proceedings IEEE Workshop on Mathematical Methods in Biomedical Image Analysis. MMBIA-2000 (Cat. No.PR00737)
  • 2000
The authors present a Gaussian window scheme, where the local statistics (here the sum of local correlation coefficients) are weighted with Gaussian kernels, and show that the criterion can be deducted easily to obtain forces to guide the registration.
Image Registration Using Wavelet-Based Motion Model
An image registration algorithm is developed to estimate dense motion vectors between two images using the coarse-to-fine wavelet-based motion model and the experimental results showed that the wavelets produced better motion estimates with error distributions having a smaller mean and smaller standard deviation.
Animal: Validation and Applications of Nonlinear Registration-Based Segmentation
An automated procedure called ANIMAL (Automatic Nonlinear Image Matching and Anatomical Labeling) is designed to objectively segment gross anatomical structures from 3D MRIs of normal brains to recover 64% of the nonlinear residual variability remaining after linear registries.
Spline-Based Image Registration
A new registration algorithm based on spline representations of the displacement field which can be specialized to solve all of the problems in multiframe image analysis, including the computation of optic flow, stereo correspondence, structure from motion, and feature tracking.
Optical flow estimation using adaptive wavelet zeroing
  • L. Ng, V. Solo
  • Mathematics
    Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348)
  • 1999
A new technique for estimating optical flow based on L/sub 1/ regularisation, which has many zero wavelet coefficients, but unlike wavelet shrinkage some of the remaining coefficients are allowed to "grow".
Voxel-Based Morphometry—The Methods
At its simplest, voxel-based morphometry (VBM) involves a voxel-wise comparison of the local concentration of gray matter between two groups of subjects. The procedure is relatively straightforward