Single- and multimodal subvoxel registration of dissimilar medical images using robust similarity measures

  title={Single- and multimodal subvoxel registration of dissimilar medical images using robust similarity measures},
  author={Christophoros Nikou and Fabrice Heitz and Jean-Paul Armspach and Izzie Jacques Namer},
  booktitle={Medical Imaging},
Although a large variety of image registration methods have been described in the literature, only a few approaches have attempted to address the rigid registration of medical images showing gross dissimilarities (due for instance to lesion evolution). In the present paper, we develop driven registration algorithms, relying on robust pixel similarity metrics, that enable an accurate (subvoxel) rigid registration of dissimilar single or multimodal 2D/3D images. In the proposed approach, gross… 

Multi-modal non-rigid registration of volumetric medical images

This dissertation examines and explains the rather unexpected behavior of Mutual Information when applied to structureless image regions or regions covering only a limited number of image pixels, and an intensity mapping technique is presented to overcome the statistical consistency problem when estimating Mutual Information for small image regions.

Multimodal Image Registration by Maximization of the Correlation Ratio

This paper addresses the determination of a new measure based on standard statistics from a theoretical point of view and shows that the correlation ratio naturally leads to a known concept of probability theory, the \textit{correlation ratio}.

Rigid and non-rigid image registration and its association with mutual information: a review

A thorough introduction into the practice of medical image registration and its association with Mutual information (MI), a popular entropy-based similarity measure which has recently experienced a prolific expansion in a number of image registration applications.

The Correlation Ratio as a New Similarity Measure for Multimodal Image Registration

This paper addresses the determination of a new measure based on standard statistics from a theoretical point of view and shows that it naturally leads to a known concept of probability theory, the correlation ratio, which is suggested to provide a good trade-off between accuracy and robustness.

Unifying maximum likelihood approaches in medical image registration

This paper clarifies the assumptions on which a number of popular similarity measures rely and shows that the search for an optimal measure can be cast into a maximum likelihood estimation problem.

Towards a Better Comprehension of Similarity Measures Used in Medical Image Registration

The motivation of this paper is to determine what are the assumptions corresponding to a number of popular similarity measures in order to better understand their use, and finally help choosing the one which is the most appropriate for a given class of problems.

Local Intensity Mapping for Hierarchical Non-rigid Registration of Multi-modal Images Using the Cross-Correlation Coefficient

This paper presents a new intensity mapping algorithm which can locally transform images of different modalities into an intermediate pseudo-modality and uses the local joint intensity histograms of the coarsely registered sub-images and allows the use of the more robust cross-correlation coefficient for the matching of smaller patches.

Rigid registration of 3-D ultrasound with MR images: a new approach combining intensity and gradient information

An image-based technique to rigidly register intraoperative three-dimensional ultrasound (US) with preoperative magnetic resonance (MR) images by maximization of a similarity measure which generalizes the correlation ratio and whose novelty is to incorporate multivariate information from the MR data.

Registration of three dimensional medical images

This research aims to further develop non-invasive retrospective registration techniques that are more accurate, robust and fully automatic in the field of medical image registration.



A Registration and Interpolation Procedure for Subvoxel Matching of Serially Acquired MR Images

The sinc-based interpolation technique enabled serially acquired MR images to be positionally matched to subvoxel accuracy so that small changes in the brain could be distinguished from effects due to misregistration.

A survey of image registration techniques

This paper organizes this material by establishing the relationship between the variations in the images and the type of registration techniques which can most appropriately be applied, and establishing a framework for understanding the merits and relationships between the wide variety of existing techniques.

Improved Methods for Image Registration

The results demonstrate an integrated system for intermodality image registration, which is important because the procedure can be performed by technicians with no anatomic knowledge and reduces the required time from hours to about 15 min on a modern computer workstation.

MRI‐PET Registration with Automated Algorithm

Modifications to this method that allow for cross-modality registration of MRI and PET brain images obtained from a single subject are described and validated quantitatively using data from patients with stereotaxic fiducial markers rigidly fixed in the skull.

Rapid Automated Algorithm for Aligning and Reslicing PET Images

A computer algorithm for the three-dimensional alignment of PET images is described that relies on anatomic information in the images rather than on external fiducial markers and can be applied retrospectively, during acquisition, to reposition the scanner gantry and bed to match an earlier study.

Multiscale minimization of global energy functions in some visual recovery problems

A new comprehensive approach to minimize global energy functions using a multiscale relaxation algorithm that appears to be far less sensitive to local minima than standard relaxation algorithms is investigated.

Automatic registration of CT and MR brain images using correlation of geometrical features

An automated approach to register CT and MR brain images that achieves an accurate match even if the scanned volumes to be matched do not completely overlap, or if some of the features in the images are not similar.

MINPRAN: A New Robust Estimator for Computer Vision

  • C. Stewart
  • Computer Science
    IEEE Trans. Pattern Anal. Mach. Intell.
  • 1995
Analytically, it is demonstrated that MINPRAN distinguished good fits to random data andMINPRAN finds accurate fits and nearly the correct number of inliers, regardless of the percentage of true inLiers.