Conference Paper

Point-set registration of tagged HE-3 images using a structurally-based Jensen-Shannon divergence measure within a deterministic annealing framework.

Dept. of Radiol., Pennsylvania Univ., Philadelphia, PA
DOI: 10.1109/ISBI.2008.4541110 Conference: Proceedings of the 2008 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Paris, France, May 14-17, 2008
Source: IEEE Xplore

ABSTRACT Helium-3 tagged magnetic resonance imaging has demonstrated potential for calculating pulmonary deformation from medical imagery. Such measurements are useful for determining the biomechanical properties of the lung. Unfortunately, the relative facility of visually tracking deformation via the high contrast tag lines has not transferred readily to the algorithmic domain of automatically establishing tag-line correspondences. We proffer a solution to this dilemma by translating the problem into a unique point-set registration scenario. Not only does this permit capitalizing on certain spectral aspects of tagged MRI but registration can be performed within a deterministic annealing framework for decreased susceptibility to local minima.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a novel and robust algorithm for the groupwise non-rigid registration of multiple unlabeled point-sets with no bias toward any of the given point-sets. To quantify the divergence between multiple probability distributions each estimated from the given point sets, we develop a novel measure based on their cumulative distribution functions that we dub the CDF-JS divergence. The measure parallels the well known Jensen-Shannon divergence (defined for probability density functions) but is more regular than the JS divergence since its definition is based on CDFs as opposed to density functions. As a consequence, CDF-JS is more immune to noise and statistically more robust than the JS.We derive the analytic gradient of the CDF-JS divergence with respect to the non-rigid registration parameters for use in the numerical optimization of the groupwise registration leading a computationally efficient and accurate algorithm. The CDF-JS is symmetric and has no bias toward any of the given point-sets, since there is NO fixed reference data set. Instead, the groupwise registration takes place between the input data sets and an evolving target dubbed the pooled model. This target evolves to a fully registered pooled data set when the CDF-JS defined over this pooled data is minimized. Our algorithm is especially useful for creating atlases of various shapes (represented as point distribution models) as well as for simultaneously registering 3D range data sets without establishing any correspondence. We present experimental results on non-rigid registration of 2D/3D real point set data.
    Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 07/2006; 1:1283-1288.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Recent innovations in hyperpolarized helium-3 magnetic resonance imaging (MRI) include the employment of MR tagging techniques for assessment of pulmonary deformation. Historically, such tagging methods have been successfully applied to cardiac research inspiring the development of computational techniques for the quantitative analysis of myocardial deformation. We present related research which concerns the calculation of kinematic quantities, such as displacement and strain, in the lung. Utilizing the high contrast tag lines as landmarks in the images and a recently developed fast n-D B-spline approximation algorithm, we fit a parametric object to the sparse tag line data to smoothly interpolate the underlying deformation field and, subsequently, extract lung kinematic information. We present results from a single human volunteer
    Proceedings of the 2007 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Washington, DC, USA, April 12-16, 2007; 01/2007
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present a novel method for automatically extracting the tagging sheets in tagged cardiac MR images, and tracking their displacement during the heart cycle, using a tunable 3D Gabor filter bank. Tagged MRI is a non-invasive technique for the study of myocardial deformation. We design the 3D Gabor filter bank based on the geometric characteristics of the tagging sheets. The tunable parameters of the Gabor filter bank are used to adapt to the myocardium deformation. The whole 3D image dataset is convolved with each Gabor filter in the filter bank, in the Fourier domain. Then we impose a set of deformable meshes onto the extracted tagging sheets and track them over time. Dynamic estimation of the filter parameters and the mesh internal smoothness are used to help the tracking. Some very encouraging results are shown.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 02/2006; 1:711-4.

Full-text (5 Sources)

Available from
Jun 3, 2014