Recent improvements in tensor scale computation and its applications to medical imaging

@inproceedings{Xu2009RecentII,
  title={Recent improvements in tensor scale computation and its applications to medical imaging},
  author={Ziyue Xu and Milan Sonka and Punam K. Saha},
  booktitle={Medical Imaging},
  year={2009}
}
Tensor scale (t-scale) is a local morphometric parameter describing local structure shape, orientation and scale. At any image location, t-scale is the parametric representation of the largest ellipse (an ellipsoid in 3D) centered at that location and contained in the same homogeneous region. Recently, we have improved the t-scale computation algorithm by: (1) optimizing digital representations for LoG and DoG kernels for edge detection and (2) ellipse fitting by using minimization of both… 

Micro-computed tomography image-based evaluation of 3D anisotropy degree of polymer scaffolds

TLDR
This methodology results in the development of non-destructive tools to engineer biomimetic scaffolds, incorporating anisotropy as a fundamental property to be mimicked from the original tissue and permitting its assessment by means of μCT image analysis.

References

SHOWING 1-10 OF 53 REFERENCES

Novel theory and methods for tensor scale: a local morphometric parameter

  • P. Saha
  • Mathematics
    SPIE Medical Imaging
  • 2003
TLDR
Tensor scale is a new idea of local scale, called tensor scale, which, at any image location, is the parametric representation of the largest ellipse or ellipsoid centered at that location that is contained in the same homogeneous region.

Tensor scale-based image registration

TLDR
Tensor scale - a recently developed local morphometric parameter - in rigid image registration is introduced and it is shown that it may allow the use of local Gestalts formed by the intensity patterns over the image instead of simply considering intensities as isolated events at the pixel level.

Curvature of n-dimensional space curves in grey-value images

TLDR
An extensive evaluation shows that the curvature estimation is unbiased even in the presence of noise, independent of the scale of the object and furthermore the relative error stays small.

Tensor scale-based fuzzy connectedness image segmentation

TLDR
The notion of "tensor scale" - a recently developed local morphometric parameter - in affinity definition is introduced and an effective utilization of local size, orientation, and ansiotropy in a unified manner is studied.

Nonrigid registration using free-form deformations: application to breast MR images

TLDR
The results clearly indicate that the proposed nonrigid registration algorithm is much better able to recover the motion and deformation of the breast than rigid or affine registration algorithms.

Task-specific comparison of 3D image registration methods

TLDR
Two pairs of rigid-body registration algorithms were implemented, using cross- correlation and mutual information, operating on original gray-level images and on the intermediate images resulting from a new scale-based method.

Multiresolution elastic matching

Landmark-based elastic registration using approximating thin-plate splines

TLDR
The authors consider elastic image registration based on a set of corresponding anatomical point landmarks and approximating thin-plate splines and uses a semi-automatic approach based on three-dimensional (3-D) differential operators to localize landmarks.

Detecting Contour Saliences using Tensor Scale

TLDR
It is shown that the proposed method can be not only faster and more robust in the detection of salience points than the CS method, but also more effective as a shape descriptor.
...