R-PLUS: A Riemannian Anisotropic Edge Detection Scheme for Vascular Segmentation

Authors:
Ali Gooya;Takeyoshi Dohi;Ichiro Sakuma;Hongen Liao
Affiliations:
Graduate School of Engineering, the University of Tokyo, The University of Tokyo, Tokyo, 113-8656;Graduate School of Informaiton Science and Technology, The University of Tokyo, Tokyo, 113-8656;Graduate School of Engineering, the University of Tokyo, The University of Tokyo, Tokyo, 113-8656;Graduate School of Engineering, the University of Tokyo, The University of Tokyo, Tokyo, 113-8656 and Translational Systems Biology and Medicine Initiative, The University of Tokyo, Tokyo, 113-865 ...
Venue:
MICCAI '08 Proceedings of the 11th international conference on Medical Image Computing and Computer-Assisted Intervention - Part I
Year:
2008

Citing 7
Cited 1

Coherence-Enhancing Diffusion Filtering

International Journal of Computer Vision
On the Location Error of Curved Edges in Low-Pass Filtered 2-D and 3-D Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Flux Maximizing Geometric Flows

IEEE Transactions on Pattern Analysis and Machine Intelligence
Riemannian Drums, Anisotropic Curve Evolution and Segmentation

SCALE-SPACE '99 Proceedings of the Second International Conference on Scale-Space Theories in Computer Vision
Correction for the Dislocation of Curved Surfaces Caused by the PSF in 2D and 3D CT Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Active contours without edges

IEEE Transactions on Image Processing
Segmentation of thin structures in volumetric medical images

IEEE Transactions on Image Processing

Tubular Structure Segmentation Based on Minimal Path Method and Anisotropic Enhancement

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, detection of edges in oriented fields is addressed. In some applications such as vessel segmentation because of the intrinsic orientation of the structures, edge detection is only demanded in a particular subspace. This is specially usefull when a curve evolution is chosen for segmentation since gradients in parallel to vessel orientation may stop the contour. An anisotropic edge detection scheme is generalized on a Riemannian manifold using the local structure tensor. The method is the generalization of the PLUSoperator proposed in [8] for accurate curved edge detection. Examples are given and the comparison is made with the state-of-the-art flux maximizing flow which indicates that significant improvements in terms of leakage minimization and thiner vessel delineation is achievable using our methodology.