Topology noise removal for curve and surface evolution

Authors:
Chao Chen;Daniel Freedman
Affiliations:
Institute of Science and Technology Austria, Vienna University of Technology, Austria;Hewlett-Packard Laboratories, Israel
Venue:
MCV'10 Proceedings of the 2010 international MICCAI conference on Medical computer vision: recognition techniques and applications in medical imaging
Year:
2010

Citing 11
Cited 1

Geodesic Active Contours

International Journal of Computer Vision
Gradient flows and geometric active contour models

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Stability of Persistence Diagrams

Discrete & Computational Geometry
Topology correction of segmented medical images using a fast marching algorithm

Computer Methods and Programs in Biomedicine
Active Contours Under Topology Control--Genus Preserving Level Sets

International Journal of Computer Vision
Topological Correction of Brain Surface Meshes Using Spherical Harmonics

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
The robustness of level sets

ESA'10 Proceedings of the 18th annual European conference on Algorithms: Part I
A topology preserving level set method for geometric deformable models

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

IEEE Transactions on Image Processing
Global Regularizing Flows With Topology Preservation for Active Contours and Polygons

IEEE Transactions on Image Processing
Self-Repelling Snakes for Topology-Preserving Segmentation Models

IEEE Transactions on Image Processing

The persistence space in multidimensional persistent homology

DGCI'13 Proceedings of the 17th IAPR international conference on Discrete Geometry for Computer Imagery

Quantified Score

Hi-index	0.00

Visualization

Abstract

In cortex surface segmentation, the extracted surface is required to have a particular topology, namely, a two-sphere. We present a new method for removing topology noise of a curve or surface within the level set framework, and thus produce a cortical surface with correct topology. We define a new energy term which quantifies topology noise. We then show how to minimize this term by computing its functional derivative with respect to the level set function. This method differs from existing methods in that it is inherently continuous and not digital; and in the way that our energy directly relates to the topology of the underlying curve or surface, versus existing knot-based measures which are related in a more indirect fashion. The proposed flow is validated empirically.