Automatic Hip Bone Segmentation Using Non-Rigid Registration

Authors:
Johanna Pettersson;Hans Knutsson;Magnus Borga
Affiliations:
Linkoping University, Sweden;Linkoping University, Sweden;Linkoping University, Sweden
Venue:
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Year:
2006

Citing 0
Cited 3

Statistical Regularization of Deformation Fields for Atlas-Based Segmentation of Bone Scintigraphy Images

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part I
Cortical bone classification by local context analysis

MIRAGE'07 Proceedings of the 3rd international conference on Computer vision/computer graphics collaboration techniques
Automatic segmentation of the pelvic bones from CT data based on a statistical shape model

EG VCBM'08 Proceedings of the First Eurographics conference on Visual Computing for Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a method for automatic segmentation of bone from volumetric computed tomography (CT) data. Due to osteoporosis, which degenerates the bone density and hence decreases the intensity of the bone in the CT dataset, it is not possible to use conventional thresholding techniques to handle the segmentation. Furthermore we want to use prior knowledge about shapes and relations of the bones in the area of interest to be able to e.g. separate adjoining bones from each other. The method we suggest is the morphon algorithm [4]. This is a non-rigid registration technique where an 2D or 3D image is iteratively deformed to match the corresponding structure in a target image. The method uses difference in local quadrature phase and certainty measures to estimate the deformations.