Jan 24, 2009

Automated 2-D cephalometric analysis of X-ray by image registration approach based on least square approximator

Conference Proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society
I El-FeghM Ahmadi

Abstract

This paper presents a new approach to cephalometric x-ray landmark localization. This approach is based on extracting features from face profile of the lateral skull x-ray. The extracted side profile is then segmented based on knowledge of known local facial structures. Once the face profile is properly segmented, nine perceptually significant landmarks (fiducial points) on the face are registered based on a local maximum curvature computation. These fiducial points are used for point-by-point correspondence to find the transformation coefficients of the control points between two images of a scene. Next, we use the obtained coefficients to find the locations of other landmarks on the target image by mapping the landmarks of the reference image. The algorithm was tested on more than 80 x-ray images to locate 20 landmarks. It was possible to locate the landmarks with accuracy of +/-2mm on more 90% of the landmarks.

  • References
  • Citations3

References

  • We're still populating references for this paper, please check back later.

Mentioned in this Paper

Establishment and Maintenance of Localization
In Silico
X-ray of Skull
Plain X-ray
Calvaria
Rietveld Refinement
Knowledge Representation (Computer)
Craniometry
Radiographic Imaging Procedure
Information Extraction

Related Feeds

Brain-Computer Interface

A brain-computer interface, also known as a brain-machine interface, is a bi-directional communication pathway between an external device and a wired brain. Here is the latest research on this topic.

Related Papers

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
Z Yang, F S Cohen
Proceedings of the ... International Symposium on Image and Signal Processing and Analysis
Fengqing ZhuEdward J Delp
© 2020 Meta ULC. All rights reserved