Segmentation of Bone structure in sinus CT images using self-organizing Maps

The diagnosis of sinus diseases (e.g. malignant disease) requires the segmentation of bone structure surrounding the sinus areas in CT (computer tomography) images. The non-uniformity of bone tissue, ranging from dense cortical bone to textured spongy bone, the irregular shapes of closely packed bon...

Full description

Saved in:
Bibliographic Details
Main Authors: Natsheh, A-R, Ponnapalli, P V S, Anani, N, Benchebra, D, El-kholy, A, Norburn, P
Format: Conference Proceeding
Language:English
Subjects:
Blood vessels
Bone diseases
Bone tissue
Cancellous bone
Cancer
Computed tomography
Image resolution
Image segmentation
Self organizing feature maps
Shape
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The diagnosis of sinus diseases (e.g. malignant disease) requires the segmentation of bone structure surrounding the sinus areas in CT (computer tomography) images. The non-uniformity of bone tissue, ranging from dense cortical bone to textured spongy bone, the irregular shapes of closely packed bones, and the small inter-bone spaces compared to the resolution of a CT image coupled with the presence of blood vessels and the inherent blurring of CT imaging, render the segmentation of a bone a challenging task. In this paper, a novel technique is presented which uses hierarchical self-organizing maps to segment the structure of bone surrounding the sinus regions. The algorithm has been successfully applied to, and tested with various CT images that have different types of disease.
ISSN:1558-2809
2832-4242
DOI:10.1109/IST.2010.5548465