Unsupervised segmentation of HRCT lung images using FDK clustering

Author

Singh, Pramod K.

Author_Institution

Sch. of Comput. Sci. & Eng., New South Wales Univ., Sydney, NSW, Australia

fYear

2004

fDate

1-3 Dec. 2004

Lastpage

39543

Abstract

Image segmentation is a prerequisite process for image content understanding in HRCT lung images for the development of a computer aided diagnosis (CAD) system. An unsupervised segmentation method is proposed in this paper. Initially, lung regions in HRCT lung images are separated and then feature vectors using the deviation in local variance of DCT coefficients are determined for each pixel of lung regions. A reduced set of feature vector is used for unsupervised classification using a rule based Fisher discriminant K-means (FDK) clustering algorithm.

Keywords

computerised tomography; discrete cosine transforms; image classification; image segmentation; lung; medical image processing; pattern clustering; statistical analysis; Fisher discriminant K-means clustering algorithm; computer aided diagnosis; discrete cosine transform; high resolution computed tomography lung images; image content understanding; unsupervised image classification; unsupervised image segmentation; Clustering algorithms; Discrete cosine transforms; Feature extraction; Filter bank; Image segmentation; Lungs; Nonlinear filters; Pixel; Robustness; Signal processing algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Circuits and Systems, 2004 IEEE International Workshop on

Print_ISBN

0-7803-8665-5

Type

conf

DOI

10.1109/BIOCAS.2004.1454138

Filename

1454138