Pulmonary CT image classification using evolutionary programming

Author

Madsen, M.T. ; Uppaluri, R. ; Hoffman, E.A. ; McLennan, G.

Author_Institution

Dept. of Radiol., Iowa Univ., Iowa City, IA, USA

Volume

2

fYear

1997

fDate

9-15 Nov 1997

Firstpage

1179

Abstract

The authors report on the use of evolutionary programming for classifying lung CT images. Evolutionary programming uses a genetic algorithm to generate a complete, compilable program that optimizes a solution to set of training data, In this case, the training set consisted of 17 features derived from multiple lung CT images along with an indicator of the target area from which the features originated. The image features included 5 parameters based on histogram analysis, 11 parameters based on run length and co-occurrence matrix measures, and the fractal dimension. Evolutionary programming produced solutions that compared favorably with more complicated and sophisticated Bayesian classifiers. The results of this study suggest that evolutionary programming is a powerful tool for developing classification algorithms

Keywords

computerised tomography; fractals; genetic algorithms; image classification; lung; medical image processing; co-occurrence matrix measures; complete compilable program; evolutionary programming; fractal dimension; histogram analysis; image features; medical diagnostic imaging; pulmonary CT image classification; run length; sophisticated Bayesian classifiers; training data set data solution optimization; Computed tomography; Fractals; Genetic algorithms; Genetic programming; Histograms; Image analysis; Image classification; Length measurement; Lungs; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Nuclear Science Symposium, 1997. IEEE

Conference_Location

Albuquerque, NM

ISSN

1082-3654

Print_ISBN

0-7803-4258-5

Type

conf

DOI

10.1109/NSSMIC.1997.670520

Filename

670520