A computer-aided system for classifying computed tomographic (CT) lung images using artificial neural network

Author

Mohammed, Hanan ; Abou-Chadi, Fatma ; Obayya, Marwa

fYear

2011

fDate

27-28 Dec. 2011

Firstpage

93

Lastpage

96

Abstract

In this paper, computed tomographic (CT) images were investigated to develop a computer-aided system to discriminate different lung abnormalities. These were done by analyzing Data recorded for healthy subjects and patients suffering from lung asthma and emphysema diseases were considered. The techniques for utilized feature extraction included statistical, intensity, and morphological features as well as features derived from texture analysis, Fourier-based features and wavelet-based features. An artificial neural network (ANN) classifier was utilized and the results have shown that using wavelet domain features gives the highest rates to recognize lung abnormalities. Classification rate reaches about 98%.

Keywords

Fourier transforms; computerised tomography; data analysis; diseases; feature extraction; image classification; image texture; lung; medical image processing; neural nets; object recognition; statistical analysis; wavelet transforms; Fourier-based features; artificial neural network classifier; computed tomographic lung image classification; computer-aided system; data analysis; emphysema diseases; feature extraction; healthy subjects; intensity features; lung abnormalities recognition; lung asthma; morphological features; statistical features; texture analysis; wavelet-based features; Biomedical imaging; Computational modeling; Databases; Feature extraction; Image segmentation; Lungs; Presses; ANN; CAD; CT; DWT; FFT; PCA;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Engineering Conference (ICENCO), 2011 Seventh International

Conference_Location

Giza

Print_ISBN

978-1-4673-0730-7

Type

conf

DOI

10.1109/ICENCO.2011.6153938

Filename

6153938