Development of an Automatic Classification System for Differentiation of Obstructive Lung Disease using HRCT

Cited 28 time in webofscience Cited 34 time in scopus
Kim, Namkug; Seo, Joon Beom; Lee, Youngjoo; Lee, June Goo; Kim, Song Soo; Kang, Suk Ho
Issue Date
Springer Verlag
Journal of Digital Imaging 22:136-148, 2009
Bayesian classifierclassifier optimizationemphysemamachine learningobstructive lung diseaseshape analysissupport vector machinetexture analysis
The motivation is to introduce new shape features and
optimize the classifier to improve performance of differentiating
obstructive lung diseases, based on highresolution
computerized tomography (HRCT) images.
Two hundred sixty-five HRCT images from 82 subjects
were selected. On each image, two experienced radiologists
selected regions of interest (ROIs) representing
area of severe centrilobular emphysema, mild centrilobular
emphysema, bronchiolitis obliterans, or normal lung.
Besides 13 textural features, additional 11 shape features
were employed to evaluate the contribution of
shape features. To optimize the system, various ROI size
(16×16, 32×32, and 64×64 pixels) and other classifier
parameters were tested. For automated classification,
the Bayesian classifier and support vector machine (SVM)
were implemented. To assess cross-validation of the
system, a five-folding method was used. In the comparison
of methods employing only the textural features,
adding shape features yielded the significant improvement
of overall sensitivity (7.3%, 6.1%, and 4.1% in the
Bayesian and 9.1%, 7.5%, and 6.4% in the SVM, in the
ROI size 16×16, 32×32, 64×64 pixels, respectively; t
test, PG0.01). After feature selection, most of cluster
shape features were survived ,and the feature selected
set shows better performance of the overall sensitivity
(93.5±1.0% in the SVM in the ROI size 64×64 pixels; t
test, PG0.01). Adding shape features to conventional
texture features is much useful to improve classification
performance of obstructive lung diseases in both Bayesian
and SVM classifiers. In addition, the shape features
contribute more to overall sensitivity in smaller ROI.
0897-1889 (print)
1618-727X (online)
Files in This Item:
There are no files associated with this item.
Appears in Collections:
College of Engineering/Engineering Practice School (공과대학/대학원)Dept. of Industrial Engineering (산업공학과)Journal Papers (저널논문_산업공학과)
  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.