Publications
Detailed Information
Development of an Automatic Classification System for Differentiation of Obstructive Lung Disease using HRCT
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Namkug | - |
dc.contributor.author | Seo, Joon Beom | - |
dc.contributor.author | Lee, Youngjoo | - |
dc.contributor.author | Lee, June Goo | - |
dc.contributor.author | Kang, Suk-Ho | - |
dc.contributor.author | Kim, Song Soo | - |
dc.date.accessioned | 2012-03-05T02:29:40Z | - |
dc.date.available | 2012-03-05T02:29:40Z | - |
dc.date.issued | 2009-04-01 | - |
dc.identifier.citation | JOURNAL OF DIGITAL IMAGING; Vol.22 2; 136-148 | - |
dc.identifier.issn | 0897-1889 | - |
dc.identifier.uri | https://hdl.handle.net/10371/75323 | - |
dc.description.abstract | The motivation is to introduce new shape features and optimize the classifier to improve performance of differentiating obstructive lung diseases, based on high-resolution 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 x 16, 32 x 32, and 64 x 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 x 16, 32 x 32, 64 x 64 pixels, respectively; t test, P < 0.01). 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 x 64 pixels; t test, P < 0.01). 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. | - |
dc.language.iso | en | - |
dc.publisher | SPRINGER | - |
dc.subject | Bayesian classifier | - |
dc.subject | classifier optimization | - |
dc.subject | emphysema | - |
dc.subject | obstructive lung disease | - |
dc.subject | support vector machine | - |
dc.subject | texture analysis | - |
dc.subject | shape analysis | - |
dc.subject | machine learning | - |
dc.title | Development of an Automatic Classification System for Differentiation of Obstructive Lung Disease using HRCT | - |
dc.type | Article | - |
dc.contributor.AlternativeAuthor | 김남국 | - |
dc.contributor.AlternativeAuthor | 서준범 | - |
dc.contributor.AlternativeAuthor | 이영주 | - |
dc.contributor.AlternativeAuthor | 이준구 | - |
dc.contributor.AlternativeAuthor | 강석호 | - |
dc.contributor.AlternativeAuthor | 김송수 | - |
dc.identifier.doi | 10.1007/s10278-008-9147-7 | - |
dc.citation.journaltitle | JOURNAL OF DIGITAL IMAGING | - |
dc.description.citedreference | Xu Y, 2006, ACAD RADIOL, V13, P969, DOI 10.1016/j.acra.2006.04.017 | - |
dc.description.citedreference | VAPNIK VN, 2006, NATURE STAT LEARNING | - |
dc.description.citedreference | HANDRICK S, 2006, P SPIE MED IM C, V6144, P1476 | - |
dc.description.citedreference | Iwano S, 2005, COMPUT MED IMAG GRAP, V29, P565, DOI 10.1016/j.compmedimag.2005.04.009 | - |
dc.description.citedreference | Wei LY, 2005, IEEE T MED IMAGING, V24, P371, DOI 10.1109/TMI.2004.842457 | - |
dc.description.citedreference | Chabat F, 2003, RADIOLOGY, V228, P871, DOI 10.1148/radiol.2283020505 | - |
dc.description.citedreference | Chan KL, 2002, IEEE T BIO-MED ENG, V49, P963, DOI 10.1109/TBME.2002.802012 | - |
dc.description.citedreference | Copley SJ, 2002, RADIOLOGY, V223, P812, DOI 10.1148/radiol.2233010760 | - |
dc.description.citedreference | GONZALEZ RC, 2002, DIGITAL IMAGE PROCES, P532 | - |
dc.description.citedreference | Ding CHQ, 2001, BIOINFORMATICS, V17, P349 | - |
dc.description.citedreference | Furey TS, 2000, BIOINFORMATICS, V16, P906 | - |
dc.description.citedreference | Zien A, 2000, BIOINFORMATICS, V16, P799 | - |
dc.description.citedreference | Rangayyan RM, 2000, MED BIOL ENG COMPUT, V38, P487 | - |
dc.description.citedreference | JOACHIMS T, 1999, ADV KERNEL METHODS S | - |
dc.description.citedreference | Amaldi E, 1998, THEOR COMPUT SCI, V209, P237 | - |
dc.description.citedreference | Dumais S, 1998, IEEE INTELL SYST APP, V13, P21 | - |
dc.description.citedreference | BURGES CJC, 1998, DATA MIN KNOWL DISC, V2, P2 | - |
dc.description.citedreference | Friedman N, 1997, MACH LEARN, V29, P131 | - |
dc.description.citedreference | MITCHELL TM, 1997, MACHINE LEARNING | - |
dc.description.citedreference | BURGES CJC, 1997, IMPROVING ACCURACY S | - |
dc.description.citedreference | SCHURMANN J, 1996, PATTERN CLASSIFICATI | - |
dc.description.citedreference | BOSER B, 1992, P 5 ANN WORKSH COMP, V5, P144 | - |
dc.description.citedreference | YAMAGISHI M, 1991, NIPPON IGAKU HOSHASE, V51, P203 | - |
dc.description.citedreference | KITTLER J, 1978, SIJTHOFF NOORDHOFF A, P41 | - |
dc.description.tc | 5 | - |
dc.identifier.wosid | 000264265000007 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.