Missouri S&T Scholar's Mine Research RepositoryMissouri S&T Research
print 
Title: A methodological approach to the classification of dermoscopy images
Author (s): Celebi, M. Emre
Kingravi, Hassan A.
Uddin, Bakhtiyar
Iyatomi, Hitoshi
Aslandogan, Y. Alp
Stoecker, William V.
Moss, Randy Hays
Department/Lab Affiliations: Electrical and Computer Engineering
Image Processing Laboratory
Keywords: dermoscopy
model selection
support vector machine
Subject Terms: Machine learning.
Skin -- Cancer.
Issue Date: 2007
Publisher: Elsevier
Citation: Celebi, M.Emre, Hassan A. Kingravi, Bakhtiyar Uddin, Hitoshi Iyatomi, Y. Alp Aslandogan, William V. Stoecker, Randy H. Moss, "A Methodological Approach to the Classification of Dermoscopy Images", Computerized Medical Imaging and Graphics, Vol. 31, no. 6, pp. 362-373, 2007.
Abstract: In this paper a methodological approach to the classification of pigmented skin lesions in dermoscopy images is presented. First, automatic border detection is performed to separate the lesion from the background skin. Shape features are then extracted from this border. For the extraction of color and texture related features, the image is divided into various clinically significant regions using the Euclidean distance transform. This feature data is fed into an optimization framework, which ranks the features using various feature selection algorithms and determines the optimal feature subset size according to the area under the ROC curve measure obtained from support vector machine classification. The issue of class imbalance is addressed using various sampling strategies, and the classifier generalization error is estimated using Monte Carlo cross validation. Experiments on a set of 564 images yielded a specificity of 92.34% and a sensitivity of 93.33%.
Type: Article - Journal
text
In Title: Computerized Medical Imaging and Graphics
Copyright Notice: Pre-print: author can archive with restrictions;Restriction: This does not include Cell Press; Post-print: author can archive;
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
FULL COPYRIGHT INFORMATION:
http://www.elsevier.com/wps/find/authorsview.authors/authorsrights
Publisher URL:
http://www.sciencedirect.com/science/article/B6T5K-4NBRYFM-1/2/447dad3cee5824122d2a3dbc36698791
Link to this page:
http://scholarsmine.mst.edu/post_prints/AMethodologicalApproachToTheClassificationOfDe_09007dcc8052af30.html



titleA methodological approach to the classification of dermoscopy images
contributor.authorCelebi, M. Emre
contributor.authorKingravi, Hassan A.
contributor.authorUddin, Bakhtiyar
contributor.authorIyatomi, Hitoshi
contributor.authorAslandogan, Y. Alp
contributor.authorStoecker, William V.
contributor.authorMoss, Randy Hays
contributor.deptlabElectrical and Computer Engineering
contributor.deptlabImage Processing Laboratory
contributor.sponsorEDRA Interactive Atlas of Dermoscopy
contributor.sponsorJames A. Schlipmann Melanoma Cancer Foundation
contributor.sponsorNational Institute of Health
contributor.sponsorNational Science Foundation
contributor.sponsorTexas Workforce Commission
subjectdermoscopy
subjectmodel selection
subjectsupport vector machine
subject.LCCMelanoma.
subject.LCSHMachine learning.
subject.LCSHSkin -- Cancer.
date.issued2007
publisherElsevier
identifier.citationCelebi, M.Emre, Hassan A. Kingravi, Bakhtiyar Uddin, Hitoshi Iyatomi, Y. Alp Aslandogan, William V. Stoecker, Randy H. Moss, "A Methodological Approach to the Classification of Dermoscopy Images", Computerized Medical Imaging and Graphics, Vol. 31, no. 6, pp. 362-373, 2007.
identifier.pub.URI
http://www.sciencedirect.com/science/article/B6T5K-4NBRYFM-1/2/447dad3cee5824122d2a3dbc36698791
description.abstractIn this paper a methodological approach to the classification of pigmented skin lesions in dermoscopy images is presented. First, automatic border detection is performed to separate the lesion from the background skin. Shape features are then extracted from this border. For the extraction of color and texture related features, the image is divided into various clinically significant regions using the Euclidean distance transform. This feature data is fed into an optimization framework, which ranks the features using various feature selection algorithms and determines the optimal feature subset size according to the area under the ROC curve measure obtained from support vector machine classification. The issue of class imbalance is addressed using various sampling strategies, and the classifier generalization error is estimated using Monte Carlo cross validation. Experiments on a set of 564 images yielded a specificity of 92.34% and a sensitivity of 93.33%.
typeArticle - Journal
type.DCMITypetext
type.statusPostprint
rightsPre-print: author can archive with restrictions;Restriction: This does not include Cell Press; Post-print: author can archive;
rightsThis material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
rights.URI
http://www.elsevier.com/wps/find/authorsview.authors/authorsrights
relation.isPartOfComputerized Medical Imaging and Graphics
date.available2008-07-07T19:47:05Z
identifier.persist.URI
http://scholarsmine.mst.edu/post_prints/AMethodologicalApproachToTheClassificationOfDe_09007dcc8052af30.html