File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Skin lesion classification using relative color features

TitleSkin lesion classification using relative color features
Authors
KeywordsTradenames
Issue Date2008
PublisherBlackwell Munksgaard. The Journal's web site is located at http://www.blackwellpublishing.com/journals/SRT
Citation
Skin Research and Technology, 2008, v. 14 n. 1, p. 53-64 How to Cite?
AbstractBackground/purpose: Clinically, it is difficult to differentiate the early stage of malignant melanoma and certain benign skin lesions due to similarity in appearance. Our research uses image analysis of clinical skin images and relative color-based pattern recognition techniques to enhance the images and improve differentiation of these lesions. Methods: First, the relative color images were created from digitized photographic images. Then, they were segmented into objects and morphologically filtered. Next, the relative color features were extracted from the objects to form two different feature spaces; a lesion feature space and an object feature space. The two feature spaces serve as two data models to be analyzed to determine the best features. Finally, we used a statistical analysis model of relative color features, which better classifies the various types of skin lesions. Results/conclusions: The best features found for differentiation of melanoma and benign skin lesions from this study are area, mean in the red and blue bands, standard deviation in the red and green bands, skewness in the green band, and entropy in the red band. With the relative color feature algorithm developed, the best results were obtained with a multi-layer perceptron neural network model. This showed an overall classification success of 79%, with 70% of the benign lesions successfully classified, and 86% of malignant melanoma successfully classified. © 2007 Blackwell Munksgaard.
Persistent Identifierhttp://hdl.handle.net/10722/91293
ISSN
2015 Impact Factor: 1.776
2015 SCImago Journal Rankings: 0.829
PubMed Central ID
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorCheng, Yen_HK
dc.contributor.authorSwamisai, Ren_HK
dc.contributor.authorUmbaugh, SEen_HK
dc.contributor.authorMoss, RHen_HK
dc.contributor.authorStoecker, WVen_HK
dc.contributor.authorTeegala, Sen_HK
dc.contributor.authorSrinivasan, SKen_HK
dc.date.accessioned2010-09-17T10:16:20Z-
dc.date.available2010-09-17T10:16:20Z-
dc.date.issued2008en_HK
dc.identifier.citationSkin Research and Technology, 2008, v. 14 n. 1, p. 53-64en_HK
dc.identifier.issn0909-752Xen_HK
dc.identifier.urihttp://hdl.handle.net/10722/91293-
dc.description.abstractBackground/purpose: Clinically, it is difficult to differentiate the early stage of malignant melanoma and certain benign skin lesions due to similarity in appearance. Our research uses image analysis of clinical skin images and relative color-based pattern recognition techniques to enhance the images and improve differentiation of these lesions. Methods: First, the relative color images were created from digitized photographic images. Then, they were segmented into objects and morphologically filtered. Next, the relative color features were extracted from the objects to form two different feature spaces; a lesion feature space and an object feature space. The two feature spaces serve as two data models to be analyzed to determine the best features. Finally, we used a statistical analysis model of relative color features, which better classifies the various types of skin lesions. Results/conclusions: The best features found for differentiation of melanoma and benign skin lesions from this study are area, mean in the red and blue bands, standard deviation in the red and green bands, skewness in the green band, and entropy in the red band. With the relative color feature algorithm developed, the best results were obtained with a multi-layer perceptron neural network model. This showed an overall classification success of 79%, with 70% of the benign lesions successfully classified, and 86% of malignant melanoma successfully classified. © 2007 Blackwell Munksgaard.en_HK
dc.languageengen_HK
dc.publisherBlackwell Munksgaard. The Journal's web site is located at http://www.blackwellpublishing.com/journals/SRTen_HK
dc.relation.ispartofSkin Research and Technologyen_HK
dc.subjectTradenamesen_HK
dc.titleSkin lesion classification using relative color featuresen_HK
dc.typeArticleen_HK
dc.identifier.emailCheng, Y:yuecheng@hku.hken_HK
dc.identifier.authorityCheng, Y=rp1320en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1111/j.1600-0846.2007.00261.xen_HK
dc.identifier.pmid18211602-
dc.identifier.pmcidPMC3184884-
dc.identifier.scopuseid_2-s2.0-38349142814en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-38349142814&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume14en_HK
dc.identifier.issue1en_HK
dc.identifier.spage53en_HK
dc.identifier.epage64en_HK
dc.identifier.eissn1600-0846-
dc.identifier.isiWOS:000252497100008-
dc.identifier.citeulike2272192-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats