Computer-based classification of dermoscopy images of melanocytic lesions on acral volar skin

Iyatomi, H., Oka, H., Celebi, M. E., Ogawa, K., Argenziano, G., Soyer, H. P., Koga, H., Saida, T., Ohara, K. and Tanaka, M. (2008) Computer-based classification of dermoscopy images of melanocytic lesions on acral volar skin. Journal of Investigative Dermatology, 128 8: 2049-2054. doi:10.1038/jid.2008.28


Author Iyatomi, H.
Oka, H.
Celebi, M. E.
Ogawa, K.
Argenziano, G.
Soyer, H. P.
Koga, H.
Saida, T.
Ohara, K.
Tanaka, M.
Title Computer-based classification of dermoscopy images of melanocytic lesions on acral volar skin
Journal name Journal of Investigative Dermatology   Check publisher's open access policy
ISSN 0022-202X
Publication date 2008-01-01
Year available 2008
Sub-type Article (original research)
DOI 10.1038/jid.2008.28
Open Access Status Not yet assessed
Volume 128
Issue 8
Start page 2049
End page 2054
Total pages 6
Editor Goldsmith, L.
Place of publication United Kingdom
Publisher Nature Publishing Gourp
Language eng
Subject C1
110304 Dermatology
920117 Skin and Related Disorders
Abstract We describe a fully automated system for the classification of acral volar melanomas. We used a total of 213 acral dermoscopy images (176 nevi and 37 melanomas). Our automatic tumor area extraction algorithm successfully extracted the tumor in 199 cases (169 nevi and 30 melanomas), and we developed a diagnostic classifier using these images. Our linear classifier achieved a sensitivity (SE) of 100%, a specificity (SP) of 95.9%, and an area under the receiver operating characteristic curve (AUC) of 0.993 using a leave-one-out cross-validation strategy (81.1% SE, 92.1% SP; considering 14 unsuccessful extraction cases as false classification). In addition, we developed three pattern detectors for typical dermoscopic structures such as parallel ridge, parallel furrow, and fibrillar patterns. These also achieved good detection accuracy as indicated by their AUC values: 0.985, 0.931, and 0.890, respectively. The features used in the melanoma-nevus classifier and the parallel ridge detector have significant overlap.
Keyword Dermatology
Dermatology
DERMATOLOGY
Q-Index Code C1
Q-Index Status Confirmed Code
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: 2009 Higher Education Research Data Collection
School of Medicine Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 36 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 34 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Fri, 03 Apr 2009, 00:03:35 EST by Nicole Lin on behalf of School of Medicine