1. Computer-Based Classification of Dermoscopy Images of Melanocytic Lesions on Acral Volar Skin
- Author
-
Hitoshi Iyatomi, Hiroshi Oka, M. Emre Celebi, Toshiaki Saida, Koichi Ogawa, Hiroshi Koga, Masaru Tanaka, Kuniaki Ohara, H. Peter Soyer, Giuseppe Argenziano, Iyatomi, H, Oka, H, Celebi, Me, Ogawa, K, Argenziano, Giuseppe, Soyer, Hp, Koga, H, Saida, T, Ohara, K, and Tanaka, M.
- Subjects
Adult ,Male ,medicine.medical_specialty ,Skin Neoplasms ,Adolescent ,Extraction algorithm ,Linear classifier ,Dermoscopy ,Dermatology ,Sensitivity and Specificity ,Biochemistry ,medicine ,Humans ,Diagnosis, Computer-Assisted ,Child ,Melanoma diagnosis ,Melanoma ,Nevus ,Molecular Biology ,Dermatoscopy ,medicine.diagnostic_test ,Receiver operating characteristic ,business.industry ,Computer based ,Pattern recognition ,Cell Biology ,Middle Aged ,Fully automated ,Melanocytes ,Female ,Artificial intelligence ,business ,Classifier (UML) - 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.
- Published
- 2008
- Full Text
- View/download PDF