DocumentCode
3083252
Title
An Internet-based melanoma screening system with acral volar lesion support
Author
Iyatomi, Hitoshi ; Celebi, M. ; Oka, Hiroshi ; Tanaka, Masaru
Author_Institution
Faculty of Engineering, Hosei University, 3-7-2 Kajinocho, Koganei, 184-8522, Tokyo, Japan
fYear
2008
fDate
20-25 Aug. 2008
Firstpage
5156
Lastpage
5159
Abstract
In this paper, we present an Internet-based melanoma screening system that newly supports acral volar lesions. A half of Asian melanomas are from these areas and they show completely different appearance from other lesions. Our screening system is accessible from all over the world and diagnoses dermoscopy images within 3–5 sec based on a neural network classifier for non-acral lesions or newly integrated linear classifier for acral volar lesions. Our system achieves a sensitivity of 85.9% and a specificity of 86.0% on a set of 1258 non-acral dermoscopy images and a sensitivity of 93.3% and a specificity of 91.1% on a set of 199 acral volar dermoscopy images using a leave-one-out cross-validation.
Keywords
Artificial neural networks; Biomedical imaging; Data mining; Hospitals; Internet; Lesions; Malignant tumors; Medical diagnostic imaging; Neural networks; Skin neoplasms; Algorithms; Artificial Intelligence; Dermoscopy; Hand; Humans; Image Enhancement; Image Interpretation, Computer-Assisted; Internet; Mass Screening; Melanoma; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Skin Neoplasms; User-Computer Interface;
fLanguage
English
Publisher
ieee
Conference_Titel
Engineering in Medicine and Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE
Conference_Location
Vancouver, BC
ISSN
1557-170X
Print_ISBN
978-1-4244-1814-5
Electronic_ISBN
1557-170X
Type
conf
DOI
10.1109/IEMBS.2008.4650375
Filename
4650375
Link To Document