Related Experiment Video
Updated: Jun 26, 2026

Screening for Melanoma Modifiers using a Zebrafish Autochthonous Tumor Model
Published on: November 13, 2012
An Internet-based melanoma screening system with acral volar lesion support
Hitoshi Iyatomi1, M Celebi, Hiroshi Oka
1Faculty of Engineering, Hosei University, 3-7-2 Kajinocho, Koganei, 184-8522, Tokyo, Japan. iyatomi@hosei.ac.jp
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.
