An improved Internet-based melanoma screening system with dermatologist-like tumor area extraction algorithm

Hitoshi Iyatomi, Hiroshi Oka, M. Emre Celebi, Masahiro Hashimoto, Masafumi Hagiwara, Masaru Tanaka, Koichi Ogawa

Research output: Contribution to journalArticle

161 Citations (Scopus)

Abstract

In this paper, we present an Internet-based melanoma screening system. Our web server is accessible from all over the world and performs the following procedures when a remote user uploads a dermoscopy image: separates the tumor area from the surrounding skin using highly accurate dermatologist-like tumor area extraction algorithm, calculates a total of 428 features for the characterization of the tumor, classifies the tumor as melanoma or nevus using a neural network classifier, and presents the diagnosis. Our system achieves a sensitivity of 85.9% and a specificity of 86.0% on a set of 1258 dermoscopy images using cross-validation.

Original languageEnglish
Pages (from-to)566-579
Number of pages14
JournalComputerized Medical Imaging and Graphics
Volume32
Issue number7
DOIs
Publication statusPublished - 2008 Oct

Fingerprint

Internet
Tumors
Melanoma
Screening
Dermoscopy
Neoplasms
Nevi and Melanomas
Skin
Computer systems
Classifiers
Servers
Neural networks
Dermatologists

Keywords

  • Computer-aided diagnosis (CAD)
  • Dermoscopy
  • Melanoma
  • Neural network
  • Tumor extraction

ASJC Scopus subject areas

  • Computer Science Applications
  • Radiology Nuclear Medicine and imaging

Cite this

An improved Internet-based melanoma screening system with dermatologist-like tumor area extraction algorithm. / Iyatomi, Hitoshi; Oka, Hiroshi; Celebi, M. Emre; Hashimoto, Masahiro; Hagiwara, Masafumi; Tanaka, Masaru; Ogawa, Koichi.

In: Computerized Medical Imaging and Graphics, Vol. 32, No. 7, 10.2008, p. 566-579.

Research output: Contribution to journalArticle

Iyatomi, Hitoshi ; Oka, Hiroshi ; Celebi, M. Emre ; Hashimoto, Masahiro ; Hagiwara, Masafumi ; Tanaka, Masaru ; Ogawa, Koichi. / An improved Internet-based melanoma screening system with dermatologist-like tumor area extraction algorithm. In: Computerized Medical Imaging and Graphics. 2008 ; Vol. 32, No. 7. pp. 566-579.
@article{b1dbc8f2e1b14fc986243aea3472080f,
title = "An improved Internet-based melanoma screening system with dermatologist-like tumor area extraction algorithm",
abstract = "In this paper, we present an Internet-based melanoma screening system. Our web server is accessible from all over the world and performs the following procedures when a remote user uploads a dermoscopy image: separates the tumor area from the surrounding skin using highly accurate dermatologist-like tumor area extraction algorithm, calculates a total of 428 features for the characterization of the tumor, classifies the tumor as melanoma or nevus using a neural network classifier, and presents the diagnosis. Our system achieves a sensitivity of 85.9{\%} and a specificity of 86.0{\%} on a set of 1258 dermoscopy images using cross-validation.",
keywords = "Computer-aided diagnosis (CAD), Dermoscopy, Melanoma, Neural network, Tumor extraction",
author = "Hitoshi Iyatomi and Hiroshi Oka and Celebi, {M. Emre} and Masahiro Hashimoto and Masafumi Hagiwara and Masaru Tanaka and Koichi Ogawa",
year = "2008",
month = "10",
doi = "10.1016/j.compmedimag.2008.06.005",
language = "English",
volume = "32",
pages = "566--579",
journal = "Computerized Medical Imaging and Graphics",
issn = "0895-6111",
publisher = "Elsevier Limited",
number = "7",

}

TY - JOUR

T1 - An improved Internet-based melanoma screening system with dermatologist-like tumor area extraction algorithm

AU - Iyatomi, Hitoshi

AU - Oka, Hiroshi

AU - Celebi, M. Emre

AU - Hashimoto, Masahiro

AU - Hagiwara, Masafumi

AU - Tanaka, Masaru

AU - Ogawa, Koichi

PY - 2008/10

Y1 - 2008/10

N2 - In this paper, we present an Internet-based melanoma screening system. Our web server is accessible from all over the world and performs the following procedures when a remote user uploads a dermoscopy image: separates the tumor area from the surrounding skin using highly accurate dermatologist-like tumor area extraction algorithm, calculates a total of 428 features for the characterization of the tumor, classifies the tumor as melanoma or nevus using a neural network classifier, and presents the diagnosis. Our system achieves a sensitivity of 85.9% and a specificity of 86.0% on a set of 1258 dermoscopy images using cross-validation.

AB - In this paper, we present an Internet-based melanoma screening system. Our web server is accessible from all over the world and performs the following procedures when a remote user uploads a dermoscopy image: separates the tumor area from the surrounding skin using highly accurate dermatologist-like tumor area extraction algorithm, calculates a total of 428 features for the characterization of the tumor, classifies the tumor as melanoma or nevus using a neural network classifier, and presents the diagnosis. Our system achieves a sensitivity of 85.9% and a specificity of 86.0% on a set of 1258 dermoscopy images using cross-validation.

KW - Computer-aided diagnosis (CAD)

KW - Dermoscopy

KW - Melanoma

KW - Neural network

KW - Tumor extraction

UR - http://www.scopus.com/inward/record.url?scp=49949112001&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=49949112001&partnerID=8YFLogxK

U2 - 10.1016/j.compmedimag.2008.06.005

DO - 10.1016/j.compmedimag.2008.06.005

M3 - Article

VL - 32

SP - 566

EP - 579

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

SN - 0895-6111

IS - 7

ER -