Diagnotic support system of melanoma based on morphological features

Toshiyuki Tanaka, Reina Yamada, Michiko Tanaka, Kunio Shimizu, Masaru Tanaka

Research output: Contribution to journalArticle

Abstract

At present the diagnosis of melanoma is mainly performed based on the experience of each doctor. They need some objective measure for diagnosis of melanoma and nevus. But there are few researches on index for the diagnosis. This study deals with features of melanoma and nevus for computer diagnosis. First, we extracted the contour of lesions by image processing. One hundred five values of features were computed based on ABCD-rule. Discriminant analysis showed the accuracy of 96.0% (Specificity of 98.3% and the Sensitivity of 90.0%). The results obviously showed the difference between melanoma and nevus.

Original languageEnglish
Pages (from-to)330-337
Number of pages8
JournalIEEJ Transactions on Electronics, Information and Systems
Volume127
Issue number3
DOIs
Publication statusPublished - 2007

Fingerprint

Discriminant analysis
Image processing

Keywords

  • Benign nevus
  • Discriminant analysis
  • Image processing
  • Melanoma

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Diagnotic support system of melanoma based on morphological features. / Tanaka, Toshiyuki; Yamada, Reina; Tanaka, Michiko; Shimizu, Kunio; Tanaka, Masaru.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 127, No. 3, 2007, p. 330-337.

Research output: Contribution to journalArticle

Tanaka, Toshiyuki ; Yamada, Reina ; Tanaka, Michiko ; Shimizu, Kunio ; Tanaka, Masaru. / Diagnotic support system of melanoma based on morphological features. In: IEEJ Transactions on Electronics, Information and Systems. 2007 ; Vol. 127, No. 3. pp. 330-337.
@article{142fdeecea7c4877a46d26a5acb3a2d8,
title = "Diagnotic support system of melanoma based on morphological features",
abstract = "At present the diagnosis of melanoma is mainly performed based on the experience of each doctor. They need some objective measure for diagnosis of melanoma and nevus. But there are few researches on index for the diagnosis. This study deals with features of melanoma and nevus for computer diagnosis. First, we extracted the contour of lesions by image processing. One hundred five values of features were computed based on ABCD-rule. Discriminant analysis showed the accuracy of 96.0{\%} (Specificity of 98.3{\%} and the Sensitivity of 90.0{\%}). The results obviously showed the difference between melanoma and nevus.",
keywords = "Benign nevus, Discriminant analysis, Image processing, Melanoma",
author = "Toshiyuki Tanaka and Reina Yamada and Michiko Tanaka and Kunio Shimizu and Masaru Tanaka",
year = "2007",
doi = "10.1541/ieejeiss.127.330",
language = "English",
volume = "127",
pages = "330--337",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "3",

}

TY - JOUR

T1 - Diagnotic support system of melanoma based on morphological features

AU - Tanaka, Toshiyuki

AU - Yamada, Reina

AU - Tanaka, Michiko

AU - Shimizu, Kunio

AU - Tanaka, Masaru

PY - 2007

Y1 - 2007

N2 - At present the diagnosis of melanoma is mainly performed based on the experience of each doctor. They need some objective measure for diagnosis of melanoma and nevus. But there are few researches on index for the diagnosis. This study deals with features of melanoma and nevus for computer diagnosis. First, we extracted the contour of lesions by image processing. One hundred five values of features were computed based on ABCD-rule. Discriminant analysis showed the accuracy of 96.0% (Specificity of 98.3% and the Sensitivity of 90.0%). The results obviously showed the difference between melanoma and nevus.

AB - At present the diagnosis of melanoma is mainly performed based on the experience of each doctor. They need some objective measure for diagnosis of melanoma and nevus. But there are few researches on index for the diagnosis. This study deals with features of melanoma and nevus for computer diagnosis. First, we extracted the contour of lesions by image processing. One hundred five values of features were computed based on ABCD-rule. Discriminant analysis showed the accuracy of 96.0% (Specificity of 98.3% and the Sensitivity of 90.0%). The results obviously showed the difference between melanoma and nevus.

KW - Benign nevus

KW - Discriminant analysis

KW - Image processing

KW - Melanoma

UR - http://www.scopus.com/inward/record.url?scp=33847703685&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847703685&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.127.330

DO - 10.1541/ieejeiss.127.330

M3 - Article

AN - SCOPUS:33847703685

VL - 127

SP - 330

EP - 337

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 3

ER -