Diagnotic Support System of Melanoma based on Morphological Features

• Tanaka Toshiyuki

  Faculty of Science and Technology, Keio University

• Yamada Reina

  Faculty of Science and Technology, Keio University

• Tanaka Michiko

  Faculty of Science and Technology, Keio University

• Shimizu Kunio

  Faculty of Science and Technology, Keio University

• Tanaka Masaru

  School of Medicine, Keio University

Bibliographic Information

Other Title

• 形態学的特徴量に基づく悪性黒色腫の診断支援システム
• ケイタイガクテキ トクチョウリョウ ニ モトズク アクセイ コクショクシュ ノ シンダン シエン システム

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.

Journal

• IEEJ Transactions on Electronics, Information and Systems

  IEEJ Transactions on Electronics, Information and Systems 127 (3), 330-337, 2007

  The Institute of Electrical Engineers of Japan

Keywords

• melanoma
• benign nevus
• image processing
• discriminant analysis

Details

• CRID: 1390282679581638656
• NII Article ID: 10018738166
• NII Book ID: AN10065950
• DOI: 10.1541/ieejeiss.127.330
• ISSN: 13488155
• ISSN: 03854221
• NDL BIB ID: 8728368
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I8728368
• Web Site: http://www.jstage.jst.go.jp/article/ieejeiss/127/3/127_3_330/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
• Abstract License Flag: Disallowed