Image feature extraction method with SIFT to diagnose prostate cancer

Yoshiteru Toki, Toshiyuki Tanaka

研究成果: Conference contribution

6 被引用数 (Scopus)

抄録

Number of prostate cancer patients are increasing but diagnosing pathologists are not enough. Then supporting system to diagnose prostate cancer on biopsy image is needed by pathologists. However staining conditions of prostate biopsy images are uneven, so extracting their form by automatic method is difficult. Because of this problem, previous study aiming to diagnose each glandular needed to except imperfect extraction glandular. Then we propose new feature extraction method (Area Rates on Components and SIFT + BoK) aiming to improve accuracy on imperfect extracted glands. In our experiment, diagnosing accuracy is improved 6.3% ∼ 13.3%.

本文言語English
ホスト出版物のタイトル2012 Proceedings of SICE Annual Conference, SICE 2012
出版社Society of Instrument and Control Engineers (SICE)
ページ2185-2188
ページ数4
ISBN(印刷版)9781467322591
出版ステータスPublished - 2012 1月 1
イベント2012 51st Annual Conference on of the Society of Instrument and Control Engineers of Japan, SICE 2012 - Akita, Japan
継続期間: 2012 8月 202012 8月 23

出版物シリーズ

名前Proceedings of the SICE Annual Conference

Other

Other2012 51st Annual Conference on of the Society of Instrument and Control Engineers of Japan, SICE 2012
国/地域Japan
CityAkita
Period12/8/2012/8/23

ASJC Scopus subject areas

  • 制御およびシステム工学
  • コンピュータ サイエンスの応用
  • 電子工学および電気工学

フィンガープリント

「Image feature extraction method with SIFT to diagnose prostate cancer」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル