Recognition of lung cancers on CT using 3-D object models of different classes

Hotaka Takizawa, Shinji Yamamoto, Tsuyoshi Shiina

研究成果: Conference contribution

抄録

The present paper describes a recognition method of pulmonary nodules in thoracic CT scans by use of 3- D spherical and cylindrical models that represent nodules (i.e. possible cancers) and blood vessels, respectively. The anatomical validity of these object models and their fidelity to CT scans are evaluated based on the Bayes theorem. The nodule recognition is employed by the maximum a posteriori estimation. The proposed method is applied to actual CT scans, and experimental results are shown.

本文言語English
ホスト出版物のタイトルProceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009
ページ257-260
ページ数4
出版ステータスPublished - 2009
外部発表はい
イベント11th IAPR Conference on Machine Vision Applications, MVA 2009 - Yokohama, Japan
継続期間: 2009 5月 202009 5月 22

出版物シリーズ

名前Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009

Conference

Conference11th IAPR Conference on Machine Vision Applications, MVA 2009
国/地域Japan
CityYokohama
Period09/5/2009/5/22

ASJC Scopus subject areas

  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Recognition of lung cancers on CT using 3-D object models of different classes」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