Feature Extraction for Classification of Breast Tumor Images Using Artificial Organisms

スポンサーリンク

概要

• 論文の詳細を見る

• This paper describes a method for classification of hematoxylin and eosin (HE)-stained breast tumor images into benign or malignant using the adaptive searching ability of artificial organisms. Each artificial organism has some attributes, such as, age, internal energy and coordinates. In addition, the artificial organism has a differentiation function for evaluating "malignant" or "benign" tumors and the adaptive behaviors of each artificial organism are evaluated using five kinds of texture features. The texture feature of nuclei regions in normal mammary glands and that of carcinoma regions in malignant tumors are treated as "self" and "non-self, " respectively. This model consists of two stages of operations for detecting tumor regions, the learning and searching stages. At the learning stage, the nuclei regions are roughly detected and classified into benign or malignant tumors. At the searching stage, the similarity of each organism's environment is investigated before and after the movement for detecting breast tumor regions precisely. The method developed was applied to 21 cases of test images and the distinction between malignant and benign tumors by the artificial organisms was successful in all cases. The proposed method has the following advantages: the texture feature values for the evaluation of tumor regions at the searching stage are decided automatically during the learning stage in every input image. Evaluation of the environment, whether the target pixel is a malignant tumor or not, is performed based on the angular difference in each texture feature. Therefore, this model can successfully detect tumor regions and classify the type of tumors correctly without affecting a wide variety of breast tumor images, which depends on the tissue condition and the degree of malignancy in each breast tumor case.

• 社団法人電子情報通信学会の論文
• 2001-03-01

著者

• Fujisawa Yasunori

  Clinical Laboratory Muroran City General Hospital

• UOZUMI Takashi

  Faculty of Technology, Muroran Institute of Technology

• ONO Koichi

  Faculty of Technology, Muroran Institute of Technology

• Ono K

  Muroran Inst. Technol. Muroran‐shi Jpn

• Okii H

  Muroran Inst. Technol. Muroran‐shi Jpn

• Uozumi T

  Muroran Inst. Technol. Muroran‐shi Jpn

• Uozumi Takashi

  Faculty Of Technology Muroran Institute Of Technology

• OKII Hironiro

  Faculty of Technology, Muroran Institute of Technology

• Ono Koichi

  Faculty Of Technology Muroran Institute Of Technology

関連論文

• Automatic Feature Extraction from Breast Tumor Images Using Artificial Organisms
• Electroluminescence in Perylene-and-Tetracene-Doped Anthracene Films
• Electroluminescence in Perylene-Doped Anthracene Films : The Ambient Gas Effect in the Emission Process
• Feature Extraction for Classification of Breast Tumor Images Using Artificial Organisms
• Automatic Detection of Nuclei Regions from HE-Stained Breast Tumor Images Using Artificial Organisms
• Detection of Breast Carcinoma Regions Using Artificial Organisms
• Automatic Color Segmentation Method Using a Neural Network Model for Stained Images

スポンサーリンク