Detection of Breast Carcinoma Regions Using Artificial Organisms

Hironori OKII  Takashi UOZUMI  Koichi ONO  Yasunori FUJISAWA  

IEICE TRANSACTIONS on Information and Systems   Vol.E79-D   No.11   pp.1596-1600
Publication Date: 1996/11/25
Online ISSN: 
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Medical Electronics and Medical Information
breast carcinoma,  medical image diagnosis,  histological diagnosis,  stained image,  artificial life,  genetic algorithm,  

Full Text: PDF>>
Buy this Article

This paper describes a new region segmentation method which is detectable carcinoma regions from hematoxylin and eosin (HE)-stained breast tumor images using collective behaviors of artificial organisms. In this model, the movement characteristics of artificial organisms are controlled by the gene, and the adaptive behavior of artificial organisms in the environment, carcinoma regions or not, is evaluated by the texture features.