Evaluation features for malignancy of lung tumor using shape features of nuclei

Daisuke Wakamiya, Toshiyuki Tanaka, Teruaki Oka

Research output: Contribution to conferencePaperpeer-review


We know that pathological diagnosis spend a lot of time, cost, and effort of person. In this research we propose some characteristics of tumor cells for evaluating malignancy using computer. We compare them to find the most effective characteristics. Then we calculate data to find the boundary of the benignant tumor cells and the malignant ones. From the result of our analysis, area of nucleus was one of effective characteristics to distinguish the malignant tumor from the benign tumor.

Original languageEnglish
Number of pages4
Publication statusPublished - 2005
EventSICE Annual Conference 2005 - Okayama, Japan
Duration: 2005 Aug 82005 Aug 10


OtherSICE Annual Conference 2005


  • Automatic cytological diagnosis screening
  • Characteristics
  • Lung tumor

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Evaluation features for malignancy of lung tumor using shape features of nuclei'. Together they form a unique fingerprint.

Cite this