Cell nucleus segmentation of skin tumor using image processing

Toshiyuki Tanaka, Tomoo Joke, Teruaki Oka

研究成果: Conference article査読

13 被引用数 (Scopus)


Automation and quantification of diagnosis of tumor cell images have been studied for these three decades in the field of medical imaging technology. Many techniques of image processing were proposed to solve problems such as nucleus segmentation and classification. But these studies have mainly focused on epithelial tumors. Nonepithelial skin tumors such as dermatofibroma (DF) and dermatofibrosarcoma protuberans (DFSP) have not been enough studied. DF is benign tumorous disease and DFSP is mid-grade malignant tumor. Recently, it is necessary that criterion of classification between DF and DFSP is quantitatively specified. In this paper a system for segmenting cell nuclei of DF and DFSP is proposed. Nuclei regions are objectively segmented and surrounded using edges of strength by the system. Segmentation of arbitrary shaped nuclear regions and weakly stained nuclear region is made. A dynamic thresholding method with combining Laplacian histogram with Ohtsu's method is used for segmentation. Segmentation test was done using real tissue cell images of DF and DFSP to evaluate validity of this system. Shape characteristics such as grade of similarity to circle were also computed from the segmented regions to assure that some differences between DF and DFSP is expressed in its distribution.

ジャーナルAnnual Reports of the Research Reactor Institute, Kyoto University
出版ステータスPublished - 2001 12月 1
イベント23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Istanbul, Turkey
継続期間: 2001 10月 252001 10月 28

ASJC Scopus subject areas

  • エネルギー工学および電力技術
  • 機械工学


「Cell nucleus segmentation of skin tumor using image processing」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。