Feature Extractions for the Pathological Diagnosis of Oral Malignancies
-
- SATOH Kyosuke
- Faculty of Engineering, Niigata University
-
- Sami Mustafa M.
- Faculty of Engineering, Niigata University
-
- KIKUCHI Hisakazu
- Faculty of Engineering, Niigata University
-
- SAKU Takashi
- Division of Oral Pathology, Graduate School of Medical and Dental Sciences, Niigata University
Bibliographic Information
- Other Title
-
- 口腔悪性腫瘍の病理診断における特徴量抽出法に関する検討
- コウクウ アクセイ シュヨウ ノ ビョウリ シンダン ニ オケル トクチョウリョウ チュウシュツホウ ニ カンスル ケントウ
Search this article
Description
Extracting the feature of alignment in oral pathological images, in helpful for the pathological diagnosis and development of diagnosis guidelines. This paper propose two types of processing, basal cell counting by the distance transform and segmentation of the epithelium region using multiple threshold values which is calculated by a self-organizing map neural network. The counting results have shown a good agreement with these of professional histopathologists, and hence the proposed counting is sufficiently accurate. The segmentation of epithelium regions has been successfully developed with the aid of a set of multiple values for luma thresholding.
Journal
-
- ITE Technical Report
-
ITE Technical Report 33.31 (0), 1-4, 2009
The Institute of Image Information and Television Engineers
- Tweet
Details 詳細情報について
-
- CRID
- 1390001204525682944
-
- NII Article ID
- 110007360894
-
- NII Book ID
- AN1059086X
-
- ISSN
- 24241970
- 13426893
-
- NDL BIB ID
- 10322545
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- CiNii Articles
-
- Abstract License Flag
- Disallowed