Classification of skin tumors based on shape features of nuclei

Toshiyuki Tanaka, Yoko Murase, Teruaki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In this paper, an automated system to segment cell nuclei of dermatofibroma (DF) and dermatofibrosarcoma protuberans (DFSP) is proposed. It is difficult to segment nuclear regions accurately, because there exists a lot of ambiguous nuclei. Objective of the system is to segment nuclear regions objectively and in some accuracy. In the system, regions to be segmented are defined as regions that are surrounded by edges of certain strength. Under this restriction, arbitrary shaped nuclear regions and weakly stained nuclear regions are possible to be extracted. At first, contrast emphasis using hue is done as preprocessing. Image binarization is done by a dynamic thresholding method with implementation of Laplacian-histogram method and Otsu□fs thresholding method. At last, Separation of the overlapping nuclei is carried out by watershed algorithm. To evaluate availability of this system, segmentation test was done using real tissue cell images of DF and DFSP. From some features computed from the segmented nuclear regions, an automated classification of benign tumor or malignant tumor is finally performed.

Original languageEnglish
Title of host publicationAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
Pages1064
Number of pages1
Volume2
Publication statusPublished - 2002
Externally publishedYes
EventProceedings of the 2002 IEEE Engineering in Medicine and Biology 24th Annual Conference and the 2002 Fall Meeting of the Biomedical Engineering Society (BMES / EMBS) - Houston, TX, United States
Duration: 2002 Oct 232002 Oct 26

Other

OtherProceedings of the 2002 IEEE Engineering in Medicine and Biology 24th Annual Conference and the 2002 Fall Meeting of the Biomedical Engineering Society (BMES / EMBS)
CountryUnited States
CityHouston, TX
Period02/10/2302/10/26

Fingerprint

Tumors
Skin
Watersheds
Cells
Availability
Tissue

Keywords

  • Classification
  • Image processing
  • Shape feature
  • Skin tumor

ASJC Scopus subject areas

  • Bioengineering

Cite this

Tanaka, T., Murase, Y., & Teruaki (2002). Classification of skin tumors based on shape features of nuclei. In Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings (Vol. 2, pp. 1064)

Classification of skin tumors based on shape features of nuclei. / Tanaka, Toshiyuki; Murase, Yoko; Teruaki.

Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. Vol. 2 2002. p. 1064.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tanaka, T, Murase, Y & Teruaki 2002, Classification of skin tumors based on shape features of nuclei. in Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. vol. 2, pp. 1064, Proceedings of the 2002 IEEE Engineering in Medicine and Biology 24th Annual Conference and the 2002 Fall Meeting of the Biomedical Engineering Society (BMES / EMBS), Houston, TX, United States, 02/10/23.
Tanaka T, Murase Y, Teruaki. Classification of skin tumors based on shape features of nuclei. In Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. Vol. 2. 2002. p. 1064
Tanaka, Toshiyuki ; Murase, Yoko ; Teruaki. / Classification of skin tumors based on shape features of nuclei. Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. Vol. 2 2002. pp. 1064
@inproceedings{b0cf19e630784c2e9210a65eec455484,
title = "Classification of skin tumors based on shape features of nuclei",
abstract = "In this paper, an automated system to segment cell nuclei of dermatofibroma (DF) and dermatofibrosarcoma protuberans (DFSP) is proposed. It is difficult to segment nuclear regions accurately, because there exists a lot of ambiguous nuclei. Objective of the system is to segment nuclear regions objectively and in some accuracy. In the system, regions to be segmented are defined as regions that are surrounded by edges of certain strength. Under this restriction, arbitrary shaped nuclear regions and weakly stained nuclear regions are possible to be extracted. At first, contrast emphasis using hue is done as preprocessing. Image binarization is done by a dynamic thresholding method with implementation of Laplacian-histogram method and Otsu□fs thresholding method. At last, Separation of the overlapping nuclei is carried out by watershed algorithm. To evaluate availability of this system, segmentation test was done using real tissue cell images of DF and DFSP. From some features computed from the segmented nuclear regions, an automated classification of benign tumor or malignant tumor is finally performed.",
keywords = "Classification, Image processing, Shape feature, Skin tumor",
author = "Toshiyuki Tanaka and Yoko Murase and Teruaki",
year = "2002",
language = "English",
volume = "2",
pages = "1064",
booktitle = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",

}

TY - GEN

T1 - Classification of skin tumors based on shape features of nuclei

AU - Tanaka, Toshiyuki

AU - Murase, Yoko

AU - Teruaki,

PY - 2002

Y1 - 2002

N2 - In this paper, an automated system to segment cell nuclei of dermatofibroma (DF) and dermatofibrosarcoma protuberans (DFSP) is proposed. It is difficult to segment nuclear regions accurately, because there exists a lot of ambiguous nuclei. Objective of the system is to segment nuclear regions objectively and in some accuracy. In the system, regions to be segmented are defined as regions that are surrounded by edges of certain strength. Under this restriction, arbitrary shaped nuclear regions and weakly stained nuclear regions are possible to be extracted. At first, contrast emphasis using hue is done as preprocessing. Image binarization is done by a dynamic thresholding method with implementation of Laplacian-histogram method and Otsu□fs thresholding method. At last, Separation of the overlapping nuclei is carried out by watershed algorithm. To evaluate availability of this system, segmentation test was done using real tissue cell images of DF and DFSP. From some features computed from the segmented nuclear regions, an automated classification of benign tumor or malignant tumor is finally performed.

AB - In this paper, an automated system to segment cell nuclei of dermatofibroma (DF) and dermatofibrosarcoma protuberans (DFSP) is proposed. It is difficult to segment nuclear regions accurately, because there exists a lot of ambiguous nuclei. Objective of the system is to segment nuclear regions objectively and in some accuracy. In the system, regions to be segmented are defined as regions that are surrounded by edges of certain strength. Under this restriction, arbitrary shaped nuclear regions and weakly stained nuclear regions are possible to be extracted. At first, contrast emphasis using hue is done as preprocessing. Image binarization is done by a dynamic thresholding method with implementation of Laplacian-histogram method and Otsu□fs thresholding method. At last, Separation of the overlapping nuclei is carried out by watershed algorithm. To evaluate availability of this system, segmentation test was done using real tissue cell images of DF and DFSP. From some features computed from the segmented nuclear regions, an automated classification of benign tumor or malignant tumor is finally performed.

KW - Classification

KW - Image processing

KW - Shape feature

KW - Skin tumor

UR - http://www.scopus.com/inward/record.url?scp=0036915913&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036915913&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0036915913

VL - 2

SP - 1064

BT - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

ER -