Support system for histopathologic diagnosis of hepatocellular carcinoma using nuclear positions

Masanobu Takahashi, Masayuki Nakano, Muneyoshi Tomita, Kazumasa Matsunaga

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

6 Citations (Scopus)

Abstract

We report support system for histopathologic diagnosis of hepatocellular carcinoma, and especially for differential diagnosis between normal and extremely well-differentiated hepatocellular carcinoma (EHCC). To extract the positions of hepatocellular nuclei, a three-step method composing candidates extraction, contours extraction and screening steps was proposed. About 83% of the nuclear positions were correctly extracted with 10% of the positions wrongly extracted. As a result, the time required to correct the wrong positions using a graphical user interface (GUI) was reduced. Nuclear density and ratio of high nuclear density area are proposed as the two features calculated using these extracted positions. Simulation results showed the effectiveness of these features for differential diagnosis between normal and EHCC. A GUI was developed that enables a user to extract the nuclear positions, to correct the positions, and to calculate the proposed features by simple button operations. The total time for processing one image and extracting the features was about 2 minutes. This system would be helpful in actual diagnosis.

Original languageEnglish
Title of host publicationProceedings of the IASTED International Conference on Biomedical Engineering
EditorsB. Tilg
Pages219-223
Number of pages5
Publication statusPublished - 2004
EventProceedings of the IASTED International Conference on Biomedical Engineering - Innsbruck
Duration: 2004 Feb 162004 Feb 18

Other

OtherProceedings of the IASTED International Conference on Biomedical Engineering
CityInnsbruck
Period04/2/1604/2/18

Fingerprint

Graphical user interfaces
Screening
Processing

Keywords

  • Contour extraction
  • Diagnosis support
  • Hepatocellular carcinoma
  • Histopathology
  • Nucleus
  • Segmentation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Takahashi, M., Nakano, M., Tomita, M., & Matsunaga, K. (2004). Support system for histopathologic diagnosis of hepatocellular carcinoma using nuclear positions. In B. Tilg (Ed.), Proceedings of the IASTED International Conference on Biomedical Engineering (pp. 219-223). [417-123]

Support system for histopathologic diagnosis of hepatocellular carcinoma using nuclear positions. / Takahashi, Masanobu; Nakano, Masayuki; Tomita, Muneyoshi; Matsunaga, Kazumasa.

Proceedings of the IASTED International Conference on Biomedical Engineering. ed. / B. Tilg. 2004. p. 219-223 417-123.

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

Takahashi, M, Nakano, M, Tomita, M & Matsunaga, K 2004, Support system for histopathologic diagnosis of hepatocellular carcinoma using nuclear positions. in B Tilg (ed.), Proceedings of the IASTED International Conference on Biomedical Engineering., 417-123, pp. 219-223, Proceedings of the IASTED International Conference on Biomedical Engineering, Innsbruck, 04/2/16.
Takahashi M, Nakano M, Tomita M, Matsunaga K. Support system for histopathologic diagnosis of hepatocellular carcinoma using nuclear positions. In Tilg B, editor, Proceedings of the IASTED International Conference on Biomedical Engineering. 2004. p. 219-223. 417-123
Takahashi, Masanobu ; Nakano, Masayuki ; Tomita, Muneyoshi ; Matsunaga, Kazumasa. / Support system for histopathologic diagnosis of hepatocellular carcinoma using nuclear positions. Proceedings of the IASTED International Conference on Biomedical Engineering. editor / B. Tilg. 2004. pp. 219-223
@inproceedings{2a42279cd1c34414bc7e468cd0534142,
title = "Support system for histopathologic diagnosis of hepatocellular carcinoma using nuclear positions",
abstract = "We report support system for histopathologic diagnosis of hepatocellular carcinoma, and especially for differential diagnosis between normal and extremely well-differentiated hepatocellular carcinoma (EHCC). To extract the positions of hepatocellular nuclei, a three-step method composing candidates extraction, contours extraction and screening steps was proposed. About 83{\%} of the nuclear positions were correctly extracted with 10{\%} of the positions wrongly extracted. As a result, the time required to correct the wrong positions using a graphical user interface (GUI) was reduced. Nuclear density and ratio of high nuclear density area are proposed as the two features calculated using these extracted positions. Simulation results showed the effectiveness of these features for differential diagnosis between normal and EHCC. A GUI was developed that enables a user to extract the nuclear positions, to correct the positions, and to calculate the proposed features by simple button operations. The total time for processing one image and extracting the features was about 2 minutes. This system would be helpful in actual diagnosis.",
keywords = "Contour extraction, Diagnosis support, Hepatocellular carcinoma, Histopathology, Nucleus, Segmentation",
author = "Masanobu Takahashi and Masayuki Nakano and Muneyoshi Tomita and Kazumasa Matsunaga",
year = "2004",
language = "English",
isbn = "0889863792",
pages = "219--223",
editor = "B. Tilg",
booktitle = "Proceedings of the IASTED International Conference on Biomedical Engineering",

}

TY - GEN

T1 - Support system for histopathologic diagnosis of hepatocellular carcinoma using nuclear positions

AU - Takahashi, Masanobu

AU - Nakano, Masayuki

AU - Tomita, Muneyoshi

AU - Matsunaga, Kazumasa

PY - 2004

Y1 - 2004

N2 - We report support system for histopathologic diagnosis of hepatocellular carcinoma, and especially for differential diagnosis between normal and extremely well-differentiated hepatocellular carcinoma (EHCC). To extract the positions of hepatocellular nuclei, a three-step method composing candidates extraction, contours extraction and screening steps was proposed. About 83% of the nuclear positions were correctly extracted with 10% of the positions wrongly extracted. As a result, the time required to correct the wrong positions using a graphical user interface (GUI) was reduced. Nuclear density and ratio of high nuclear density area are proposed as the two features calculated using these extracted positions. Simulation results showed the effectiveness of these features for differential diagnosis between normal and EHCC. A GUI was developed that enables a user to extract the nuclear positions, to correct the positions, and to calculate the proposed features by simple button operations. The total time for processing one image and extracting the features was about 2 minutes. This system would be helpful in actual diagnosis.

AB - We report support system for histopathologic diagnosis of hepatocellular carcinoma, and especially for differential diagnosis between normal and extremely well-differentiated hepatocellular carcinoma (EHCC). To extract the positions of hepatocellular nuclei, a three-step method composing candidates extraction, contours extraction and screening steps was proposed. About 83% of the nuclear positions were correctly extracted with 10% of the positions wrongly extracted. As a result, the time required to correct the wrong positions using a graphical user interface (GUI) was reduced. Nuclear density and ratio of high nuclear density area are proposed as the two features calculated using these extracted positions. Simulation results showed the effectiveness of these features for differential diagnosis between normal and EHCC. A GUI was developed that enables a user to extract the nuclear positions, to correct the positions, and to calculate the proposed features by simple button operations. The total time for processing one image and extracting the features was about 2 minutes. This system would be helpful in actual diagnosis.

KW - Contour extraction

KW - Diagnosis support

KW - Hepatocellular carcinoma

KW - Histopathology

KW - Nucleus

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=11144298104&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11144298104&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:11144298104

SN - 0889863792

SN - 9780889863798

SP - 219

EP - 223

BT - Proceedings of the IASTED International Conference on Biomedical Engineering

A2 - Tilg, B.

ER -