Segmentation of nuclei in hepatic histological images using multimodal method

Masanobu Takahashi, J. Koichi, Y. Makino, T. Kitani, M. Nakano

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

Abstract

Nuclear density and nuclear morphometric features such as shape of nuclei are useful in diagnosing hepatocellular carcinoma, especially well-differentiated hepatocellular carcinoma (ewHCC). We previously developed a support system for diagnosing ewHCC that enables the user to estimate the nuclear density and the roundness factor of nuclei. The system automatically extracts the positions and contours of nuclei from a microscopic image. However, it takes a few minutes for the user to correct wrong positions and contours using a graphical user interface (GUI). Our target is to improve the accuracy for nuclear position extraction and contours extraction and to make the system more convenient. As a method to improve the accuracy, a multimodal method was employed. A multimodal method is a method to use images captured by more than one imaging methods. We found a composite image of bright-field and dark-field images improves the accuracy. Experimental results showed that the accuracy was improved by the multimodal method as well as by some additional improvements in the method.

Original languageEnglish
Title of host publicationIFMBE Proceedings
Pages639-642
Number of pages4
Volume37
DOIs
Publication statusPublished - 2011

Fingerprint

Graphical user interfaces
Imaging techniques
Composite materials

Keywords

  • Contour
  • Hepatocellular carcinoma
  • Histology
  • Image
  • Nuclear density
  • Nucleolus
  • Nucleus
  • Segmentation
  • Support

ASJC Scopus subject areas

  • Biomedical Engineering
  • Bioengineering

Cite this

Takahashi, M., Koichi, J., Makino, Y., Kitani, T., & Nakano, M. (2011). Segmentation of nuclei in hepatic histological images using multimodal method. In IFMBE Proceedings (Vol. 37, pp. 639-642) https://doi.org/10.1007/978-3-642-23508-5_166

Segmentation of nuclei in hepatic histological images using multimodal method. / Takahashi, Masanobu; Koichi, J.; Makino, Y.; Kitani, T.; Nakano, M.

IFMBE Proceedings. Vol. 37 2011. p. 639-642.

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

Takahashi, M, Koichi, J, Makino, Y, Kitani, T & Nakano, M 2011, Segmentation of nuclei in hepatic histological images using multimodal method. in IFMBE Proceedings. vol. 37, pp. 639-642. https://doi.org/10.1007/978-3-642-23508-5_166
Takahashi M, Koichi J, Makino Y, Kitani T, Nakano M. Segmentation of nuclei in hepatic histological images using multimodal method. In IFMBE Proceedings. Vol. 37. 2011. p. 639-642 https://doi.org/10.1007/978-3-642-23508-5_166
Takahashi, Masanobu ; Koichi, J. ; Makino, Y. ; Kitani, T. ; Nakano, M. / Segmentation of nuclei in hepatic histological images using multimodal method. IFMBE Proceedings. Vol. 37 2011. pp. 639-642
@inproceedings{c6d949176fb14cfaa0e4db4e4cab93f5,
title = "Segmentation of nuclei in hepatic histological images using multimodal method",
abstract = "Nuclear density and nuclear morphometric features such as shape of nuclei are useful in diagnosing hepatocellular carcinoma, especially well-differentiated hepatocellular carcinoma (ewHCC). We previously developed a support system for diagnosing ewHCC that enables the user to estimate the nuclear density and the roundness factor of nuclei. The system automatically extracts the positions and contours of nuclei from a microscopic image. However, it takes a few minutes for the user to correct wrong positions and contours using a graphical user interface (GUI). Our target is to improve the accuracy for nuclear position extraction and contours extraction and to make the system more convenient. As a method to improve the accuracy, a multimodal method was employed. A multimodal method is a method to use images captured by more than one imaging methods. We found a composite image of bright-field and dark-field images improves the accuracy. Experimental results showed that the accuracy was improved by the multimodal method as well as by some additional improvements in the method.",
keywords = "Contour, Hepatocellular carcinoma, Histology, Image, Nuclear density, Nucleolus, Nucleus, Segmentation, Support",
author = "Masanobu Takahashi and J. Koichi and Y. Makino and T. Kitani and M. Nakano",
year = "2011",
doi = "10.1007/978-3-642-23508-5_166",
language = "English",
volume = "37",
pages = "639--642",
booktitle = "IFMBE Proceedings",

}

TY - GEN

T1 - Segmentation of nuclei in hepatic histological images using multimodal method

AU - Takahashi, Masanobu

AU - Koichi, J.

AU - Makino, Y.

AU - Kitani, T.

AU - Nakano, M.

PY - 2011

Y1 - 2011

N2 - Nuclear density and nuclear morphometric features such as shape of nuclei are useful in diagnosing hepatocellular carcinoma, especially well-differentiated hepatocellular carcinoma (ewHCC). We previously developed a support system for diagnosing ewHCC that enables the user to estimate the nuclear density and the roundness factor of nuclei. The system automatically extracts the positions and contours of nuclei from a microscopic image. However, it takes a few minutes for the user to correct wrong positions and contours using a graphical user interface (GUI). Our target is to improve the accuracy for nuclear position extraction and contours extraction and to make the system more convenient. As a method to improve the accuracy, a multimodal method was employed. A multimodal method is a method to use images captured by more than one imaging methods. We found a composite image of bright-field and dark-field images improves the accuracy. Experimental results showed that the accuracy was improved by the multimodal method as well as by some additional improvements in the method.

AB - Nuclear density and nuclear morphometric features such as shape of nuclei are useful in diagnosing hepatocellular carcinoma, especially well-differentiated hepatocellular carcinoma (ewHCC). We previously developed a support system for diagnosing ewHCC that enables the user to estimate the nuclear density and the roundness factor of nuclei. The system automatically extracts the positions and contours of nuclei from a microscopic image. However, it takes a few minutes for the user to correct wrong positions and contours using a graphical user interface (GUI). Our target is to improve the accuracy for nuclear position extraction and contours extraction and to make the system more convenient. As a method to improve the accuracy, a multimodal method was employed. A multimodal method is a method to use images captured by more than one imaging methods. We found a composite image of bright-field and dark-field images improves the accuracy. Experimental results showed that the accuracy was improved by the multimodal method as well as by some additional improvements in the method.

KW - Contour

KW - Hepatocellular carcinoma

KW - Histology

KW - Image

KW - Nuclear density

KW - Nucleolus

KW - Nucleus

KW - Segmentation

KW - Support

UR - http://www.scopus.com/inward/record.url?scp=80455162733&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80455162733&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-23508-5_166

DO - 10.1007/978-3-642-23508-5_166

M3 - Conference contribution

AN - SCOPUS:80455162733

VL - 37

SP - 639

EP - 642

BT - IFMBE Proceedings

ER -