Multimodal method for extracting nuclei in hepatic histological images

Keita Miyamoto, Masanobu Takahashi, Jumpei Koichi, Takuya Kitani, Masayuki 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 hepato-cellular 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. Dark-field and phase-contrast images, which can easily be captured using a combined condenser and a phasecontrast objective lens, were used in addition to a conventional bright-field image. Three kinds of multimodal techniques, alpha-blending of bright-field and dark-field images, enhancement of nuclei, and removal of positions extracted in sinusoidal areas, were employed. Experiments for nuclear position extraction and contour extraction were carried out. The best results were obtained when all the multimodal techniques were employed, showing the effectiveness of the method.

Original languageEnglish
Title of host publicationIFMBE Proceedings
Pages927-930
Number of pages4
Volume39 IFMBE
DOIs
Publication statusPublished - 2013
EventWorld Congress on Medical Physics and Biomedical Engineering - Beijing
Duration: 2012 May 262012 May 31

Other

OtherWorld Congress on Medical Physics and Biomedical Engineering
CityBeijing
Period12/5/2612/5/31

Fingerprint

Image enhancement
Graphical user interfaces
Lenses
Imaging techniques
Experiments

Keywords

  • Dark-field
  • Hepatocellular carcinoma
  • Histology
  • Multimodal
  • Nucleus

ASJC Scopus subject areas

  • Biomedical Engineering
  • Bioengineering

Cite this

Miyamoto, K., Takahashi, M., Koichi, J., Kitani, T., & Nakano, M. (2013). Multimodal method for extracting nuclei in hepatic histological images. In IFMBE Proceedings (Vol. 39 IFMBE, pp. 927-930) https://doi.org/10.1007/978-3-642-29305-4_243

Multimodal method for extracting nuclei in hepatic histological images. / Miyamoto, Keita; Takahashi, Masanobu; Koichi, Jumpei; Kitani, Takuya; Nakano, Masayuki.

IFMBE Proceedings. Vol. 39 IFMBE 2013. p. 927-930.

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

Miyamoto, K, Takahashi, M, Koichi, J, Kitani, T & Nakano, M 2013, Multimodal method for extracting nuclei in hepatic histological images. in IFMBE Proceedings. vol. 39 IFMBE, pp. 927-930, World Congress on Medical Physics and Biomedical Engineering, Beijing, 12/5/26. https://doi.org/10.1007/978-3-642-29305-4_243
Miyamoto K, Takahashi M, Koichi J, Kitani T, Nakano M. Multimodal method for extracting nuclei in hepatic histological images. In IFMBE Proceedings. Vol. 39 IFMBE. 2013. p. 927-930 https://doi.org/10.1007/978-3-642-29305-4_243
Miyamoto, Keita ; Takahashi, Masanobu ; Koichi, Jumpei ; Kitani, Takuya ; Nakano, Masayuki. / Multimodal method for extracting nuclei in hepatic histological images. IFMBE Proceedings. Vol. 39 IFMBE 2013. pp. 927-930
@inproceedings{cb78ef8f304145feb580d9a0fcf1eda4,
title = "Multimodal method for extracting nuclei in hepatic histological images",
abstract = "Nuclear density and nuclear morphometric features such as shape of nuclei are useful in diagnosing hepato-cellular 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. Dark-field and phase-contrast images, which can easily be captured using a combined condenser and a phasecontrast objective lens, were used in addition to a conventional bright-field image. Three kinds of multimodal techniques, alpha-blending of bright-field and dark-field images, enhancement of nuclei, and removal of positions extracted in sinusoidal areas, were employed. Experiments for nuclear position extraction and contour extraction were carried out. The best results were obtained when all the multimodal techniques were employed, showing the effectiveness of the method.",
keywords = "Dark-field, Hepatocellular carcinoma, Histology, Multimodal, Nucleus",
author = "Keita Miyamoto and Masanobu Takahashi and Jumpei Koichi and Takuya Kitani and Masayuki Nakano",
year = "2013",
doi = "10.1007/978-3-642-29305-4_243",
language = "English",
isbn = "9783642293047",
volume = "39 IFMBE",
pages = "927--930",
booktitle = "IFMBE Proceedings",

}

TY - GEN

T1 - Multimodal method for extracting nuclei in hepatic histological images

AU - Miyamoto, Keita

AU - Takahashi, Masanobu

AU - Koichi, Jumpei

AU - Kitani, Takuya

AU - Nakano, Masayuki

PY - 2013

Y1 - 2013

N2 - Nuclear density and nuclear morphometric features such as shape of nuclei are useful in diagnosing hepato-cellular 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. Dark-field and phase-contrast images, which can easily be captured using a combined condenser and a phasecontrast objective lens, were used in addition to a conventional bright-field image. Three kinds of multimodal techniques, alpha-blending of bright-field and dark-field images, enhancement of nuclei, and removal of positions extracted in sinusoidal areas, were employed. Experiments for nuclear position extraction and contour extraction were carried out. The best results were obtained when all the multimodal techniques were employed, showing the effectiveness of the method.

AB - Nuclear density and nuclear morphometric features such as shape of nuclei are useful in diagnosing hepato-cellular 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. Dark-field and phase-contrast images, which can easily be captured using a combined condenser and a phasecontrast objective lens, were used in addition to a conventional bright-field image. Three kinds of multimodal techniques, alpha-blending of bright-field and dark-field images, enhancement of nuclei, and removal of positions extracted in sinusoidal areas, were employed. Experiments for nuclear position extraction and contour extraction were carried out. The best results were obtained when all the multimodal techniques were employed, showing the effectiveness of the method.

KW - Dark-field

KW - Hepatocellular carcinoma

KW - Histology

KW - Multimodal

KW - Nucleus

UR - http://www.scopus.com/inward/record.url?scp=84876046206&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876046206&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-29305-4_243

DO - 10.1007/978-3-642-29305-4_243

M3 - Conference contribution

SN - 9783642293047

VL - 39 IFMBE

SP - 927

EP - 930

BT - IFMBE Proceedings

ER -