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 publicationWorld Congress on Medical Physics and Biomedical Engineering
Pages927-930
Number of pages4
DOIs
Publication statusPublished - 2013 Apr 16
EventWorld Congress on Medical Physics and Biomedical Engineering - Beijing, China
Duration: 2012 May 262012 May 31

Publication series

NameIFMBE Proceedings
Volume39 IFMBE
ISSN (Print)1680-0737

Conference

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

Keywords

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

ASJC Scopus subject areas

  • Bioengineering
  • Biomedical Engineering

Fingerprint Dive into the research topics of 'Multimodal method for extracting nuclei in hepatic histological images'. Together they form a unique fingerprint.

  • Cite this

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