An accurate method of extracting fat droplets in liver images for quantitative evaluation

Masahiro Ishikawa, Naoki Kobayashi, Hideki Komagata, Kazuma Shinoda, Masahiro Yamaguchi, Tokiya Abe, Akinori Hashiguchi, Michiie Sakamoto

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

2 Citations (Scopus)

Abstract

The steatosis in liver pathological tissue images is a promising indicator of nonalcoholic fatty liver disease (NAFLD) and the possible risk of hepatocellular carcinoma (HCC). The resulting values are also important for ensuring the automatic and accurate classification of HCC images, because the existence of many fat droplets is likely to create errors in quantifying the morphological features used in the process. In this study we propose a method that can automatically detect, and exclude regions with many fat droplets by using the feature values of colors, shapes and the arrangement of cell nuclei. We implement the method and confirm that it can accurately detect fat droplets and quantify the fat droplet ratio of actual images. This investigation also clarifies the effective characteristics that contribute to accurate detection.

Original languageEnglish
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
PublisherSPIE
Volume9420
ISBN (Print)9781628415100
DOIs
Publication statusPublished - 2015
EventMedical Imaging 2015: Digital Pathology - Orlando, United States
Duration: 2015 Feb 252015 Feb 26

Other

OtherMedical Imaging 2015: Digital Pathology
CountryUnited States
CityOrlando
Period15/2/2515/2/26

Fingerprint

fats
Oils and fats
liver
Liver
Fats
evaluation
Cell Nucleus Shape
Hepatocellular Carcinoma
cancer
Fatty Liver
Color
Cells
Tissue
color
nuclei

Keywords

  • Extract of fat droplets
  • Histopathological tissue images
  • Quantification

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Ishikawa, M., Kobayashi, N., Komagata, H., Shinoda, K., Yamaguchi, M., Abe, T., ... Sakamoto, M. (2015). An accurate method of extracting fat droplets in liver images for quantitative evaluation. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 9420). [94200Y] SPIE. https://doi.org/10.1117/12.2081670

An accurate method of extracting fat droplets in liver images for quantitative evaluation. / Ishikawa, Masahiro; Kobayashi, Naoki; Komagata, Hideki; Shinoda, Kazuma; Yamaguchi, Masahiro; Abe, Tokiya; Hashiguchi, Akinori; Sakamoto, Michiie.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9420 SPIE, 2015. 94200Y.

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

Ishikawa, M, Kobayashi, N, Komagata, H, Shinoda, K, Yamaguchi, M, Abe, T, Hashiguchi, A & Sakamoto, M 2015, An accurate method of extracting fat droplets in liver images for quantitative evaluation. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 9420, 94200Y, SPIE, Medical Imaging 2015: Digital Pathology, Orlando, United States, 15/2/25. https://doi.org/10.1117/12.2081670
Ishikawa M, Kobayashi N, Komagata H, Shinoda K, Yamaguchi M, Abe T et al. An accurate method of extracting fat droplets in liver images for quantitative evaluation. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9420. SPIE. 2015. 94200Y https://doi.org/10.1117/12.2081670
Ishikawa, Masahiro ; Kobayashi, Naoki ; Komagata, Hideki ; Shinoda, Kazuma ; Yamaguchi, Masahiro ; Abe, Tokiya ; Hashiguchi, Akinori ; Sakamoto, Michiie. / An accurate method of extracting fat droplets in liver images for quantitative evaluation. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9420 SPIE, 2015.
@inproceedings{72f075a1ad2a43c7af20f64a404d9d1e,
title = "An accurate method of extracting fat droplets in liver images for quantitative evaluation",
abstract = "The steatosis in liver pathological tissue images is a promising indicator of nonalcoholic fatty liver disease (NAFLD) and the possible risk of hepatocellular carcinoma (HCC). The resulting values are also important for ensuring the automatic and accurate classification of HCC images, because the existence of many fat droplets is likely to create errors in quantifying the morphological features used in the process. In this study we propose a method that can automatically detect, and exclude regions with many fat droplets by using the feature values of colors, shapes and the arrangement of cell nuclei. We implement the method and confirm that it can accurately detect fat droplets and quantify the fat droplet ratio of actual images. This investigation also clarifies the effective characteristics that contribute to accurate detection.",
keywords = "Extract of fat droplets, Histopathological tissue images, Quantification",
author = "Masahiro Ishikawa and Naoki Kobayashi and Hideki Komagata and Kazuma Shinoda and Masahiro Yamaguchi and Tokiya Abe and Akinori Hashiguchi and Michiie Sakamoto",
year = "2015",
doi = "10.1117/12.2081670",
language = "English",
isbn = "9781628415100",
volume = "9420",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",

}

TY - GEN

T1 - An accurate method of extracting fat droplets in liver images for quantitative evaluation

AU - Ishikawa, Masahiro

AU - Kobayashi, Naoki

AU - Komagata, Hideki

AU - Shinoda, Kazuma

AU - Yamaguchi, Masahiro

AU - Abe, Tokiya

AU - Hashiguchi, Akinori

AU - Sakamoto, Michiie

PY - 2015

Y1 - 2015

N2 - The steatosis in liver pathological tissue images is a promising indicator of nonalcoholic fatty liver disease (NAFLD) and the possible risk of hepatocellular carcinoma (HCC). The resulting values are also important for ensuring the automatic and accurate classification of HCC images, because the existence of many fat droplets is likely to create errors in quantifying the morphological features used in the process. In this study we propose a method that can automatically detect, and exclude regions with many fat droplets by using the feature values of colors, shapes and the arrangement of cell nuclei. We implement the method and confirm that it can accurately detect fat droplets and quantify the fat droplet ratio of actual images. This investigation also clarifies the effective characteristics that contribute to accurate detection.

AB - The steatosis in liver pathological tissue images is a promising indicator of nonalcoholic fatty liver disease (NAFLD) and the possible risk of hepatocellular carcinoma (HCC). The resulting values are also important for ensuring the automatic and accurate classification of HCC images, because the existence of many fat droplets is likely to create errors in quantifying the morphological features used in the process. In this study we propose a method that can automatically detect, and exclude regions with many fat droplets by using the feature values of colors, shapes and the arrangement of cell nuclei. We implement the method and confirm that it can accurately detect fat droplets and quantify the fat droplet ratio of actual images. This investigation also clarifies the effective characteristics that contribute to accurate detection.

KW - Extract of fat droplets

KW - Histopathological tissue images

KW - Quantification

UR - http://www.scopus.com/inward/record.url?scp=84932083777&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84932083777&partnerID=8YFLogxK

U2 - 10.1117/12.2081670

DO - 10.1117/12.2081670

M3 - Conference contribution

SN - 9781628415100

VL - 9420

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

PB - SPIE

ER -