Computational hepatocellular carcinoma tumor grading based on cell nuclei classification

Chamidu Atupelage, Hiroshi Nagahashi, Fumikazu Kimura, Masahiro Yamaguchi, Abe Tokiya, Akinori Hashiguchi, Michiie Sakamoto

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Hepatocellular carcinoma (HCC) is the most common histological type of primary liver cancer. HCC is graded according to the malignancy of the tissues. It is important to diagnose low-grade HCC tumors because these tissues have good prognosis. Image interpretation-based computer-aided diagnosis (CAD) systems have been developed to automate the HCC grading process. Generally, the HCC grade is determined by the characteristics of liver cell nuclei. Therefore, it is preferable that CAD systems utilize only liver cell nuclei for HCC grading. This paper proposes an automated HCC diagnosing method. In particular, it defines a pipeline-path that excludes nonliver cell nuclei in two consequent pipeline-modules and utilizes the liver cell nuclear features for HCC grading. The significance of excluding the nonliver cell nuclei for HCC grading is experimentally evaluated. Four categories of liver cell nuclear features were utilized for classifying the HCC tumors. Results indicated that nuclear texture is the dominant feature for HCC grading and others contribute to increase the classification accuracy. The proposed method was employed to classify a set of regions of interest selected from HCC whole slide images into five classes and resulted in a 95.97% correct classification rate.

Original languageEnglish
Article number034501
JournalJournal of Medical Imaging
Volume1
Issue number3
DOIs
Publication statusPublished - 2014 Oct 1

Fingerprint

Neoplasm Grading
Cell Nucleus
Liver
Tumors
Hepatocellular Carcinoma
Cells
Computer aided diagnosis
Pipelines
Tissue
Textures
Neoplasms
Liver Neoplasms

Keywords

  • cancer grading
  • classification
  • hepatocellular carcinoma histological images
  • multifractal computation
  • multifractal measures
  • segmentation
  • textural feature descriptor

ASJC Scopus subject areas

  • Bioengineering
  • Radiology Nuclear Medicine and imaging

Cite this

Computational hepatocellular carcinoma tumor grading based on cell nuclei classification. / Atupelage, Chamidu; Nagahashi, Hiroshi; Kimura, Fumikazu; Yamaguchi, Masahiro; Tokiya, Abe; Hashiguchi, Akinori; Sakamoto, Michiie.

In: Journal of Medical Imaging, Vol. 1, No. 3, 034501, 01.10.2014.

Research output: Contribution to journalArticle

Atupelage, Chamidu ; Nagahashi, Hiroshi ; Kimura, Fumikazu ; Yamaguchi, Masahiro ; Tokiya, Abe ; Hashiguchi, Akinori ; Sakamoto, Michiie. / Computational hepatocellular carcinoma tumor grading based on cell nuclei classification. In: Journal of Medical Imaging. 2014 ; Vol. 1, No. 3.
@article{2cf204e539bb4f6ca70989168a5f6849,
title = "Computational hepatocellular carcinoma tumor grading based on cell nuclei classification",
abstract = "Hepatocellular carcinoma (HCC) is the most common histological type of primary liver cancer. HCC is graded according to the malignancy of the tissues. It is important to diagnose low-grade HCC tumors because these tissues have good prognosis. Image interpretation-based computer-aided diagnosis (CAD) systems have been developed to automate the HCC grading process. Generally, the HCC grade is determined by the characteristics of liver cell nuclei. Therefore, it is preferable that CAD systems utilize only liver cell nuclei for HCC grading. This paper proposes an automated HCC diagnosing method. In particular, it defines a pipeline-path that excludes nonliver cell nuclei in two consequent pipeline-modules and utilizes the liver cell nuclear features for HCC grading. The significance of excluding the nonliver cell nuclei for HCC grading is experimentally evaluated. Four categories of liver cell nuclear features were utilized for classifying the HCC tumors. Results indicated that nuclear texture is the dominant feature for HCC grading and others contribute to increase the classification accuracy. The proposed method was employed to classify a set of regions of interest selected from HCC whole slide images into five classes and resulted in a 95.97{\%} correct classification rate.",
keywords = "cancer grading, classification, hepatocellular carcinoma histological images, multifractal computation, multifractal measures, segmentation, textural feature descriptor",
author = "Chamidu Atupelage and Hiroshi Nagahashi and Fumikazu Kimura and Masahiro Yamaguchi and Abe Tokiya and Akinori Hashiguchi and Michiie Sakamoto",
year = "2014",
month = "10",
day = "1",
doi = "10.1117/1.JMI.1.3.034501",
language = "English",
volume = "1",
journal = "Journal of Medical Imaging",
issn = "0720-048X",
publisher = "Elsevier Ireland Ltd",
number = "3",

}

TY - JOUR

T1 - Computational hepatocellular carcinoma tumor grading based on cell nuclei classification

AU - Atupelage, Chamidu

AU - Nagahashi, Hiroshi

AU - Kimura, Fumikazu

AU - Yamaguchi, Masahiro

AU - Tokiya, Abe

AU - Hashiguchi, Akinori

AU - Sakamoto, Michiie

PY - 2014/10/1

Y1 - 2014/10/1

N2 - Hepatocellular carcinoma (HCC) is the most common histological type of primary liver cancer. HCC is graded according to the malignancy of the tissues. It is important to diagnose low-grade HCC tumors because these tissues have good prognosis. Image interpretation-based computer-aided diagnosis (CAD) systems have been developed to automate the HCC grading process. Generally, the HCC grade is determined by the characteristics of liver cell nuclei. Therefore, it is preferable that CAD systems utilize only liver cell nuclei for HCC grading. This paper proposes an automated HCC diagnosing method. In particular, it defines a pipeline-path that excludes nonliver cell nuclei in two consequent pipeline-modules and utilizes the liver cell nuclear features for HCC grading. The significance of excluding the nonliver cell nuclei for HCC grading is experimentally evaluated. Four categories of liver cell nuclear features were utilized for classifying the HCC tumors. Results indicated that nuclear texture is the dominant feature for HCC grading and others contribute to increase the classification accuracy. The proposed method was employed to classify a set of regions of interest selected from HCC whole slide images into five classes and resulted in a 95.97% correct classification rate.

AB - Hepatocellular carcinoma (HCC) is the most common histological type of primary liver cancer. HCC is graded according to the malignancy of the tissues. It is important to diagnose low-grade HCC tumors because these tissues have good prognosis. Image interpretation-based computer-aided diagnosis (CAD) systems have been developed to automate the HCC grading process. Generally, the HCC grade is determined by the characteristics of liver cell nuclei. Therefore, it is preferable that CAD systems utilize only liver cell nuclei for HCC grading. This paper proposes an automated HCC diagnosing method. In particular, it defines a pipeline-path that excludes nonliver cell nuclei in two consequent pipeline-modules and utilizes the liver cell nuclear features for HCC grading. The significance of excluding the nonliver cell nuclei for HCC grading is experimentally evaluated. Four categories of liver cell nuclear features were utilized for classifying the HCC tumors. Results indicated that nuclear texture is the dominant feature for HCC grading and others contribute to increase the classification accuracy. The proposed method was employed to classify a set of regions of interest selected from HCC whole slide images into five classes and resulted in a 95.97% correct classification rate.

KW - cancer grading

KW - classification

KW - hepatocellular carcinoma histological images

KW - multifractal computation

KW - multifractal measures

KW - segmentation

KW - textural feature descriptor

UR - http://www.scopus.com/inward/record.url?scp=85019275831&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019275831&partnerID=8YFLogxK

U2 - 10.1117/1.JMI.1.3.034501

DO - 10.1117/1.JMI.1.3.034501

M3 - Article

AN - SCOPUS:85019275831

VL - 1

JO - Journal of Medical Imaging

JF - Journal of Medical Imaging

SN - 0720-048X

IS - 3

M1 - 034501

ER -