Precise segmentation of nuclei in hepatic histological images

Tomofumi Fujii, Masanobu Takahashi, Kousuke Yamada, Masayuki Nakano

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

Abstract

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. In the system, the contours of a nucleus are extracted as a collection of discrete contour points which are converted to a spline curve by interpolating them. The user can correct wrong contours by moving the contour points using a mouse. So, the number of contour points is limited to a small number, usually eight, in order to reduce the time for contour correction. As a result, it was difficult to precisely express the shape of nuclear contours especially in deformed nuclei. In order to solve this problem, new process to improve the contours was introduced. After the contour correction using the GUI, the contours were improved using 80 contour points. An energy function including four energy terms, the energies of the image, the distance between contour points, the curvature, and the color differences, was used. Experimental results showed this process is effective for all the three types of contours, normal round-shaped, deformed, and vague contours. The average absolute error of contour positions was reduced to about 1/3 of the conventional error. As a result, the average absolute error of nuclear areas was reduced to about 1/10, which corresponds to 0.50% of the average nuclear area. The error of roundness factors was also improved. This new process is totally automatic, which means no additional manpower is required.

Original languageEnglish
Title of host publicationIFMBE Proceedings
Pages880-883
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

Graphical user interfaces
Splines
Color

Keywords

  • Contour
  • Hepatocellular carcinoma
  • Histology
  • Image
  • Nucleus

ASJC Scopus subject areas

  • Biomedical Engineering
  • Bioengineering

Cite this

Fujii, T., Takahashi, M., Yamada, K., & Nakano, M. (2013). Precise segmentation of nuclei in hepatic histological images. In IFMBE Proceedings (Vol. 39 IFMBE, pp. 880-883) https://doi.org/10.1007/978-3-642-29305-4_231

Precise segmentation of nuclei in hepatic histological images. / Fujii, Tomofumi; Takahashi, Masanobu; Yamada, Kousuke; Nakano, Masayuki.

IFMBE Proceedings. Vol. 39 IFMBE 2013. p. 880-883.

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

Fujii, T, Takahashi, M, Yamada, K & Nakano, M 2013, Precise segmentation of nuclei in hepatic histological images. in IFMBE Proceedings. vol. 39 IFMBE, pp. 880-883, World Congress on Medical Physics and Biomedical Engineering, Beijing, 12/5/26. https://doi.org/10.1007/978-3-642-29305-4_231
Fujii T, Takahashi M, Yamada K, Nakano M. Precise segmentation of nuclei in hepatic histological images. In IFMBE Proceedings. Vol. 39 IFMBE. 2013. p. 880-883 https://doi.org/10.1007/978-3-642-29305-4_231
Fujii, Tomofumi ; Takahashi, Masanobu ; Yamada, Kousuke ; Nakano, Masayuki. / Precise segmentation of nuclei in hepatic histological images. IFMBE Proceedings. Vol. 39 IFMBE 2013. pp. 880-883
@inproceedings{da2537d251d54fd4ad9e2960d7781f5f,
title = "Precise segmentation of nuclei in hepatic histological images",
abstract = "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. In the system, the contours of a nucleus are extracted as a collection of discrete contour points which are converted to a spline curve by interpolating them. The user can correct wrong contours by moving the contour points using a mouse. So, the number of contour points is limited to a small number, usually eight, in order to reduce the time for contour correction. As a result, it was difficult to precisely express the shape of nuclear contours especially in deformed nuclei. In order to solve this problem, new process to improve the contours was introduced. After the contour correction using the GUI, the contours were improved using 80 contour points. An energy function including four energy terms, the energies of the image, the distance between contour points, the curvature, and the color differences, was used. Experimental results showed this process is effective for all the three types of contours, normal round-shaped, deformed, and vague contours. The average absolute error of contour positions was reduced to about 1/3 of the conventional error. As a result, the average absolute error of nuclear areas was reduced to about 1/10, which corresponds to 0.50{\%} of the average nuclear area. The error of roundness factors was also improved. This new process is totally automatic, which means no additional manpower is required.",
keywords = "Contour, Hepatocellular carcinoma, Histology, Image, Nucleus",
author = "Tomofumi Fujii and Masanobu Takahashi and Kousuke Yamada and Masayuki Nakano",
year = "2013",
doi = "10.1007/978-3-642-29305-4_231",
language = "English",
isbn = "9783642293047",
volume = "39 IFMBE",
pages = "880--883",
booktitle = "IFMBE Proceedings",

}

TY - GEN

T1 - Precise segmentation of nuclei in hepatic histological images

AU - Fujii, Tomofumi

AU - Takahashi, Masanobu

AU - Yamada, Kousuke

AU - Nakano, Masayuki

PY - 2013

Y1 - 2013

N2 - 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. In the system, the contours of a nucleus are extracted as a collection of discrete contour points which are converted to a spline curve by interpolating them. The user can correct wrong contours by moving the contour points using a mouse. So, the number of contour points is limited to a small number, usually eight, in order to reduce the time for contour correction. As a result, it was difficult to precisely express the shape of nuclear contours especially in deformed nuclei. In order to solve this problem, new process to improve the contours was introduced. After the contour correction using the GUI, the contours were improved using 80 contour points. An energy function including four energy terms, the energies of the image, the distance between contour points, the curvature, and the color differences, was used. Experimental results showed this process is effective for all the three types of contours, normal round-shaped, deformed, and vague contours. The average absolute error of contour positions was reduced to about 1/3 of the conventional error. As a result, the average absolute error of nuclear areas was reduced to about 1/10, which corresponds to 0.50% of the average nuclear area. The error of roundness factors was also improved. This new process is totally automatic, which means no additional manpower is required.

AB - 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. In the system, the contours of a nucleus are extracted as a collection of discrete contour points which are converted to a spline curve by interpolating them. The user can correct wrong contours by moving the contour points using a mouse. So, the number of contour points is limited to a small number, usually eight, in order to reduce the time for contour correction. As a result, it was difficult to precisely express the shape of nuclear contours especially in deformed nuclei. In order to solve this problem, new process to improve the contours was introduced. After the contour correction using the GUI, the contours were improved using 80 contour points. An energy function including four energy terms, the energies of the image, the distance between contour points, the curvature, and the color differences, was used. Experimental results showed this process is effective for all the three types of contours, normal round-shaped, deformed, and vague contours. The average absolute error of contour positions was reduced to about 1/3 of the conventional error. As a result, the average absolute error of nuclear areas was reduced to about 1/10, which corresponds to 0.50% of the average nuclear area. The error of roundness factors was also improved. This new process is totally automatic, which means no additional manpower is required.

KW - Contour

KW - Hepatocellular carcinoma

KW - Histology

KW - Image

KW - Nucleus

UR - http://www.scopus.com/inward/record.url?scp=84876044970&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876044970&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-29305-4_231

DO - 10.1007/978-3-642-29305-4_231

M3 - Conference contribution

SN - 9783642293047

VL - 39 IFMBE

SP - 880

EP - 883

BT - IFMBE Proceedings

ER -