Automatic malignancy classification of colon tumor by feature analysis of biopsy images

Takatoshi Karino, Toshiyuki Tanaka

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

Abstract

We intend to construct a system to automatically diagnose malignant potential of colon biopsies. First, we classified biopsies components (nuclei, cytoplasm and interstitium) by discriminant analysis method with Mahalanobis's generalized distance and Otsu method twice. Furthermore, only ductal nuclei were sorted out from the other nuclei by using differences of areas and densities of edges, that is high in lymphoid follicles. We proposed a method for quantifying pseudostratified nuclei by a measure of thickness of ductal nuclei and methods for quantifying structural atypia by fractal dimension analysis with Box-counting method and HLAC features. Moreover, poorly and moderately differentiated carcinoma in Group5 was able to be discriminated with high accuracy by density of labeled ranges. With these features, biopsies' images were classified into 4 Groups by support vector machine.

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
Pages1820-1824
Number of pages5
Publication statusPublished - 2013
Event2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013 - Nagoya, Japan
Duration: 2013 Sep 142013 Sep 17

Other

Other2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013
CountryJapan
CityNagoya
Period13/9/1413/9/17

Fingerprint

Biopsy
Tumors
Discriminant analysis
Fractal dimension
Support vector machines

Keywords

  • Biopsy test
  • Cancer
  • Colon
  • Image processing

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications

Cite this

Karino, T., & Tanaka, T. (2013). Automatic malignancy classification of colon tumor by feature analysis of biopsy images. In Proceedings of the SICE Annual Conference (pp. 1820-1824)

Automatic malignancy classification of colon tumor by feature analysis of biopsy images. / Karino, Takatoshi; Tanaka, Toshiyuki.

Proceedings of the SICE Annual Conference. 2013. p. 1820-1824.

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

Karino, T & Tanaka, T 2013, Automatic malignancy classification of colon tumor by feature analysis of biopsy images. in Proceedings of the SICE Annual Conference. pp. 1820-1824, 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013, Nagoya, Japan, 13/9/14.
Karino T, Tanaka T. Automatic malignancy classification of colon tumor by feature analysis of biopsy images. In Proceedings of the SICE Annual Conference. 2013. p. 1820-1824
Karino, Takatoshi ; Tanaka, Toshiyuki. / Automatic malignancy classification of colon tumor by feature analysis of biopsy images. Proceedings of the SICE Annual Conference. 2013. pp. 1820-1824
@inproceedings{144724f4be9746678d65bb0f8ee62eee,
title = "Automatic malignancy classification of colon tumor by feature analysis of biopsy images",
abstract = "We intend to construct a system to automatically diagnose malignant potential of colon biopsies. First, we classified biopsies components (nuclei, cytoplasm and interstitium) by discriminant analysis method with Mahalanobis's generalized distance and Otsu method twice. Furthermore, only ductal nuclei were sorted out from the other nuclei by using differences of areas and densities of edges, that is high in lymphoid follicles. We proposed a method for quantifying pseudostratified nuclei by a measure of thickness of ductal nuclei and methods for quantifying structural atypia by fractal dimension analysis with Box-counting method and HLAC features. Moreover, poorly and moderately differentiated carcinoma in Group5 was able to be discriminated with high accuracy by density of labeled ranges. With these features, biopsies' images were classified into 4 Groups by support vector machine.",
keywords = "Biopsy test, Cancer, Colon, Image processing",
author = "Takatoshi Karino and Toshiyuki Tanaka",
year = "2013",
language = "English",
pages = "1820--1824",
booktitle = "Proceedings of the SICE Annual Conference",

}

TY - GEN

T1 - Automatic malignancy classification of colon tumor by feature analysis of biopsy images

AU - Karino, Takatoshi

AU - Tanaka, Toshiyuki

PY - 2013

Y1 - 2013

N2 - We intend to construct a system to automatically diagnose malignant potential of colon biopsies. First, we classified biopsies components (nuclei, cytoplasm and interstitium) by discriminant analysis method with Mahalanobis's generalized distance and Otsu method twice. Furthermore, only ductal nuclei were sorted out from the other nuclei by using differences of areas and densities of edges, that is high in lymphoid follicles. We proposed a method for quantifying pseudostratified nuclei by a measure of thickness of ductal nuclei and methods for quantifying structural atypia by fractal dimension analysis with Box-counting method and HLAC features. Moreover, poorly and moderately differentiated carcinoma in Group5 was able to be discriminated with high accuracy by density of labeled ranges. With these features, biopsies' images were classified into 4 Groups by support vector machine.

AB - We intend to construct a system to automatically diagnose malignant potential of colon biopsies. First, we classified biopsies components (nuclei, cytoplasm and interstitium) by discriminant analysis method with Mahalanobis's generalized distance and Otsu method twice. Furthermore, only ductal nuclei were sorted out from the other nuclei by using differences of areas and densities of edges, that is high in lymphoid follicles. We proposed a method for quantifying pseudostratified nuclei by a measure of thickness of ductal nuclei and methods for quantifying structural atypia by fractal dimension analysis with Box-counting method and HLAC features. Moreover, poorly and moderately differentiated carcinoma in Group5 was able to be discriminated with high accuracy by density of labeled ranges. With these features, biopsies' images were classified into 4 Groups by support vector machine.

KW - Biopsy test

KW - Cancer

KW - Colon

KW - Image processing

UR - http://www.scopus.com/inward/record.url?scp=84888597173&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84888597173&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84888597173

SP - 1820

EP - 1824

BT - Proceedings of the SICE Annual Conference

ER -