Classification of gastric tumors on gastric biopsy images

Ryo Ohtsuki, Toshiyuki Tanaka

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

Abstract

The well-known Group Classification method for hematoxylin and eojin stained gastric tumors uses morphological features of histology patterns within a tissue slide to classify it into 5 grades from Group1 to Group5. Our approach developed an automated classification method being used for automated Group Classification of gastric tumor images. We have demonstrate the performance of the proposed method for a three class classification ± Group1 (benign), Group3 (gastric adenoma), Group5 (gastric cancer) ± on a 90 teaching dataset and 90 test dataset using Support Vector Machine and achieved accuracy of 75.6% on Group1, 64.4% on Group3, and 95.6% on Group5. Our approach combines the morphological features such as nuclear-cytoplasmic ratio, some texture features, and HLAC (higher order local autocorrelation).

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
Pages2502-2506
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
Histology
Autocorrelation
Support vector machines
Teaching
Textures
Tissue

Keywords

  • Automated classification
  • Digital pathology
  • Gastric biopsy
  • Image processing

ASJC Scopus subject areas

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

Cite this

Ohtsuki, R., & Tanaka, T. (2013). Classification of gastric tumors on gastric biopsy images. In Proceedings of the SICE Annual Conference (pp. 2502-2506)

Classification of gastric tumors on gastric biopsy images. / Ohtsuki, Ryo; Tanaka, Toshiyuki.

Proceedings of the SICE Annual Conference. 2013. p. 2502-2506.

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

Ohtsuki, R & Tanaka, T 2013, Classification of gastric tumors on gastric biopsy images. in Proceedings of the SICE Annual Conference. pp. 2502-2506, 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013, Nagoya, Japan, 13/9/14.
Ohtsuki R, Tanaka T. Classification of gastric tumors on gastric biopsy images. In Proceedings of the SICE Annual Conference. 2013. p. 2502-2506
Ohtsuki, Ryo ; Tanaka, Toshiyuki. / Classification of gastric tumors on gastric biopsy images. Proceedings of the SICE Annual Conference. 2013. pp. 2502-2506
@inproceedings{c4af7840e40542aa9d171c59c540d682,
title = "Classification of gastric tumors on gastric biopsy images",
abstract = "The well-known Group Classification method for hematoxylin and eojin stained gastric tumors uses morphological features of histology patterns within a tissue slide to classify it into 5 grades from Group1 to Group5. Our approach developed an automated classification method being used for automated Group Classification of gastric tumor images. We have demonstrate the performance of the proposed method for a three class classification ± Group1 (benign), Group3 (gastric adenoma), Group5 (gastric cancer) ± on a 90 teaching dataset and 90 test dataset using Support Vector Machine and achieved accuracy of 75.6{\%} on Group1, 64.4{\%} on Group3, and 95.6{\%} on Group5. Our approach combines the morphological features such as nuclear-cytoplasmic ratio, some texture features, and HLAC (higher order local autocorrelation).",
keywords = "Automated classification, Digital pathology, Gastric biopsy, Image processing",
author = "Ryo Ohtsuki and Toshiyuki Tanaka",
year = "2013",
language = "English",
pages = "2502--2506",
booktitle = "Proceedings of the SICE Annual Conference",

}

TY - GEN

T1 - Classification of gastric tumors on gastric biopsy images

AU - Ohtsuki, Ryo

AU - Tanaka, Toshiyuki

PY - 2013

Y1 - 2013

N2 - The well-known Group Classification method for hematoxylin and eojin stained gastric tumors uses morphological features of histology patterns within a tissue slide to classify it into 5 grades from Group1 to Group5. Our approach developed an automated classification method being used for automated Group Classification of gastric tumor images. We have demonstrate the performance of the proposed method for a three class classification ± Group1 (benign), Group3 (gastric adenoma), Group5 (gastric cancer) ± on a 90 teaching dataset and 90 test dataset using Support Vector Machine and achieved accuracy of 75.6% on Group1, 64.4% on Group3, and 95.6% on Group5. Our approach combines the morphological features such as nuclear-cytoplasmic ratio, some texture features, and HLAC (higher order local autocorrelation).

AB - The well-known Group Classification method for hematoxylin and eojin stained gastric tumors uses morphological features of histology patterns within a tissue slide to classify it into 5 grades from Group1 to Group5. Our approach developed an automated classification method being used for automated Group Classification of gastric tumor images. We have demonstrate the performance of the proposed method for a three class classification ± Group1 (benign), Group3 (gastric adenoma), Group5 (gastric cancer) ± on a 90 teaching dataset and 90 test dataset using Support Vector Machine and achieved accuracy of 75.6% on Group1, 64.4% on Group3, and 95.6% on Group5. Our approach combines the morphological features such as nuclear-cytoplasmic ratio, some texture features, and HLAC (higher order local autocorrelation).

KW - Automated classification

KW - Digital pathology

KW - Gastric biopsy

KW - Image processing

UR - http://www.scopus.com/inward/record.url?scp=84888607937&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84888607937&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84888607937

SP - 2502

EP - 2506

BT - Proceedings of the SICE Annual Conference

ER -