Colorectal cancer image classification using image pre-processing and multilayer Perceptron

Mohd Yamin Ahmad, Azlinah Mohamed, Yasmin Anum Mohd Yusof, Siti Aishah Siti

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

Abstract

Manual screening of colorectal biopsy tissue under microscope to conform the presence of cancerous cell is difficult and time consuming. The criteria in diagnosing colorectal cancer cell are gland shape and nucleus size. In this paper, we proposed a method of automatic image pre-processing to extract important feature of colorectal tissue images. Images captured under microscope may vary in color brightness due to different staining concentration and the size of biopsy tissue. In this paper we proposed a method using HSV color to remove element outside the area of nucleus. In order to extract the gland shape, we proposed a gland tracking boundary and segmentation. By using the result of gland tracking, nucleus size that forms the glands are measured. Multilayer Perceptron is being used to detect the shape of glands. By combining result of gland shape and nucleus size, we perform the image classification. The result shows that classification achieves 94% accuracy by using the proposed methods.

Original languageEnglish
Title of host publication2012 International Conference on Computer and Information Science, ICCIS 2012 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2012 - Conference Proceedings
Pages275-280
Number of pages6
Volume1
DOIs
Publication statusPublished - 2012
Event2012 International Conference on Computer and Information Science, ICCIS 2012 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2012 - Kuala Lumpur
Duration: 12 Jun 201214 Jun 2012

Other

Other2012 International Conference on Computer and Information Science, ICCIS 2012 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2012
CityKuala Lumpur
Period12/6/1214/6/12

Fingerprint

Cancer Classification
Colorectal Cancer
Image classification
Image Classification
Multilayer neural networks
Perceptron
Nucleus
Preprocessing
Multilayer
Biopsy
Tissue
Microscopes
Processing
Microscope
Color
Luminance
Cell
Screening
Brightness
Cells

Keywords

  • Color Removal
  • Gland Tracking
  • HSV
  • Image processing
  • Multilayer Perceptron
  • Neural Network
  • Pattern Recognition

ASJC Scopus subject areas

  • Information Systems
  • Theoretical Computer Science

Cite this

Ahmad, M. Y., Mohamed, A., Mohd Yusof, Y. A., & Siti, S. A. (2012). Colorectal cancer image classification using image pre-processing and multilayer Perceptron. In 2012 International Conference on Computer and Information Science, ICCIS 2012 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2012 - Conference Proceedings (Vol. 1, pp. 275-280). [6297253] https://doi.org/10.1109/ICCISci.2012.6297253

Colorectal cancer image classification using image pre-processing and multilayer Perceptron. / Ahmad, Mohd Yamin; Mohamed, Azlinah; Mohd Yusof, Yasmin Anum; Siti, Siti Aishah.

2012 International Conference on Computer and Information Science, ICCIS 2012 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2012 - Conference Proceedings. Vol. 1 2012. p. 275-280 6297253.

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

Ahmad, MY, Mohamed, A, Mohd Yusof, YA & Siti, SA 2012, Colorectal cancer image classification using image pre-processing and multilayer Perceptron. in 2012 International Conference on Computer and Information Science, ICCIS 2012 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2012 - Conference Proceedings. vol. 1, 6297253, pp. 275-280, 2012 International Conference on Computer and Information Science, ICCIS 2012 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2012, Kuala Lumpur, 12/6/12. https://doi.org/10.1109/ICCISci.2012.6297253
Ahmad MY, Mohamed A, Mohd Yusof YA, Siti SA. Colorectal cancer image classification using image pre-processing and multilayer Perceptron. In 2012 International Conference on Computer and Information Science, ICCIS 2012 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2012 - Conference Proceedings. Vol. 1. 2012. p. 275-280. 6297253 https://doi.org/10.1109/ICCISci.2012.6297253
Ahmad, Mohd Yamin ; Mohamed, Azlinah ; Mohd Yusof, Yasmin Anum ; Siti, Siti Aishah. / Colorectal cancer image classification using image pre-processing and multilayer Perceptron. 2012 International Conference on Computer and Information Science, ICCIS 2012 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2012 - Conference Proceedings. Vol. 1 2012. pp. 275-280
@inproceedings{c93d052ef55c46e2ad081b8273644353,
title = "Colorectal cancer image classification using image pre-processing and multilayer Perceptron",
abstract = "Manual screening of colorectal biopsy tissue under microscope to conform the presence of cancerous cell is difficult and time consuming. The criteria in diagnosing colorectal cancer cell are gland shape and nucleus size. In this paper, we proposed a method of automatic image pre-processing to extract important feature of colorectal tissue images. Images captured under microscope may vary in color brightness due to different staining concentration and the size of biopsy tissue. In this paper we proposed a method using HSV color to remove element outside the area of nucleus. In order to extract the gland shape, we proposed a gland tracking boundary and segmentation. By using the result of gland tracking, nucleus size that forms the glands are measured. Multilayer Perceptron is being used to detect the shape of glands. By combining result of gland shape and nucleus size, we perform the image classification. The result shows that classification achieves 94{\%} accuracy by using the proposed methods.",
keywords = "Color Removal, Gland Tracking, HSV, Image processing, Multilayer Perceptron, Neural Network, Pattern Recognition",
author = "Ahmad, {Mohd Yamin} and Azlinah Mohamed and {Mohd Yusof}, {Yasmin Anum} and Siti, {Siti Aishah}",
year = "2012",
doi = "10.1109/ICCISci.2012.6297253",
language = "English",
isbn = "9781467319386",
volume = "1",
pages = "275--280",
booktitle = "2012 International Conference on Computer and Information Science, ICCIS 2012 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2012 - Conference Proceedings",

}

TY - GEN

T1 - Colorectal cancer image classification using image pre-processing and multilayer Perceptron

AU - Ahmad, Mohd Yamin

AU - Mohamed, Azlinah

AU - Mohd Yusof, Yasmin Anum

AU - Siti, Siti Aishah

PY - 2012

Y1 - 2012

N2 - Manual screening of colorectal biopsy tissue under microscope to conform the presence of cancerous cell is difficult and time consuming. The criteria in diagnosing colorectal cancer cell are gland shape and nucleus size. In this paper, we proposed a method of automatic image pre-processing to extract important feature of colorectal tissue images. Images captured under microscope may vary in color brightness due to different staining concentration and the size of biopsy tissue. In this paper we proposed a method using HSV color to remove element outside the area of nucleus. In order to extract the gland shape, we proposed a gland tracking boundary and segmentation. By using the result of gland tracking, nucleus size that forms the glands are measured. Multilayer Perceptron is being used to detect the shape of glands. By combining result of gland shape and nucleus size, we perform the image classification. The result shows that classification achieves 94% accuracy by using the proposed methods.

AB - Manual screening of colorectal biopsy tissue under microscope to conform the presence of cancerous cell is difficult and time consuming. The criteria in diagnosing colorectal cancer cell are gland shape and nucleus size. In this paper, we proposed a method of automatic image pre-processing to extract important feature of colorectal tissue images. Images captured under microscope may vary in color brightness due to different staining concentration and the size of biopsy tissue. In this paper we proposed a method using HSV color to remove element outside the area of nucleus. In order to extract the gland shape, we proposed a gland tracking boundary and segmentation. By using the result of gland tracking, nucleus size that forms the glands are measured. Multilayer Perceptron is being used to detect the shape of glands. By combining result of gland shape and nucleus size, we perform the image classification. The result shows that classification achieves 94% accuracy by using the proposed methods.

KW - Color Removal

KW - Gland Tracking

KW - HSV

KW - Image processing

KW - Multilayer Perceptron

KW - Neural Network

KW - Pattern Recognition

UR - http://www.scopus.com/inward/record.url?scp=84867908199&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867908199&partnerID=8YFLogxK

U2 - 10.1109/ICCISci.2012.6297253

DO - 10.1109/ICCISci.2012.6297253

M3 - Conference contribution

AN - SCOPUS:84867908199

SN - 9781467319386

VL - 1

SP - 275

EP - 280

BT - 2012 International Conference on Computer and Information Science, ICCIS 2012 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2012 - Conference Proceedings

ER -