Ensemble learning of tissue components for prostate histopathology image grading

Dheeb Albashish, Shahnorbanun Sahran, Azizi Abdullah, Nordashima Abd Shukor, Suria Hayati Md Pauzi

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Ensemble learning is an effective machine learning approach to improve the prediction performance by fusing several single classifier models. In computer-aided diagnosis system (CAD), machine learning has become one of the dominant solutions for tissue images diagnosis and grading. One problem in a single classifier model for multi-components of the tissue images combination to construct dense feature vectors is the overfitting. In this paper, an ensemble learning for multi-component tissue images classification approach is proposed. The prostate cancer Hematoxylin and Eosin (H&E) histopathology images from HUKM were used to test the proposed ensemble approach for diagnosing and Gleason grading. The experiments results of several prostate classification tasks, namely, benign vs. Grade 3, benign vs.Grade4, and Grade 3vs.Grade 4 show that the proposed ensemble significantly outperforms the previous typical CAD and the naïve approach that combines the texture features of all tissue component directly in dense feature vectors for a classifier.

Original languageEnglish
Pages (from-to)1134-1140
Number of pages7
JournalInternational Journal on Advanced Science, Engineering and Information Technology
Volume6
Issue number6
DOIs
Publication statusPublished - 2016

Fingerprint

histopathology
Prostate
learning
Learning
Tissue
Computer aided diagnosis
Classifiers
artificial intelligence
Learning systems
Neoplasm Grading
Image classification
prostatic neoplasms
Hematoxylin
Eosine Yellowish-(YS)
Prostatic Neoplasms
Textures
texture
prediction
tissues
Experiments

Keywords

  • Ensemble machine learning
  • Naïve approach
  • Prostate cancer histological image
  • Tissue components
  • Typical CAD system

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Computer Science(all)
  • Engineering(all)

Cite this

@article{ec96c28807324608ad56cb6c03444348,
title = "Ensemble learning of tissue components for prostate histopathology image grading",
abstract = "Ensemble learning is an effective machine learning approach to improve the prediction performance by fusing several single classifier models. In computer-aided diagnosis system (CAD), machine learning has become one of the dominant solutions for tissue images diagnosis and grading. One problem in a single classifier model for multi-components of the tissue images combination to construct dense feature vectors is the overfitting. In this paper, an ensemble learning for multi-component tissue images classification approach is proposed. The prostate cancer Hematoxylin and Eosin (H&E) histopathology images from HUKM were used to test the proposed ensemble approach for diagnosing and Gleason grading. The experiments results of several prostate classification tasks, namely, benign vs. Grade 3, benign vs.Grade4, and Grade 3vs.Grade 4 show that the proposed ensemble significantly outperforms the previous typical CAD and the na{\"i}ve approach that combines the texture features of all tissue component directly in dense feature vectors for a classifier.",
keywords = "Ensemble machine learning, Na{\"i}ve approach, Prostate cancer histological image, Tissue components, Typical CAD system",
author = "Dheeb Albashish and Shahnorbanun Sahran and Azizi Abdullah and Shukor, {Nordashima Abd} and {Md Pauzi}, {Suria Hayati}",
year = "2016",
doi = "10.18517/ijaseit.6.6.1489",
language = "English",
volume = "6",
pages = "1134--1140",
journal = "International Journal on Advanced Science, Engineering and Information Technology",
issn = "2088-5334",
publisher = "INSIGHT - Indonesian Society for Knowledge and Human Development",
number = "6",

}

TY - JOUR

T1 - Ensemble learning of tissue components for prostate histopathology image grading

AU - Albashish, Dheeb

AU - Sahran, Shahnorbanun

AU - Abdullah, Azizi

AU - Shukor, Nordashima Abd

AU - Md Pauzi, Suria Hayati

PY - 2016

Y1 - 2016

N2 - Ensemble learning is an effective machine learning approach to improve the prediction performance by fusing several single classifier models. In computer-aided diagnosis system (CAD), machine learning has become one of the dominant solutions for tissue images diagnosis and grading. One problem in a single classifier model for multi-components of the tissue images combination to construct dense feature vectors is the overfitting. In this paper, an ensemble learning for multi-component tissue images classification approach is proposed. The prostate cancer Hematoxylin and Eosin (H&E) histopathology images from HUKM were used to test the proposed ensemble approach for diagnosing and Gleason grading. The experiments results of several prostate classification tasks, namely, benign vs. Grade 3, benign vs.Grade4, and Grade 3vs.Grade 4 show that the proposed ensemble significantly outperforms the previous typical CAD and the naïve approach that combines the texture features of all tissue component directly in dense feature vectors for a classifier.

AB - Ensemble learning is an effective machine learning approach to improve the prediction performance by fusing several single classifier models. In computer-aided diagnosis system (CAD), machine learning has become one of the dominant solutions for tissue images diagnosis and grading. One problem in a single classifier model for multi-components of the tissue images combination to construct dense feature vectors is the overfitting. In this paper, an ensemble learning for multi-component tissue images classification approach is proposed. The prostate cancer Hematoxylin and Eosin (H&E) histopathology images from HUKM were used to test the proposed ensemble approach for diagnosing and Gleason grading. The experiments results of several prostate classification tasks, namely, benign vs. Grade 3, benign vs.Grade4, and Grade 3vs.Grade 4 show that the proposed ensemble significantly outperforms the previous typical CAD and the naïve approach that combines the texture features of all tissue component directly in dense feature vectors for a classifier.

KW - Ensemble machine learning

KW - Naïve approach

KW - Prostate cancer histological image

KW - Tissue components

KW - Typical CAD system

UR - http://www.scopus.com/inward/record.url?scp=85010192507&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85010192507&partnerID=8YFLogxK

U2 - 10.18517/ijaseit.6.6.1489

DO - 10.18517/ijaseit.6.6.1489

M3 - Article

AN - SCOPUS:85010192507

VL - 6

SP - 1134

EP - 1140

JO - International Journal on Advanced Science, Engineering and Information Technology

JF - International Journal on Advanced Science, Engineering and Information Technology

SN - 2088-5334

IS - 6

ER -