A hierarchical classifier for multiclass prostate histopathology image gleason grading

Dheeb Albashish, Shahnorbanun Sahran, Azizi Abdullah, Mohammed Alweshah, Afzan Adam

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Automated classification of prostate histopathology images includes the identification of multiple classes, such as benign and cancerous (grades 3 & 4). To address the multiclass classification problem in prostate histopathology images, breakdown approaches are utilized, such as one-versus-one (OVO) and one-versus-all (Ovall). In these approaches, the multiclass problem is decomposed into numerous binary subtasks, which are separately addressed. However, OVALL introduces an artificial class imbalance, which degrades the classification performance, while in the case of OVO, the correlation between different classes not regarded as a multiclass problem is broken into multiple independent binary problems. This paper proposes a new multiclass approach called multi-level (hierarchical) learning architecture (MLA). It addresses the binary classification tasks within the framework of a hierarchical strategy. It does so by accounting for the interaction between several classes and the domain knowledge. The proposed approach relies on the 'divide- and-conquer' principle by allocating each binary task into two separate subtasks; strong and weak, based on the power of the samples in each binary task. Conversely, the strong samples include more information about the considered task, which motivates the production of the final prediction. Experimental results on prostate histopathological images illustrated that the MLA significantly outperforms the Ovall and OVO approaches when applied to the ensemble framework. The results also confirmed the high efficiency of the ensemble framework with the MLA scheme in dealing with the multiclass classification problem.

Original languageEnglish
Pages (from-to)323-346
Number of pages24
JournalJournal of Information and Communication Technology
Volume17
Issue number2
Publication statusPublished - 1 Apr 2018

Fingerprint

Grading
Multi-class
Classifiers
Classifier
Binary
Multi-class Classification
Classification Problems
Ensemble
Binary Classification
Divide and conquer
Domain Knowledge
High Efficiency
Breakdown
Class
Prediction
Experimental Results
Interaction
Framework

Keywords

  • Ensemble classification
  • Hierarchical classification
  • Image classification
  • Multiclasss classification

ASJC Scopus subject areas

  • Computer Science(all)
  • Mathematics(all)

Cite this

A hierarchical classifier for multiclass prostate histopathology image gleason grading. / Albashish, Dheeb; Sahran, Shahnorbanun; Abdullah, Azizi; Alweshah, Mohammed; Adam, Afzan.

In: Journal of Information and Communication Technology, Vol. 17, No. 2, 01.04.2018, p. 323-346.

Research output: Contribution to journalArticle

@article{b11f2e33c3af498cb9ba4c1ee52832c2,
title = "A hierarchical classifier for multiclass prostate histopathology image gleason grading",
abstract = "Automated classification of prostate histopathology images includes the identification of multiple classes, such as benign and cancerous (grades 3 & 4). To address the multiclass classification problem in prostate histopathology images, breakdown approaches are utilized, such as one-versus-one (OVO) and one-versus-all (Ovall). In these approaches, the multiclass problem is decomposed into numerous binary subtasks, which are separately addressed. However, OVALL introduces an artificial class imbalance, which degrades the classification performance, while in the case of OVO, the correlation between different classes not regarded as a multiclass problem is broken into multiple independent binary problems. This paper proposes a new multiclass approach called multi-level (hierarchical) learning architecture (MLA). It addresses the binary classification tasks within the framework of a hierarchical strategy. It does so by accounting for the interaction between several classes and the domain knowledge. The proposed approach relies on the 'divide- and-conquer' principle by allocating each binary task into two separate subtasks; strong and weak, based on the power of the samples in each binary task. Conversely, the strong samples include more information about the considered task, which motivates the production of the final prediction. Experimental results on prostate histopathological images illustrated that the MLA significantly outperforms the Ovall and OVO approaches when applied to the ensemble framework. The results also confirmed the high efficiency of the ensemble framework with the MLA scheme in dealing with the multiclass classification problem.",
keywords = "Ensemble classification, Hierarchical classification, Image classification, Multiclasss classification",
author = "Dheeb Albashish and Shahnorbanun Sahran and Azizi Abdullah and Mohammed Alweshah and Afzan Adam",
year = "2018",
month = "4",
day = "1",
language = "English",
volume = "17",
pages = "323--346",
journal = "Journal of Information and Communication Technology",
issn = "1675-414X",
publisher = "Universiti Utara Malaysia Press",
number = "2",

}

TY - JOUR

T1 - A hierarchical classifier for multiclass prostate histopathology image gleason grading

AU - Albashish, Dheeb

AU - Sahran, Shahnorbanun

AU - Abdullah, Azizi

AU - Alweshah, Mohammed

AU - Adam, Afzan

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Automated classification of prostate histopathology images includes the identification of multiple classes, such as benign and cancerous (grades 3 & 4). To address the multiclass classification problem in prostate histopathology images, breakdown approaches are utilized, such as one-versus-one (OVO) and one-versus-all (Ovall). In these approaches, the multiclass problem is decomposed into numerous binary subtasks, which are separately addressed. However, OVALL introduces an artificial class imbalance, which degrades the classification performance, while in the case of OVO, the correlation between different classes not regarded as a multiclass problem is broken into multiple independent binary problems. This paper proposes a new multiclass approach called multi-level (hierarchical) learning architecture (MLA). It addresses the binary classification tasks within the framework of a hierarchical strategy. It does so by accounting for the interaction between several classes and the domain knowledge. The proposed approach relies on the 'divide- and-conquer' principle by allocating each binary task into two separate subtasks; strong and weak, based on the power of the samples in each binary task. Conversely, the strong samples include more information about the considered task, which motivates the production of the final prediction. Experimental results on prostate histopathological images illustrated that the MLA significantly outperforms the Ovall and OVO approaches when applied to the ensemble framework. The results also confirmed the high efficiency of the ensemble framework with the MLA scheme in dealing with the multiclass classification problem.

AB - Automated classification of prostate histopathology images includes the identification of multiple classes, such as benign and cancerous (grades 3 & 4). To address the multiclass classification problem in prostate histopathology images, breakdown approaches are utilized, such as one-versus-one (OVO) and one-versus-all (Ovall). In these approaches, the multiclass problem is decomposed into numerous binary subtasks, which are separately addressed. However, OVALL introduces an artificial class imbalance, which degrades the classification performance, while in the case of OVO, the correlation between different classes not regarded as a multiclass problem is broken into multiple independent binary problems. This paper proposes a new multiclass approach called multi-level (hierarchical) learning architecture (MLA). It addresses the binary classification tasks within the framework of a hierarchical strategy. It does so by accounting for the interaction between several classes and the domain knowledge. The proposed approach relies on the 'divide- and-conquer' principle by allocating each binary task into two separate subtasks; strong and weak, based on the power of the samples in each binary task. Conversely, the strong samples include more information about the considered task, which motivates the production of the final prediction. Experimental results on prostate histopathological images illustrated that the MLA significantly outperforms the Ovall and OVO approaches when applied to the ensemble framework. The results also confirmed the high efficiency of the ensemble framework with the MLA scheme in dealing with the multiclass classification problem.

KW - Ensemble classification

KW - Hierarchical classification

KW - Image classification

KW - Multiclasss classification

UR - http://www.scopus.com/inward/record.url?scp=85043504076&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85043504076&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85043504076

VL - 17

SP - 323

EP - 346

JO - Journal of Information and Communication Technology

JF - Journal of Information and Communication Technology

SN - 1675-414X

IS - 2

ER -