Absolute cosine-based SVM-RFE feature selection method for prostate histopathological grading

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

Research output: Contribution to journalArticle

Abstract

Objective: Feature selection (FS) methods are widely used in grading and diagnosing prostate histopathological images. In this context, FS is based on the texture features obtained from the lumen, nuclei, cytoplasm and stroma, all of which are important tissue components. However, it is difficult to represent the high-dimensional textures of these tissue components. To solve this problem, we propose a new FS method that enables the selection of features with minimal redundancy in the tissue components. Methodology: We categorise tissue images based on the texture of individual tissue components via the construction of a single classifier and also construct an ensemble learning model by merging the values obtained by each classifier. Another issue that arises is overfitting due to the high-dimensional texture of individual tissue components. We propose a new FS method, SVM-RFE(AC), that integrates a Support Vector Machine-Recursive Feature Elimination (SVM-RFE) embedded procedure with an absolute cosine (AC) filter method to prevent redundancy in the selected features of the SV-RFE and an unoptimised classifier in the AC. Results: We conducted experiments on H&E histopathological prostate and colon cancer images with respect to three prostate classifications, namely benign vs. grade 3, benign vs. grade 4 and grade 3 vs. grade 4. The colon benchmark dataset requires a distinction between grades 1 and 2, which are the most difficult cases to distinguish in the colon domain. The results obtained by both the single and ensemble classification models (which uses the product rule as its merging method) confirm that the proposed SVM-RFE(AC) is superior to the other SVM and SVM-RFE-based methods. Conclusion: We developed an FS method based on SVM-RFE and AC and successfully showed that its use enabled the identification of the most crucial texture feature of each tissue component. Thus, it makes possible the distinction between multiple Gleason grades (e.g. grade 3 vs. grade 4) and its performance is far superior to other reported FS methods.

LanguageEnglish
Pages78-90
Number of pages13
JournalArtificial Intelligence in Medicine
Volume87
DOIs
Publication statusPublished - 1 May 2018

Fingerprint

Feature extraction
Prostate
Tissue
Textures
Classifiers
Merging
Redundancy
Colon
Benchmarking
Support vector machines
Colonic Neoplasms
Prostatic Neoplasms
Cytoplasm
Learning
Experiments

Keywords

  • Absolute cosine
  • Ensemble classification
  • Feature selection
  • Prostate histopathological image
  • Redundancy
  • SVM-RFE
  • Tissue components

ASJC Scopus subject areas

  • Medicine (miscellaneous)
  • Artificial Intelligence

Cite this

Absolute cosine-based SVM-RFE feature selection method for prostate histopathological grading. / Sahran, Shahnorbanun; Albashish, Dheeb; Abdullah, Azizi; Shukor, Nordashima Abd; Hayati Md Pauzi, Suria.

In: Artificial Intelligence in Medicine, Vol. 87, 01.05.2018, p. 78-90.

Research output: Contribution to journalArticle

@article{531de78448e44158a7b1280e1e61c3a2,
title = "Absolute cosine-based SVM-RFE feature selection method for prostate histopathological grading",
abstract = "Objective: Feature selection (FS) methods are widely used in grading and diagnosing prostate histopathological images. In this context, FS is based on the texture features obtained from the lumen, nuclei, cytoplasm and stroma, all of which are important tissue components. However, it is difficult to represent the high-dimensional textures of these tissue components. To solve this problem, we propose a new FS method that enables the selection of features with minimal redundancy in the tissue components. Methodology: We categorise tissue images based on the texture of individual tissue components via the construction of a single classifier and also construct an ensemble learning model by merging the values obtained by each classifier. Another issue that arises is overfitting due to the high-dimensional texture of individual tissue components. We propose a new FS method, SVM-RFE(AC), that integrates a Support Vector Machine-Recursive Feature Elimination (SVM-RFE) embedded procedure with an absolute cosine (AC) filter method to prevent redundancy in the selected features of the SV-RFE and an unoptimised classifier in the AC. Results: We conducted experiments on H&E histopathological prostate and colon cancer images with respect to three prostate classifications, namely benign vs. grade 3, benign vs. grade 4 and grade 3 vs. grade 4. The colon benchmark dataset requires a distinction between grades 1 and 2, which are the most difficult cases to distinguish in the colon domain. The results obtained by both the single and ensemble classification models (which uses the product rule as its merging method) confirm that the proposed SVM-RFE(AC) is superior to the other SVM and SVM-RFE-based methods. Conclusion: We developed an FS method based on SVM-RFE and AC and successfully showed that its use enabled the identification of the most crucial texture feature of each tissue component. Thus, it makes possible the distinction between multiple Gleason grades (e.g. grade 3 vs. grade 4) and its performance is far superior to other reported FS methods.",
keywords = "Absolute cosine, Ensemble classification, Feature selection, Prostate histopathological image, Redundancy, SVM-RFE, Tissue components",
author = "Shahnorbanun Sahran and Dheeb Albashish and Azizi Abdullah and Shukor, {Nordashima Abd} and {Hayati Md Pauzi}, Suria",
year = "2018",
month = "5",
day = "1",
doi = "10.1016/j.artmed.2018.04.002",
language = "English",
volume = "87",
pages = "78--90",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",

}

TY - JOUR

T1 - Absolute cosine-based SVM-RFE feature selection method for prostate histopathological grading

AU - Sahran, Shahnorbanun

AU - Albashish, Dheeb

AU - Abdullah, Azizi

AU - Shukor, Nordashima Abd

AU - Hayati Md Pauzi, Suria

PY - 2018/5/1

Y1 - 2018/5/1

N2 - Objective: Feature selection (FS) methods are widely used in grading and diagnosing prostate histopathological images. In this context, FS is based on the texture features obtained from the lumen, nuclei, cytoplasm and stroma, all of which are important tissue components. However, it is difficult to represent the high-dimensional textures of these tissue components. To solve this problem, we propose a new FS method that enables the selection of features with minimal redundancy in the tissue components. Methodology: We categorise tissue images based on the texture of individual tissue components via the construction of a single classifier and also construct an ensemble learning model by merging the values obtained by each classifier. Another issue that arises is overfitting due to the high-dimensional texture of individual tissue components. We propose a new FS method, SVM-RFE(AC), that integrates a Support Vector Machine-Recursive Feature Elimination (SVM-RFE) embedded procedure with an absolute cosine (AC) filter method to prevent redundancy in the selected features of the SV-RFE and an unoptimised classifier in the AC. Results: We conducted experiments on H&E histopathological prostate and colon cancer images with respect to three prostate classifications, namely benign vs. grade 3, benign vs. grade 4 and grade 3 vs. grade 4. The colon benchmark dataset requires a distinction between grades 1 and 2, which are the most difficult cases to distinguish in the colon domain. The results obtained by both the single and ensemble classification models (which uses the product rule as its merging method) confirm that the proposed SVM-RFE(AC) is superior to the other SVM and SVM-RFE-based methods. Conclusion: We developed an FS method based on SVM-RFE and AC and successfully showed that its use enabled the identification of the most crucial texture feature of each tissue component. Thus, it makes possible the distinction between multiple Gleason grades (e.g. grade 3 vs. grade 4) and its performance is far superior to other reported FS methods.

AB - Objective: Feature selection (FS) methods are widely used in grading and diagnosing prostate histopathological images. In this context, FS is based on the texture features obtained from the lumen, nuclei, cytoplasm and stroma, all of which are important tissue components. However, it is difficult to represent the high-dimensional textures of these tissue components. To solve this problem, we propose a new FS method that enables the selection of features with minimal redundancy in the tissue components. Methodology: We categorise tissue images based on the texture of individual tissue components via the construction of a single classifier and also construct an ensemble learning model by merging the values obtained by each classifier. Another issue that arises is overfitting due to the high-dimensional texture of individual tissue components. We propose a new FS method, SVM-RFE(AC), that integrates a Support Vector Machine-Recursive Feature Elimination (SVM-RFE) embedded procedure with an absolute cosine (AC) filter method to prevent redundancy in the selected features of the SV-RFE and an unoptimised classifier in the AC. Results: We conducted experiments on H&E histopathological prostate and colon cancer images with respect to three prostate classifications, namely benign vs. grade 3, benign vs. grade 4 and grade 3 vs. grade 4. The colon benchmark dataset requires a distinction between grades 1 and 2, which are the most difficult cases to distinguish in the colon domain. The results obtained by both the single and ensemble classification models (which uses the product rule as its merging method) confirm that the proposed SVM-RFE(AC) is superior to the other SVM and SVM-RFE-based methods. Conclusion: We developed an FS method based on SVM-RFE and AC and successfully showed that its use enabled the identification of the most crucial texture feature of each tissue component. Thus, it makes possible the distinction between multiple Gleason grades (e.g. grade 3 vs. grade 4) and its performance is far superior to other reported FS methods.

KW - Absolute cosine

KW - Ensemble classification

KW - Feature selection

KW - Prostate histopathological image

KW - Redundancy

KW - SVM-RFE

KW - Tissue components

UR - http://www.scopus.com/inward/record.url?scp=85045841135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045841135&partnerID=8YFLogxK

U2 - 10.1016/j.artmed.2018.04.002

DO - 10.1016/j.artmed.2018.04.002

M3 - Article

VL - 87

SP - 78

EP - 90

JO - Artificial Intelligence in Medicine

T2 - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

ER -