Detection of small bowel tumor in wireless capsule endoscopy images using an adaptive neuro-fuzzy inference system

Mahdi Alizadeh, Omid Haji Maghsoudi, Kaveh Sharzehi, Hamid Reza Hemati, Alireza Kamali Asl, Alireza Talebpour

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Automatic diagnosis tool helps physicians to evaluate capsule endoscopic examinations faster and more accurate. The purpose of this study was to evaluate the validity and reliability of an automatic post-processing method for identifying and classifying wireless capsule endoscopic images, and investigate statistical measures to differentiate normal and abnormal images. The proposed technique consists of two main stages, namely, feature extraction and classification. Primarily, 32 features incorporating four statistical measures (contrast, correlation, homogeneity and energy) calculated from co-occurrence metrics were computed. Then, mutual information was used to select features with maximal dependence on the target class and with minimal redundancy between features. Finally, a trained classifier, adaptive neuro-fuzzy interface system was implemented to classify endoscopic images into tumor, healthy and unhealthy classes. Classification accuracy of 94.2% was obtained using the proposed pipeline. Such techniques are valuable for accurate detection characterization and interpretation of endoscopic images.

Original languageEnglish (US)
Pages (from-to)419-427
Number of pages9
JournalJournal of Biomedical Research
Volume31
Issue number5
DOIs
StatePublished - Jan 1 2017
Externally publishedYes

Fingerprint

Capsule Endoscopy
Endoscopy
Fuzzy inference
Capsules
Tumors
Reproducibility of Results
Redundancy
Feature extraction
Neoplasms
Classifiers
Pipelines
Physicians
Processing

Keywords

  • Adaptive neuro-fuzzy inference system
  • Co-occurrence matrix
  • Texture feature
  • Wireless capsule endoscopy

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)

Cite this

Detection of small bowel tumor in wireless capsule endoscopy images using an adaptive neuro-fuzzy inference system. / Alizadeh, Mahdi; Maghsoudi, Omid Haji; Sharzehi, Kaveh; Hemati, Hamid Reza; Asl, Alireza Kamali; Talebpour, Alireza.

In: Journal of Biomedical Research, Vol. 31, No. 5, 01.01.2017, p. 419-427.

Research output: Contribution to journalArticle

Alizadeh, Mahdi ; Maghsoudi, Omid Haji ; Sharzehi, Kaveh ; Hemati, Hamid Reza ; Asl, Alireza Kamali ; Talebpour, Alireza. / Detection of small bowel tumor in wireless capsule endoscopy images using an adaptive neuro-fuzzy inference system. In: Journal of Biomedical Research. 2017 ; Vol. 31, No. 5. pp. 419-427.
@article{ee3d3a5f25c649b693d4bb94fee0476d,
title = "Detection of small bowel tumor in wireless capsule endoscopy images using an adaptive neuro-fuzzy inference system",
abstract = "Automatic diagnosis tool helps physicians to evaluate capsule endoscopic examinations faster and more accurate. The purpose of this study was to evaluate the validity and reliability of an automatic post-processing method for identifying and classifying wireless capsule endoscopic images, and investigate statistical measures to differentiate normal and abnormal images. The proposed technique consists of two main stages, namely, feature extraction and classification. Primarily, 32 features incorporating four statistical measures (contrast, correlation, homogeneity and energy) calculated from co-occurrence metrics were computed. Then, mutual information was used to select features with maximal dependence on the target class and with minimal redundancy between features. Finally, a trained classifier, adaptive neuro-fuzzy interface system was implemented to classify endoscopic images into tumor, healthy and unhealthy classes. Classification accuracy of 94.2{\%} was obtained using the proposed pipeline. Such techniques are valuable for accurate detection characterization and interpretation of endoscopic images.",
keywords = "Adaptive neuro-fuzzy inference system, Co-occurrence matrix, Texture feature, Wireless capsule endoscopy",
author = "Mahdi Alizadeh and Maghsoudi, {Omid Haji} and Kaveh Sharzehi and Hemati, {Hamid Reza} and Asl, {Alireza Kamali} and Alireza Talebpour",
year = "2017",
month = "1",
day = "1",
doi = "10.7555/JBR.31.20160008",
language = "English (US)",
volume = "31",
pages = "419--427",
journal = "Journal of Biomedical Research",
issn = "1674-8301",
publisher = "Nanjing Medical University",
number = "5",

}

TY - JOUR

T1 - Detection of small bowel tumor in wireless capsule endoscopy images using an adaptive neuro-fuzzy inference system

AU - Alizadeh, Mahdi

AU - Maghsoudi, Omid Haji

AU - Sharzehi, Kaveh

AU - Hemati, Hamid Reza

AU - Asl, Alireza Kamali

AU - Talebpour, Alireza

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Automatic diagnosis tool helps physicians to evaluate capsule endoscopic examinations faster and more accurate. The purpose of this study was to evaluate the validity and reliability of an automatic post-processing method for identifying and classifying wireless capsule endoscopic images, and investigate statistical measures to differentiate normal and abnormal images. The proposed technique consists of two main stages, namely, feature extraction and classification. Primarily, 32 features incorporating four statistical measures (contrast, correlation, homogeneity and energy) calculated from co-occurrence metrics were computed. Then, mutual information was used to select features with maximal dependence on the target class and with minimal redundancy between features. Finally, a trained classifier, adaptive neuro-fuzzy interface system was implemented to classify endoscopic images into tumor, healthy and unhealthy classes. Classification accuracy of 94.2% was obtained using the proposed pipeline. Such techniques are valuable for accurate detection characterization and interpretation of endoscopic images.

AB - Automatic diagnosis tool helps physicians to evaluate capsule endoscopic examinations faster and more accurate. The purpose of this study was to evaluate the validity and reliability of an automatic post-processing method for identifying and classifying wireless capsule endoscopic images, and investigate statistical measures to differentiate normal and abnormal images. The proposed technique consists of two main stages, namely, feature extraction and classification. Primarily, 32 features incorporating four statistical measures (contrast, correlation, homogeneity and energy) calculated from co-occurrence metrics were computed. Then, mutual information was used to select features with maximal dependence on the target class and with minimal redundancy between features. Finally, a trained classifier, adaptive neuro-fuzzy interface system was implemented to classify endoscopic images into tumor, healthy and unhealthy classes. Classification accuracy of 94.2% was obtained using the proposed pipeline. Such techniques are valuable for accurate detection characterization and interpretation of endoscopic images.

KW - Adaptive neuro-fuzzy inference system

KW - Co-occurrence matrix

KW - Texture feature

KW - Wireless capsule endoscopy

UR - http://www.scopus.com/inward/record.url?scp=85029684680&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029684680&partnerID=8YFLogxK

U2 - 10.7555/JBR.31.20160008

DO - 10.7555/JBR.31.20160008

M3 - Article

VL - 31

SP - 419

EP - 427

JO - Journal of Biomedical Research

JF - Journal of Biomedical Research

SN - 1674-8301

IS - 5

ER -