Automated detection and classification of liver fibrosis stages using contourlet transform and nonlinear features

U. Rajendra Acharya, U. Raghavendra, Joel E.W. Koh, Kristen M. Meiburger, Edward J. Ciaccio, Yuki Hagiwara, Filippo Molinari, Wai Ling Leong, Anushya Vijayananthan, Nur Adura Yaakup, Mohd Kamil Bin Mohd Fabell, Chai Hong Yeong

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Background and objective: Liver fibrosis is a type of chronic liver injury that is characterized by an excessive deposition of extracellular matrix protein. Early detection of liver fibrosis may prevent further growth toward liver cirrhosis and hepatocellular carcinoma. In the past, the only method to assess liver fibrosis was through biopsy, but this examination is invasive, expensive, prone to sampling errors, and may cause complications such as bleeding. Ultrasound-based elastography is a promising tool to measure tissue elasticity in real time; however, this technology requires an upgrade of the ultrasound system and software. In this study, a novel computer-aided diagnosis tool is proposed to automatically detect and classify the various stages of liver fibrosis based upon conventional B-mode ultrasound images. Methods: The proposed method uses a 2D contourlet transform and a set of texture features that are efficiently extracted from the transformed image. Then, the combination of a kernel discriminant analysis (KDA)-based feature reduction technique and analysis of variance (ANOVA)-based feature ranking technique was used, and the images were then classified into various stages of liver fibrosis. Results: Our 2D contourlet transform and texture feature analysis approach achieved a 91.46% accuracy using only four features input to the probabilistic neural network classifier, to classify the five stages of liver fibrosis. It also achieved a 92.16% sensitivity and 88.92% specificity for the same model. The evaluation was done on a database of 762 ultrasound images belonging to five different stages of liver fibrosis. Conclusions: The findings suggest that the proposed method can be useful to automatically detect and classify liver fibrosis, which would greatly assist clinicians in making an accurate diagnosis.

Original languageEnglish
Pages (from-to)91-98
Number of pages8
JournalComputer Methods and Programs in Biomedicine
Volume166
DOIs
Publication statusPublished - 01-11-2018

Fingerprint

Liver Cirrhosis
Liver
Ultrasonics
Textures
Elasticity Imaging Techniques
Computer aided diagnosis
Selection Bias
Extracellular Matrix Proteins
Elasticity
Discriminant Analysis
Biopsy
Discriminant analysis
Analysis of variance (ANOVA)
Hepatocellular Carcinoma
Analysis of Variance
Software
Classifiers
Databases
Hemorrhage
Technology

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Health Informatics

Cite this

Acharya, U. Rajendra ; Raghavendra, U. ; Koh, Joel E.W. ; Meiburger, Kristen M. ; Ciaccio, Edward J. ; Hagiwara, Yuki ; Molinari, Filippo ; Leong, Wai Ling ; Vijayananthan, Anushya ; Yaakup, Nur Adura ; Fabell, Mohd Kamil Bin Mohd ; Yeong, Chai Hong. / Automated detection and classification of liver fibrosis stages using contourlet transform and nonlinear features. In: Computer Methods and Programs in Biomedicine. 2018 ; Vol. 166. pp. 91-98.
@article{d7b615dc6de2417f84a0b6893fce0f89,
title = "Automated detection and classification of liver fibrosis stages using contourlet transform and nonlinear features",
abstract = "Background and objective: Liver fibrosis is a type of chronic liver injury that is characterized by an excessive deposition of extracellular matrix protein. Early detection of liver fibrosis may prevent further growth toward liver cirrhosis and hepatocellular carcinoma. In the past, the only method to assess liver fibrosis was through biopsy, but this examination is invasive, expensive, prone to sampling errors, and may cause complications such as bleeding. Ultrasound-based elastography is a promising tool to measure tissue elasticity in real time; however, this technology requires an upgrade of the ultrasound system and software. In this study, a novel computer-aided diagnosis tool is proposed to automatically detect and classify the various stages of liver fibrosis based upon conventional B-mode ultrasound images. Methods: The proposed method uses a 2D contourlet transform and a set of texture features that are efficiently extracted from the transformed image. Then, the combination of a kernel discriminant analysis (KDA)-based feature reduction technique and analysis of variance (ANOVA)-based feature ranking technique was used, and the images were then classified into various stages of liver fibrosis. Results: Our 2D contourlet transform and texture feature analysis approach achieved a 91.46{\%} accuracy using only four features input to the probabilistic neural network classifier, to classify the five stages of liver fibrosis. It also achieved a 92.16{\%} sensitivity and 88.92{\%} specificity for the same model. The evaluation was done on a database of 762 ultrasound images belonging to five different stages of liver fibrosis. Conclusions: The findings suggest that the proposed method can be useful to automatically detect and classify liver fibrosis, which would greatly assist clinicians in making an accurate diagnosis.",
author = "Acharya, {U. Rajendra} and U. Raghavendra and Koh, {Joel E.W.} and Meiburger, {Kristen M.} and Ciaccio, {Edward J.} and Yuki Hagiwara and Filippo Molinari and Leong, {Wai Ling} and Anushya Vijayananthan and Yaakup, {Nur Adura} and Fabell, {Mohd Kamil Bin Mohd} and Yeong, {Chai Hong}",
year = "2018",
month = "11",
day = "1",
doi = "10.1016/j.cmpb.2018.10.006",
language = "English",
volume = "166",
pages = "91--98",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",

}

Acharya, UR, Raghavendra, U, Koh, JEW, Meiburger, KM, Ciaccio, EJ, Hagiwara, Y, Molinari, F, Leong, WL, Vijayananthan, A, Yaakup, NA, Fabell, MKBM & Yeong, CH 2018, 'Automated detection and classification of liver fibrosis stages using contourlet transform and nonlinear features', Computer Methods and Programs in Biomedicine, vol. 166, pp. 91-98. https://doi.org/10.1016/j.cmpb.2018.10.006

Automated detection and classification of liver fibrosis stages using contourlet transform and nonlinear features. / Acharya, U. Rajendra; Raghavendra, U.; Koh, Joel E.W.; Meiburger, Kristen M.; Ciaccio, Edward J.; Hagiwara, Yuki; Molinari, Filippo; Leong, Wai Ling; Vijayananthan, Anushya; Yaakup, Nur Adura; Fabell, Mohd Kamil Bin Mohd; Yeong, Chai Hong.

In: Computer Methods and Programs in Biomedicine, Vol. 166, 01.11.2018, p. 91-98.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated detection and classification of liver fibrosis stages using contourlet transform and nonlinear features

AU - Acharya, U. Rajendra

AU - Raghavendra, U.

AU - Koh, Joel E.W.

AU - Meiburger, Kristen M.

AU - Ciaccio, Edward J.

AU - Hagiwara, Yuki

AU - Molinari, Filippo

AU - Leong, Wai Ling

AU - Vijayananthan, Anushya

AU - Yaakup, Nur Adura

AU - Fabell, Mohd Kamil Bin Mohd

AU - Yeong, Chai Hong

PY - 2018/11/1

Y1 - 2018/11/1

N2 - Background and objective: Liver fibrosis is a type of chronic liver injury that is characterized by an excessive deposition of extracellular matrix protein. Early detection of liver fibrosis may prevent further growth toward liver cirrhosis and hepatocellular carcinoma. In the past, the only method to assess liver fibrosis was through biopsy, but this examination is invasive, expensive, prone to sampling errors, and may cause complications such as bleeding. Ultrasound-based elastography is a promising tool to measure tissue elasticity in real time; however, this technology requires an upgrade of the ultrasound system and software. In this study, a novel computer-aided diagnosis tool is proposed to automatically detect and classify the various stages of liver fibrosis based upon conventional B-mode ultrasound images. Methods: The proposed method uses a 2D contourlet transform and a set of texture features that are efficiently extracted from the transformed image. Then, the combination of a kernel discriminant analysis (KDA)-based feature reduction technique and analysis of variance (ANOVA)-based feature ranking technique was used, and the images were then classified into various stages of liver fibrosis. Results: Our 2D contourlet transform and texture feature analysis approach achieved a 91.46% accuracy using only four features input to the probabilistic neural network classifier, to classify the five stages of liver fibrosis. It also achieved a 92.16% sensitivity and 88.92% specificity for the same model. The evaluation was done on a database of 762 ultrasound images belonging to five different stages of liver fibrosis. Conclusions: The findings suggest that the proposed method can be useful to automatically detect and classify liver fibrosis, which would greatly assist clinicians in making an accurate diagnosis.

AB - Background and objective: Liver fibrosis is a type of chronic liver injury that is characterized by an excessive deposition of extracellular matrix protein. Early detection of liver fibrosis may prevent further growth toward liver cirrhosis and hepatocellular carcinoma. In the past, the only method to assess liver fibrosis was through biopsy, but this examination is invasive, expensive, prone to sampling errors, and may cause complications such as bleeding. Ultrasound-based elastography is a promising tool to measure tissue elasticity in real time; however, this technology requires an upgrade of the ultrasound system and software. In this study, a novel computer-aided diagnosis tool is proposed to automatically detect and classify the various stages of liver fibrosis based upon conventional B-mode ultrasound images. Methods: The proposed method uses a 2D contourlet transform and a set of texture features that are efficiently extracted from the transformed image. Then, the combination of a kernel discriminant analysis (KDA)-based feature reduction technique and analysis of variance (ANOVA)-based feature ranking technique was used, and the images were then classified into various stages of liver fibrosis. Results: Our 2D contourlet transform and texture feature analysis approach achieved a 91.46% accuracy using only four features input to the probabilistic neural network classifier, to classify the five stages of liver fibrosis. It also achieved a 92.16% sensitivity and 88.92% specificity for the same model. The evaluation was done on a database of 762 ultrasound images belonging to five different stages of liver fibrosis. Conclusions: The findings suggest that the proposed method can be useful to automatically detect and classify liver fibrosis, which would greatly assist clinicians in making an accurate diagnosis.

UR - http://www.scopus.com/inward/record.url?scp=85054743325&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054743325&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2018.10.006

DO - 10.1016/j.cmpb.2018.10.006

M3 - Article

VL - 166

SP - 91

EP - 98

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

ER -