Classification of liver diseases based on ultrasound image texture features

Sendren Sheng Dong Xu, Chun Chao Chang, Chien Tien Su, Pham Quoc Phu

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper discusses using computer-aided diagnosis (CAD) to distinguish between hepatocellular carcinoma (HCC), i.e., the most common type of primary liver malignancy and a leading cause of death in people with cirrhosis worldwide, and liver abscess based on ultrasound image texture features and a support vector machine (SVM) classifier. Among 79 cases of liver diseases including 44 cases of liver cancer and 35 cases of liver abscess, this research extracts 96 features including 52 features of the gray-level co-occurrence matrix (GLCM) and 44 features of the gray-level run-length matrix (GLRLM) from the regions of interest (ROIs) in ultrasound images. Three feature selection models-(i) sequential forward selection (SFS), (ii) sequential backward selection (SBS), and (iii) F-score-are adopted to distinguish the two liver diseases. Finally, the developed system can classify liver cancer and liver abscess by SVM with an accuracy of 88.875%. The proposed methods for CAD can provide diagnostic assistance while distinguishing these two types of liver lesions.

Original languageEnglish
Article number342
JournalApplied Sciences (Switzerland)
Volume9
Issue number2
DOIs
Publication statusPublished - Jan 19 2019

Fingerprint

Image texture
liver
Liver
textures
Ultrasonics
Computer aided diagnosis
cancer
Support vector machines
matrices
classifiers
death
lesions
Feature extraction
Classifiers
occurrences

Keywords

  • Classification
  • F-score
  • Gray-level co-occurrence matrix (GLCM)
  • Gray-level run-length matrix (GLRLM)
  • Hepatocellular carcinoma (HCC)
  • Image texture
  • Liver abscess
  • Liver cancer
  • Sequential backward selection (SBS)
  • Sequential forward selection (SFS)
  • Support vector machine (SVM)
  • Ultrasound images

ASJC Scopus subject areas

  • Materials Science(all)
  • Instrumentation
  • Engineering(all)
  • Process Chemistry and Technology
  • Computer Science Applications
  • Fluid Flow and Transfer Processes

Cite this

Classification of liver diseases based on ultrasound image texture features. / Xu, Sendren Sheng Dong; Chang, Chun Chao; Su, Chien Tien; Phu, Pham Quoc.

In: Applied Sciences (Switzerland), Vol. 9, No. 2, 342, 19.01.2019.

Research output: Contribution to journalArticle

@article{83d787d3deb3415a9bdb4205296a9d54,
title = "Classification of liver diseases based on ultrasound image texture features",
abstract = "This paper discusses using computer-aided diagnosis (CAD) to distinguish between hepatocellular carcinoma (HCC), i.e., the most common type of primary liver malignancy and a leading cause of death in people with cirrhosis worldwide, and liver abscess based on ultrasound image texture features and a support vector machine (SVM) classifier. Among 79 cases of liver diseases including 44 cases of liver cancer and 35 cases of liver abscess, this research extracts 96 features including 52 features of the gray-level co-occurrence matrix (GLCM) and 44 features of the gray-level run-length matrix (GLRLM) from the regions of interest (ROIs) in ultrasound images. Three feature selection models-(i) sequential forward selection (SFS), (ii) sequential backward selection (SBS), and (iii) F-score-are adopted to distinguish the two liver diseases. Finally, the developed system can classify liver cancer and liver abscess by SVM with an accuracy of 88.875{\%}. The proposed methods for CAD can provide diagnostic assistance while distinguishing these two types of liver lesions.",
keywords = "Classification, F-score, Gray-level co-occurrence matrix (GLCM), Gray-level run-length matrix (GLRLM), Hepatocellular carcinoma (HCC), Image texture, Liver abscess, Liver cancer, Sequential backward selection (SBS), Sequential forward selection (SFS), Support vector machine (SVM), Ultrasound images",
author = "Xu, {Sendren Sheng Dong} and Chang, {Chun Chao} and Su, {Chien Tien} and Phu, {Pham Quoc}",
year = "2019",
month = "1",
day = "19",
doi = "10.3390/app9020342",
language = "English",
volume = "9",
journal = "Applied Sciences (Switzerland)",
issn = "2076-3417",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "2",

}

TY - JOUR

T1 - Classification of liver diseases based on ultrasound image texture features

AU - Xu, Sendren Sheng Dong

AU - Chang, Chun Chao

AU - Su, Chien Tien

AU - Phu, Pham Quoc

PY - 2019/1/19

Y1 - 2019/1/19

N2 - This paper discusses using computer-aided diagnosis (CAD) to distinguish between hepatocellular carcinoma (HCC), i.e., the most common type of primary liver malignancy and a leading cause of death in people with cirrhosis worldwide, and liver abscess based on ultrasound image texture features and a support vector machine (SVM) classifier. Among 79 cases of liver diseases including 44 cases of liver cancer and 35 cases of liver abscess, this research extracts 96 features including 52 features of the gray-level co-occurrence matrix (GLCM) and 44 features of the gray-level run-length matrix (GLRLM) from the regions of interest (ROIs) in ultrasound images. Three feature selection models-(i) sequential forward selection (SFS), (ii) sequential backward selection (SBS), and (iii) F-score-are adopted to distinguish the two liver diseases. Finally, the developed system can classify liver cancer and liver abscess by SVM with an accuracy of 88.875%. The proposed methods for CAD can provide diagnostic assistance while distinguishing these two types of liver lesions.

AB - This paper discusses using computer-aided diagnosis (CAD) to distinguish between hepatocellular carcinoma (HCC), i.e., the most common type of primary liver malignancy and a leading cause of death in people with cirrhosis worldwide, and liver abscess based on ultrasound image texture features and a support vector machine (SVM) classifier. Among 79 cases of liver diseases including 44 cases of liver cancer and 35 cases of liver abscess, this research extracts 96 features including 52 features of the gray-level co-occurrence matrix (GLCM) and 44 features of the gray-level run-length matrix (GLRLM) from the regions of interest (ROIs) in ultrasound images. Three feature selection models-(i) sequential forward selection (SFS), (ii) sequential backward selection (SBS), and (iii) F-score-are adopted to distinguish the two liver diseases. Finally, the developed system can classify liver cancer and liver abscess by SVM with an accuracy of 88.875%. The proposed methods for CAD can provide diagnostic assistance while distinguishing these two types of liver lesions.

KW - Classification

KW - F-score

KW - Gray-level co-occurrence matrix (GLCM)

KW - Gray-level run-length matrix (GLRLM)

KW - Hepatocellular carcinoma (HCC)

KW - Image texture

KW - Liver abscess

KW - Liver cancer

KW - Sequential backward selection (SBS)

KW - Sequential forward selection (SFS)

KW - Support vector machine (SVM)

KW - Ultrasound images

UR - http://www.scopus.com/inward/record.url?scp=85060290076&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060290076&partnerID=8YFLogxK

U2 - 10.3390/app9020342

DO - 10.3390/app9020342

M3 - Article

AN - SCOPUS:85060290076

VL - 9

JO - Applied Sciences (Switzerland)

JF - Applied Sciences (Switzerland)

SN - 2076-3417

IS - 2

M1 - 342

ER -