Computer-aided diagnosis of liver tumors on computed tomography images

Chin Chen Chang, Hong Hao Chen, Yeun Chung Chang, Ming Yang Yang, Chung Ming Lo, Wei Chun Ko, Yee Fan Lee, Kao Lang Liu, Ruey Feng Chang

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Background and objective Liver cancer is the tenth most common cancer in the USA, and its incidence has been increasing for several decades. Early detection, diagnosis, and treatment of the disease are very important. Computed tomography (CT) is one of the most common and robust imaging techniques for the detection of liver cancer. CT scanners can provide multiple-phase sequential scans of the whole liver. In this study, we proposed a computer-aided diagnosis (CAD) system to diagnose liver cancer using the features of tumors obtained from multiphase CT images. Methods A total of 71 histologically-proven liver tumors including 49 benign and 22 malignant lesions were evaluated with the proposed CAD system to evaluate its performance. Tumors were identified by the user and then segmented using a region growing algorithm. After tumor segmentation, three kinds of features were obtained for each tumor, including texture, shape, and kinetic curve. The texture was quantified using 3 dimensional (3-D) texture data of the tumor based on the grey level co-occurrence matrix (GLCM). Compactness, margin, and an elliptic model were used to describe the 3-D shape of the tumor. The kinetic curve was established from each phase of tumor and represented as variations in density between each phase. Backward elimination was used to select the best combination of features, and binary logistic regression analysis was used to classify the tumors with leave-one-out cross validation. Results The accuracy and sensitivity for the texture were 71.82% and 68.18%, respectively, which were better than for the shape and kinetic curve under closed specificity. Combining all of the features achieved the highest accuracy (58/71, 81.69%), sensitivity (18/22, 81.82%), and specificity (40/49, 81.63%). The Az value of combining all features was 0.8713. Conclusions Combining texture, shape, and kinetic curve features may be able to differentiate benign from malignant tumors in the liver using our proposed CAD system.

Original languageEnglish
Pages (from-to)45-51
Number of pages7
JournalComputer Methods and Programs in Biomedicine
Volume145
DOIs
Publication statusPublished - Jul 1 2017

Fingerprint

Computer aided diagnosis
Liver
Tomography
Tumors
Neoplasms
Textures
Liver Neoplasms
Kinetics
X-Ray Computed Tomography Scanners
Regression analysis
Logistics
Early Diagnosis
Logistic Models
Regression Analysis
Imaging techniques

Keywords

  • Computed tomography
  • Diagnosis
  • Elliptic model
  • Grey level co-occurrence matrix
  • Kinetic curve
  • Liver

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Health Informatics

Cite this

Chang, C. C., Chen, H. H., Chang, Y. C., Yang, M. Y., Lo, C. M., Ko, W. C., ... Chang, R. F. (2017). Computer-aided diagnosis of liver tumors on computed tomography images. Computer Methods and Programs in Biomedicine, 145, 45-51. https://doi.org/10.1016/j.cmpb.2017.04.008

Computer-aided diagnosis of liver tumors on computed tomography images. / Chang, Chin Chen; Chen, Hong Hao; Chang, Yeun Chung; Yang, Ming Yang; Lo, Chung Ming; Ko, Wei Chun; Lee, Yee Fan; Liu, Kao Lang; Chang, Ruey Feng.

In: Computer Methods and Programs in Biomedicine, Vol. 145, 01.07.2017, p. 45-51.

Research output: Contribution to journalArticle

Chang, CC, Chen, HH, Chang, YC, Yang, MY, Lo, CM, Ko, WC, Lee, YF, Liu, KL & Chang, RF 2017, 'Computer-aided diagnosis of liver tumors on computed tomography images', Computer Methods and Programs in Biomedicine, vol. 145, pp. 45-51. https://doi.org/10.1016/j.cmpb.2017.04.008
Chang, Chin Chen ; Chen, Hong Hao ; Chang, Yeun Chung ; Yang, Ming Yang ; Lo, Chung Ming ; Ko, Wei Chun ; Lee, Yee Fan ; Liu, Kao Lang ; Chang, Ruey Feng. / Computer-aided diagnosis of liver tumors on computed tomography images. In: Computer Methods and Programs in Biomedicine. 2017 ; Vol. 145. pp. 45-51.
@article{d7c9bbc2e27d4af3b6e817f1cb028643,
title = "Computer-aided diagnosis of liver tumors on computed tomography images",
abstract = "Background and objective Liver cancer is the tenth most common cancer in the USA, and its incidence has been increasing for several decades. Early detection, diagnosis, and treatment of the disease are very important. Computed tomography (CT) is one of the most common and robust imaging techniques for the detection of liver cancer. CT scanners can provide multiple-phase sequential scans of the whole liver. In this study, we proposed a computer-aided diagnosis (CAD) system to diagnose liver cancer using the features of tumors obtained from multiphase CT images. Methods A total of 71 histologically-proven liver tumors including 49 benign and 22 malignant lesions were evaluated with the proposed CAD system to evaluate its performance. Tumors were identified by the user and then segmented using a region growing algorithm. After tumor segmentation, three kinds of features were obtained for each tumor, including texture, shape, and kinetic curve. The texture was quantified using 3 dimensional (3-D) texture data of the tumor based on the grey level co-occurrence matrix (GLCM). Compactness, margin, and an elliptic model were used to describe the 3-D shape of the tumor. The kinetic curve was established from each phase of tumor and represented as variations in density between each phase. Backward elimination was used to select the best combination of features, and binary logistic regression analysis was used to classify the tumors with leave-one-out cross validation. Results The accuracy and sensitivity for the texture were 71.82{\%} and 68.18{\%}, respectively, which were better than for the shape and kinetic curve under closed specificity. Combining all of the features achieved the highest accuracy (58/71, 81.69{\%}), sensitivity (18/22, 81.82{\%}), and specificity (40/49, 81.63{\%}). The Az value of combining all features was 0.8713. Conclusions Combining texture, shape, and kinetic curve features may be able to differentiate benign from malignant tumors in the liver using our proposed CAD system.",
keywords = "Computed tomography, Diagnosis, Elliptic model, Grey level co-occurrence matrix, Kinetic curve, Liver",
author = "Chang, {Chin Chen} and Chen, {Hong Hao} and Chang, {Yeun Chung} and Yang, {Ming Yang} and Lo, {Chung Ming} and Ko, {Wei Chun} and Lee, {Yee Fan} and Liu, {Kao Lang} and Chang, {Ruey Feng}",
year = "2017",
month = "7",
day = "1",
doi = "10.1016/j.cmpb.2017.04.008",
language = "English",
volume = "145",
pages = "45--51",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - Computer-aided diagnosis of liver tumors on computed tomography images

AU - Chang, Chin Chen

AU - Chen, Hong Hao

AU - Chang, Yeun Chung

AU - Yang, Ming Yang

AU - Lo, Chung Ming

AU - Ko, Wei Chun

AU - Lee, Yee Fan

AU - Liu, Kao Lang

AU - Chang, Ruey Feng

PY - 2017/7/1

Y1 - 2017/7/1

N2 - Background and objective Liver cancer is the tenth most common cancer in the USA, and its incidence has been increasing for several decades. Early detection, diagnosis, and treatment of the disease are very important. Computed tomography (CT) is one of the most common and robust imaging techniques for the detection of liver cancer. CT scanners can provide multiple-phase sequential scans of the whole liver. In this study, we proposed a computer-aided diagnosis (CAD) system to diagnose liver cancer using the features of tumors obtained from multiphase CT images. Methods A total of 71 histologically-proven liver tumors including 49 benign and 22 malignant lesions were evaluated with the proposed CAD system to evaluate its performance. Tumors were identified by the user and then segmented using a region growing algorithm. After tumor segmentation, three kinds of features were obtained for each tumor, including texture, shape, and kinetic curve. The texture was quantified using 3 dimensional (3-D) texture data of the tumor based on the grey level co-occurrence matrix (GLCM). Compactness, margin, and an elliptic model were used to describe the 3-D shape of the tumor. The kinetic curve was established from each phase of tumor and represented as variations in density between each phase. Backward elimination was used to select the best combination of features, and binary logistic regression analysis was used to classify the tumors with leave-one-out cross validation. Results The accuracy and sensitivity for the texture were 71.82% and 68.18%, respectively, which were better than for the shape and kinetic curve under closed specificity. Combining all of the features achieved the highest accuracy (58/71, 81.69%), sensitivity (18/22, 81.82%), and specificity (40/49, 81.63%). The Az value of combining all features was 0.8713. Conclusions Combining texture, shape, and kinetic curve features may be able to differentiate benign from malignant tumors in the liver using our proposed CAD system.

AB - Background and objective Liver cancer is the tenth most common cancer in the USA, and its incidence has been increasing for several decades. Early detection, diagnosis, and treatment of the disease are very important. Computed tomography (CT) is one of the most common and robust imaging techniques for the detection of liver cancer. CT scanners can provide multiple-phase sequential scans of the whole liver. In this study, we proposed a computer-aided diagnosis (CAD) system to diagnose liver cancer using the features of tumors obtained from multiphase CT images. Methods A total of 71 histologically-proven liver tumors including 49 benign and 22 malignant lesions were evaluated with the proposed CAD system to evaluate its performance. Tumors were identified by the user and then segmented using a region growing algorithm. After tumor segmentation, three kinds of features were obtained for each tumor, including texture, shape, and kinetic curve. The texture was quantified using 3 dimensional (3-D) texture data of the tumor based on the grey level co-occurrence matrix (GLCM). Compactness, margin, and an elliptic model were used to describe the 3-D shape of the tumor. The kinetic curve was established from each phase of tumor and represented as variations in density between each phase. Backward elimination was used to select the best combination of features, and binary logistic regression analysis was used to classify the tumors with leave-one-out cross validation. Results The accuracy and sensitivity for the texture were 71.82% and 68.18%, respectively, which were better than for the shape and kinetic curve under closed specificity. Combining all of the features achieved the highest accuracy (58/71, 81.69%), sensitivity (18/22, 81.82%), and specificity (40/49, 81.63%). The Az value of combining all features was 0.8713. Conclusions Combining texture, shape, and kinetic curve features may be able to differentiate benign from malignant tumors in the liver using our proposed CAD system.

KW - Computed tomography

KW - Diagnosis

KW - Elliptic model

KW - Grey level co-occurrence matrix

KW - Kinetic curve

KW - Liver

UR - http://www.scopus.com/inward/record.url?scp=85017661100&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017661100&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2017.04.008

DO - 10.1016/j.cmpb.2017.04.008

M3 - Article

C2 - 28552125

AN - SCOPUS:85017661100

VL - 145

SP - 45

EP - 51

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

ER -