Classification of Liver Diseases Based on Ultrasound Image Texture Features

被引：34

作者：

Xu, Sendren Sheng-Dong ^{[1
]}

Chang, Chun-Chao ^{[2
,3
]}

Su, Chien-Tien ^{[4
,5
,6
]}

Pham Quoc Phu ^{[1
]}

机构：

[1] Natl Taiwan Univ Sci & Technol, Grad Inst Automat & Control, Taipei 10607, Taiwan

[2] Taipei Med Univ Hosp, Dept Internal Med, Div Gastroenterol & Hepatol, Taipei 11031, Taiwan

[3] Taipei Med Univ, Coll Med, Sch Med, Dept Internal Med, Taipei 11031, Taiwan

[4] Taipei Med Univ Hosp, Dept Occupat Med, Taipei 11031, Taiwan

[5] Taipei Med Univ, Coll Med, Sch Med, Dept Family Med, Taipei 11031, Taiwan

[6] Taipei Med Univ, Coll Publ Hlth & Nutr, Sch Publ Hlth, Taipei 11031, Taiwan

来源：

APPLIED SCIENCES-BASEL | 2019年 / 9卷 / 02期

关键词：

classification; F-score; gray-level co-occurrence matrix (GLCM); gray-level run-length matrix (GLRLM); hepatocellular carcinoma (HCC); liver cancer; liver abscess; image texture; sequential backward selection (SBS); sequential forward selection (SFS); support vector machine (SVM); ultrasound images; COMPUTER-AIDED DIAGNOSIS; HEPATOCELLULAR-CARCINOMA; TISSUE CHARACTERIZATION; MR ELASTOGRAPHY; SEGMENTATION; INFORMATION; TOMOGRAPHY; SELECTION; CT;

D O I：

10.3390/app9020342

中图分类号：

O6 [化学];

学科分类号：

0703 ;

摘要：

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-scoreare 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.

引用

页数：25

共 56 条

[1] Albinsson J, 2018, APPL SCI-BASEL, V8, DOI [10.3390/app8040662, 10.3390/app8050662]
[2] [Anonymous], 1979, Estimation of Dependences Based on Empirical Data
[3] [Anonymous], 1975, Comput. Graph. Image Process., DOI [DOI 10.1016/S0146-664X(75)80008-6, 10.1016/s0146-664x(75)80008-6]
[4] Enhancement approach for liver lesion diagnosis using unenhanced CT images
Balagourouchetty, Lakshmipriya
Pragatheeswaran, Jayanthi K.
Pottakkat, Biju
Govindarajalou, Ramkumar
[J]. IET COMPUTER VISION, 2018, 12 (08) : 1078 - 1087
[5] Random field models in the textural analysis of ultrasonic images of the liver
Bleck, JS
Ranft, U
Gebel, M
Hecker, H
WesthoffBleck, M
Thiesemann, C
Wagner, S
[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 1996, 15 (06) : 796 - 801
[6] Ultrasound-Based Liver Stiffness Surveillance in Patients Treated for Chronic Hepatitis B or C
Chen, Sheng-Hung
Peng, Cheng-Yuan
[J]. APPLIED SCIENCES-BASEL, 2018, 8 (04):
[7] Chen YW, 2006, STUD FUZZ SOFT COMP, V207, P315
[8] Choi Byung Ihn, 2004, Liver Transpl, V10, pS20, DOI 10.1002/lt.20038
[9] USE OF GRAY VALUE DISTRIBUTION OF RUN LENGTHS FOR TEXTURE ANALYSIS
CHU, A
SEHGAL, CM
GREENLEAF, JF
[J]. PATTERN RECOGNITION LETTERS, 1990, 11 (06) : 415 - 419
[10] Cruz-Gómez C, 2013, 2013 INTERNATIONAL CONFERENCE ON TECHNOLOGICAL ADVANCES IN ELECTRICAL, ELECTRONICS AND COMPUTER ENGINEERING (TAEECE), P88

← 1 2 3 4 5 6 →