Journal Home > Volume 26 , Issue 2
Tsinghua Science and Technology 2021, 26(2): 199-207 https://doi.org/10.26599/TST.2019.9010058
Open Access | Issue | Published: 24 July 2020

Study of Texture Segmentation and Classification for Grading Small Hepatocellular Carcinoma Based on CT Images

Show Author's Information Bei Hui( ),  Yanbo Liu,  Jiajun Qiu,  Likun Cao,  Lin Ji,  Zhiqiang He
School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China.
West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu 610041, China.
Department of Radiology of Peking Union Medical College Hospital, Beijing 100032, China.
Department of Radiology, West China Hospital, Sichuan University, Chengdu 610041, China.
Keywords:
grading of Small Hepatocellular CarCinoma (SHCC), Gray-Level Co-occurrence Matrix (GLCM), texture clustering, super-resolution reconstruction
Cite this article:
Hui B, Liu Y, Qiu J, et al. Study of Texture Segmentation and Classification for Grading Small Hepatocellular Carcinoma Based on CT Images. Tsinghua Science and Technology, 2021, 26(2): 199-207. https://doi.org/10.26599/TST.2019.9010058
Download citation
EndNote(RIS)
BibTeX

621

Views

33

Downloads

Citations

12

Crossref

N/A

WoS

15

Scopus

2

CSCD

Abstract Full text About this article

To grade Small Hepatocellular CarCinoma (SHCC) using texture analysis of CT images, we retrospectively analysed 68 cases of Grade II (medium-differentiation) and 37 cases of Grades III and IV (high-differentiation). The grading scheme follows 4 stages: (1) training a Super Resolution Generative Adversarial Network (SRGAN) migration learning model on the Lung Nodule Analysis 2016 Dataset, and employing this model to reconstruct Super Resolution Images of the SHCC Dataset (SR-SHCC) images; (2) designing a texture clustering method based on Gray-Level Co-occurrence Matrix (GLCM) to segment tumour regions, which are Regions Of Interest (ROIs), from the original and SR-SHCC images, respectively; (3) extracting texture features on the ROIs; (4) performing statistical analysis and classifications. The segmentation achieved accuracies of 0.9049 and 0.8590 in the original SHCC images and the SR-SHCC images, respectively. The classification achived an accuracy of 0.838 and an Area Under the ROC Curve (AUC) of 0.84. The grading scheme can effectively reduce poor impacts on the texture analysis of SHCC ROIs. It may play a guiding role for physicians in early diagnoses of medium-differentiation and high-differentiation in SHCC.


menu
Abstract
Full text
Outline
About this article

Study of Texture Segmentation and Classification for Grading Small Hepatocellular Carcinoma Based on CT Images

Show Author's information Bei Hui( ), Yanbo Liu, Jiajun Qiu, Likun Cao, Lin Ji, Zhiqiang He
School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China.
West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu 610041, China.
Department of Radiology of Peking Union Medical College Hospital, Beijing 100032, China.
Department of Radiology, West China Hospital, Sichuan University, Chengdu 610041, China.

Abstract

To grade Small Hepatocellular CarCinoma (SHCC) using texture analysis of CT images, we retrospectively analysed 68 cases of Grade II (medium-differentiation) and 37 cases of Grades III and IV (high-differentiation). The grading scheme follows 4 stages: (1) training a Super Resolution Generative Adversarial Network (SRGAN) migration learning model on the Lung Nodule Analysis 2016 Dataset, and employing this model to reconstruct Super Resolution Images of the SHCC Dataset (SR-SHCC) images; (2) designing a texture clustering method based on Gray-Level Co-occurrence Matrix (GLCM) to segment tumour regions, which are Regions Of Interest (ROIs), from the original and SR-SHCC images, respectively; (3) extracting texture features on the ROIs; (4) performing statistical analysis and classifications. The segmentation achieved accuracies of 0.9049 and 0.8590 in the original SHCC images and the SR-SHCC images, respectively. The classification achived an accuracy of 0.838 and an Area Under the ROC Curve (AUC) of 0.84. The grading scheme can effectively reduce poor impacts on the texture analysis of SHCC ROIs. It may play a guiding role for physicians in early diagnoses of medium-differentiation and high-differentiation in SHCC.

Keywords: grading of Small Hepatocellular CarCinoma (SHCC), Gray-Level Co-occurrence Matrix (GLCM), texture clustering, super-resolution reconstruction

References(31)

[1]
P. Bertuccio, F. Turati, G. Carioli, T. Rodriguez, C. Lavecchia, M. Malvezzi, and E. Negri, Global trends and predictions in hepatocellular carcinoma mortality, Journal of Hepatology, vol. 67, no. 2, pp. 302-309, 2017.
DOI Google Scholar
[2]
P. Huang and Y. Lai, Effective segmentation and classification for HCC biopsy images, Pattern Recognition, vol. 43, no. 4, pp. 1550-1563, 2010.
DOI Google Scholar
[3]
C. Atupelage, H. Nagahashi, F. Kimura, M. Yamaguchi, T. Abe, A. Hashiguchi, and M. Sakamoto, Computational cell classification methodology for hepatocellular carcinoma, in Proc. of International Conference on Advances in ICT for Emerging Regions, Bauddhaloka Mawatha, Sri Lanka, pp. 21-27, 2013.
DOI
[4]
C. Atupelage, H. Nagahashi, M. Yamaguchi, T. Abe, A. Hashiguchi, and M. Sakamoto, Multifractal feature descriptor for grading hepatocellular carcinoma, presented at the 23rd Annu. Meeting International Conference on Pattern Recognition, Amsterdam, the Netherlands, 2016.
[5]
H. Lin, L. Lin, G. Wang, N. Zuo, Z. Zhan, S. Xie, G. Chen, J. Chen, and S. Zhou, Label-free classification of hepatocellular-carcinoma grading using second harmonic generation microscopy, Biomedical Optics Express, vol. 9, no. 8, pp. 3783-3797, 2018.
DOI Google Scholar
[6]
A. H. Mir, M. Hanmandlu, and S. N. Tandon, Texture analysis of CT images, IEEE Engineering in Medicine and Biology Magazine, vol. 14, no. 6, pp. 781-786, 1995.
DOI Google Scholar
[7]
Chinese Society of Liver Cancer, Chinese Anti-Cancer Association, Liver Cancer Study Group, Chinese Society of Hepatology, Chinese Medical Association, and Chinese Society of Pathology, Evidence-based practice guidelines for the standardized pathological diagnosis of primary liver cancer in China (2015 update), Journal of Clinical Hepatology, vol. 23, no. 5, pp. 321-327, 2015.
Google Scholar
[8]
J. Liu, Y. Pan, M. Li, Z. Chen, L. Tang, C. Lu, and J. X. Wang, Applications of deep learning to MRI images: A survey, Big Data Mining and Analytics, vol. 1, no. 1, pp. 1-18, 2018.
DOI Google Scholar
[9]
J. Lötsch, F. Lerch, R. Djaldetti, I. Tegder, and A. Ultsch, Identification of disease-distinct complex biomarker patterns by means of unsupervised machine-learning using an interactive R toolbox (Umatrix), Big Data Analytics, vol. 3, no. 1, p. 5, 2018.
DOI Google Scholar
[10]
J. Qiao, H. Song, and K. Zhang, Image super-resolution using conditional generative adversarial network, IET Image Processing, vol. 13, no. 4, pp. 2673-2677, 2019.
DOI Google Scholar
[11]
C. Ledig, L. Theis, F. Huszar, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, and Z. Wang, Photo-realistic single image super-resolution using a generative adversarial network, Computer Vision & Pattern Recognition, .
DOI Google Scholar
[12]
D. A. Clausi, K-means Iterative Fisher (KIF) unsupervised clustering algorithm applied to image texture segmentation, Pattern Recognition, vol. 35, no. 9, pp. 1959-1972, 2002.
DOI Google Scholar
[13]
B. Yu, L. Yan, and F. Chao, An improved watershed segmentation method of medical image, Applied Mechanics and Materials, vols. 719&720, no. 3, pp. 1009-1012, 2015.
DOI Google Scholar
[14]
J. Chen and S. Liu, A medical image segmentation method based on watershed transform, presented at the 5th Annu. Meeting International Conference on Computer & Information Technology, Shanghai, China, 2005.
[15]
R. M. Haralick, K. Shanmugam, and I. H. Dinstein, Textural features for image classification, IEEE Transactions on Systems, Man & Cybernetics, vol. 3, no. 6, pp. 610-621, 1973.
DOI Google Scholar
[16]
W. Zhou, L. Zhang, K. Wang, S. Chen, G. Wang, Z. Liu, and C. Liang, Malignancy characterization of hepatocellular carcinomas based on texture analysis of contrast-enhanced MR images, Journal of Magnetic Resonance Imaging, vol. 45, no. 5, pp. 1476-1484, 2016.
DOI Google Scholar
[17]
D. Mahmoud-Ghoneim, G. Toussaint, J. Constans, and J. D. de Carteines, Three dimensional texture analysisin MRI: Preliminary evaluation in gliomas, Magnetic Resonance Imaging, vol. 21, no. 9, pp. 983-987, 2003.
DOI Google Scholar
[18]
M. S. M. Rahim, T. Saba, F. Nayer, and A. Z. Syed, 3D texture features mining for MRI brain tumor identification, 3D Research,, vol. 5, no. 3, pp. 1-8, 2014.
DOI Google Scholar
[19]
T. Y. Kim, N. H. Cho, G. B. Jeong, E. Bengtsson, and H. K. Choi, 3D texture analysis in renal cell carcinoma tissue image grading, Computational and Mathematical Methods in Medicine, vol. 2014, pp. 1-12, 2014.
DOI Google Scholar
[20]
D. W. Zimmerman, Comparative power of student T test and Mann-Whitney U Test for unequal sample sizes and variances, Journal of Experimental Education, vol. 55, no. 3, pp. 171-174, 2014.
DOI Google Scholar
[21]
M. H. Horng, Performance evaluation of multiple classification of the ultrasonic supraspinatus images by using ML, RBFNN, and SVM classifiers, Expert System with Application, vol. 37, no. 41, pp. 46-55, 2010.
DOI Google Scholar
[22]
K. T. Gribbon and D. G. Bailey, A novel approach to real-time bilinear interpolation, IEEE International Workshop on Electronic Design, .
DOI Google Scholar
[23]
J. Lu, X. Si, and S. Wu, An improved bilinear interpolation algorithm of converting standard-definition television images to high-definition television images, presented at the 2nd Annu. Meeting WASE International Conference on Information Engineering, Taiyuan, China, 2009.
[24]
X. Zhao, S. Yun, Y. Dong, J. WANG, and L. Zhai, Kind of super-resolution method of CCD image based on wavelet and bicubic interpolation, Application Research of Computers, vol. 26, no. 6, pp. 2365-2367, 2009.
Google Scholar
[25]
D. Feng, F. Chen, and W. Xu, Efficient leave-one-out strategy for supervised feature selection, Tsinghua Science and Technology, vol. 18, no. 6, pp. 629-635, 2013.
DOI Google Scholar
[26]
P. Phoungphol, Y. Zhang, and Y. Zhao, Robust multiclass classification for learning from imbalanced biomedical data, Tsinghua Science and Technology, vol. 17, no. 6, pp. 619-628, 2012.
DOI Google Scholar
[27]
Z. Cai, R. Goebel, M. R. Salavatipour, and G. Lin, Selecting dissimilar genes for multi-class classification, an application in cancer subtyping, BioMed Central Bioinformatics, vol. 8, no. 1, p. 206, 2007.
DOI Google Scholar
[28]
Z. Cai, M. Heydari, and G. Lin, Clustering binary Oligonucleotide fingerprint vectors for DNA clone classification analysis, Journal of Combinatorial Optimization, vol. 9, no. 2, pp. 199-211, 2005.
DOI Google Scholar
[29]
K. Yang, Z. Cai, J. Li, and G. Li, A stable gene selection in microarray data analysis, BioMed Central Bioinformatics, vol. 7, no. 1, p. 228, 2006.
DOI Google Scholar
[30]
Z. Cai, T. Zhang, and X. Wan, A computational framework for influenza antigenic cartography, PLoS Computational Biology, vol. 6, no. 10, pp. 1-14, 2010.
DOI Google Scholar
[31]
R. J. Gillies, P. E. Kinahan, and H. Hricak, Radiomics: Images are more than pictures, they are data, Radiology, vol. 278, no. 2, pp. 563-577, 2016.
DOI Google Scholar
Publication history
Copyright
Acknowledgements
Rights and permissions

Publication history

Received: 29 September 2019
Revised: 03 December 2019
Accepted: 02 January 2020
Published: 24 July 2020
Issue date: April 2021

Copyright

© The author(s) 2021.

Acknowledgements

This work was supported by the National Key R&D Program of China (No. 2018YFC0807500).

Rights and permissions

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).

Return