Skip to main content

Evaluation of ultrasonic fibrosis diagnostic system using convolutional network for ordinal regression



Diagnosis of liver fibrosis is important for establishing treatment and assessing the risk of carcinogenesis. Ultrasound imaging is an excellent diagnostic method as a screening test in terms of non-invasiveness and simplicity. The purpose of this study was to automatically diagnose liver fibrosis using ultrasound images to reduce the burden on physicians.


We proposed and implemented a system for extracting regions of liver parenchyma utilizing U-Net. Using regions of interest, the stage of fibrosis was classified as F0, F1, F2, F3, or F4 utilizing CORALNet, an ordinal regression model based on ResNet18. The effectiveness of the proposed system was verified.


The system implemented using U-Net had a maximum mean Dice coefficient of 0.929. The results of classification of liver fibrosis utilizing CORALNet had a mean absolute error (MAE) of 1.22 and root mean square error (RMSE) of 1.60. The per-case results had a MAE of 1.55 and RMSE of 1.34.


U-Net extracted regions of liver parenchyma from the images with high accuracy, and CORALNet showed effectiveness using ordinal information to classify fibrosis in the images. As a future task, we will study a model that is less dependent on teaching data.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5


  1. 1.

    Virmani J, Kumar V, Kalra N, Khandelwal N (2013) SVM-based characterisation of liver cirrhosis by singular value decomposition of GLCM matrix. Int J Artif Intell Soft Comput 3(3):276–296

    Article  Google Scholar 

  2. 2.

    Meng D, Zhang L, Cao G, Cao W, Zhang G, Hu B (2017) Liver fibrosis classification based on transfer learning and FCNet for ultrasound images. Ieee Access 5:5804–5810

    Google Scholar 

  3. 3.

    Milletari F, Navab N, Ahmadi SA (2016) V-net: fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV). IEEE, 565–571

  4. 4.

    Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In international conference on medical image computing and computer-assisted intervention. Springer, Cham. 234–241

  5. 5.

    Li L, Lin HT (2006) Ordinal regression by extended binary classification. Adv Neural Inf Process Syst 19:865–872

    Google Scholar 

  6. 6.

    Niu Z, Zhou M, Wang L, Gao X, Hua G (2016) Ordinal regression with multiple output cnn for age estimation. In proceedings of the IEEE conference on computer vision and pattern recognition, 4920–4928

  7. 7.

    Cao W, Mirjalili V, Raschka S (2020) Rank consistent ordinal regression for neural networks with application to age estimation. Pattern Recogn Lett 140:325–331

    Article  Google Scholar 

  8. 8.

    Masuzaki R, Tateishi R, Yoshida H, Goto E, Sato T, Ohki T, Goto T, Yoshida H, Kanai F, Sugioka Y, Ikeda H, Shiina S, Kawabe T, Omata M (2008) Comparison of liver biopsy and transient elastography based on clinical relevance. Can JGastroenterol 22(9):753–757.

    Article  Google Scholar 

  9. 9.

    Masuzaki R, Kanda T, Sasaki R, Matsumoto N, Ogawa M, Matsuoka S, Karp SJ, Moriyama M (2020) Noninvasive assessment of liver fibrosis: current and future clinical and molecular perspectives. Int J Mol Sci 21(14):4906.

    CAS  Article  PubMed Central  Google Scholar 

  10. 10.

    Yoneda M, Honda Y, Nogami A, Imajo K, Nakajima A (2020) Advances in ultrasound elastography for nonalcoholic fatty liver disease. J Med Ultrason 47(4):521–533.

    Article  Google Scholar 

Download references


The authors gratefully acknowledge the financial support by the Japan Society for the Promotion of Science, KAKENHI Grants 20H02113 and 18H03548, and the Saitama Prefecture New Technology and Product Development Subsidy Project.

Author information



Corresponding author

Correspondence to Norihiro Koizumi.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical standard

Approval was obtained from the ethics committee of Nihon University Itabashi Hospital (RK-200908–4). The procedures used in this study adhere to the tenets of the Declaration of Helsinki.

Informed consent

Informed consent was obtained from all individual participants included in the study.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Saito, R., Koizumi, N., Nishiyama, Y. et al. Evaluation of ultrasonic fibrosis diagnostic system using convolutional network for ordinal regression. Int J CARS (2021).

Download citation


  • Ultrasound image
  • Deep learning
  • Liver fibrosis