Skip to main content
SpringerLink
Log in

Non-invasive precise staging of liver fibrosis using deep residual network model based on plain CT images

  • Original Article
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Purpose

The aim of this study was to explore the application of five-class deep residual network models based on plain CT images and clinical features for the precise staging of liver fibrosis.

Methods

This retrospective clinical study included 347 patients who underwent liver CT, with pathological staging of liver fibrosis as the gold standard. We established three ResNet models to stage liver fibrosis. The output diagnosis labels of models were 0, 1, 2, 3 and 4, which correspond to F0, F1, F2, F3, and F4 stages. Confusion matrices were used to evaluate the performances of models to precisely stage liver fibrosis. The performance for diagnosing cirrhosis (F4), advanced fibrosis (≥ F3) and significant fibrosis (≥ F2) of models was evaluated with receiver operating characteristic (ROC) analyses.

Results

The kappa coefficients of the five-class ResNet model (based on plain CT images), the five-class ResNet clinical model (based on clinical features), and the five-class mixed ResNet model (based on plain CT images and clinical features) for precise staging liver fibrosis were 0.566, 0.306, and 0.63, respectively. The recall rates and precision rates for F0, F1, F2, and F3 of three models were lower than 60%. The ROC AUC values of the five-class ResNet model, the five-class ResNet clinical model, and the five-class mixed ResNet model for diagnosing cirrhosis, advanced fibrosis, and significant fibrosis were 0.95, 0.88, and 0.82, 0.80, 0.72, and 0.70, 0.95, 0.90, and 0.83, respectively.

Conclusions

The five-class ResNet models are of high value in the diagnosis of liver cirrhosis, advanced liver fibrosis, and significant liver fibrosis. However, for the precise staging of liver fibrosis, the models cannot accurately distinguish other liver fibrosis stages except F4. Plain CT images combined with clinical features have the potential to improve the performance of the ResNet models in diagnosing liver fibrosis.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig.3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, van Stiphout RG, Granton P, Zegers CM, Gillies R, Boellard R, Dekker A, Aerts HJ (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 48(4):441–446

    Article  PubMed  PubMed Central  Google Scholar 

  2. Yasaka K, Akai H, Kunimatsu A, Abe O, Kiryu S (2018) Deep learning for staging liver fibrosis on CT: a pilot study. Eur Radiol 28(11):4578–4585

    Article  PubMed  Google Scholar 

  3. Yasaka K, Akai H, Kunimatsu A, Abe O, Kiryu S (2018) Liver fibrosis: deep convolutional neural network for staging by using gadoxetic acid-enhanced hepatobiliary phase MR images. Radiology 287(1):146–155

    Article  PubMed  Google Scholar 

  4. Park HJ, Park B, Lee SS (2020) Radiomics and deep learning: hepatic applications. Korean J Radiol 21(4):387–401

    Article  PubMed  PubMed Central  Google Scholar 

  5. Treacher A, Beauchamp D, Quadri B, Fetzer D, Vij A, Yokoo T, Montillo A (2019) Deep learning convolutional neural networks for the estimation of liver fibrosis severity from ultrasound texture. Proc SPIE Int Soc Opt Eng 10950:109503E

    PubMed  PubMed Central  Google Scholar 

  6. Yu Y, Wang J, Ng CW, Ma Y, Mo S, Fong ELS, Xing J, Song Z, Xie Y, Si K, Wee A, Welsch RE, So PTC, Yu H (2018) Deep learning enables automated scoring of liver fibrosis stages. Sci Rep 8(1):16016

    Article  PubMed  PubMed Central  Google Scholar 

  7. Bedossa P, Poynard T (1996) An algorithm for the grading of activity in chronic hepatitis C. The METAVIR Cooperative Study Group. Hepatology 24(2):289–293

    Article  CAS  PubMed  Google Scholar 

  8. Lee JH, Joo I, Kang TW, Paik YH, Sinn DH, Ha SY, Kim K, Choi C, Lee G, Yi J, Bang WC (2020) Deep learning with ultrasonography: automated classification of liver fibrosis using a deep convolutional neural network. Eur Radiol 30(2):1264–1273

    Article  PubMed  Google Scholar 

  9. Association CSoHCM, Association CSoGCM (2020) Chinese Society of Infectious Diseases CMA. Consensus on the diagnosis and treatment of hepatic fibrosis (2019). J Dig Dis 21(3): 127–138

  10. Li Q, Yu B, Tian X, Cui X, Zhang R, Guo Q (2020) Deep residual nets model for staging liver fibrosis on plain CT images. Int J Comput Assist Radiol Surg 15(8):1399–1406

    Article  PubMed  Google Scholar 

  11. Kojiro M, Shimamatsu K, Kage M (1995) Pathomorphologic comparison of hepatitis C virus-related and hepatitis B virus-related cirrhosis bearing hepatocellular carcinoma. Princess Takamatsu Symp 25:179–184

    CAS  PubMed  Google Scholar 

  12. Tampi C (2012) Pathology for the HPB Surgeon. Indian J Surg 74(1):67–72

    Article  PubMed  Google Scholar 

  13. Geng XX, Lin JM, Yang XX, Huang RG, Jiang N (2009) Comparison of liver pathohistological and clinical characteristics between chronic HBV carriers and chronic hepatitis B patients with mild elevation in ALT. Zhonghua Gan Zang Bing Za Zhi 17(10):735–739

    PubMed  Google Scholar 

  14. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Conference proceedings: proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  15. Mathew J, Pang CK, Luo M, Leong WH (2018) Classification of imbalanced data by oversampling in kernel space of support vector machines. IEEE Trans Neural Netw Learn Syst 29(9):4065–4076

    Article  PubMed  Google Scholar 

  16. Xie YN, Yu L, Guan GH, He YJ (2018) An overlapping cell image synthesis method for imbalance data. Anal Cell Pathol (Amst) 2018:7919503

    Google Scholar 

  17. Wang K, Lu X, Zhou H, Gao Y, Zheng J, Tong M, Wu C, Liu C, Huang L, Jiang T, Meng F, Lu Y, Ai H, Xie XY, Yin LP, Liang P, Tian J, Zheng R (2019) Deep learning Radiomics of shear wave elastography significantly improved diagnostic performance for assessing liver fibrosis in chronic hepatitis B: a prospective multicentre study. Gut 68(4):729–741

    Article  CAS  PubMed  Google Scholar 

  18. Warrens MJ (2013) Conditional inequalities between Cohen’s kappa and weighted kappas. Stat Methodol 10(1):14–22

    Article  Google Scholar 

  19. Vilar-Gomez E, Chalasani N (2018) Non-invasive assessment of non-alcoholic fatty liver disease: clinical prediction rules and blood-based biomarkers. J Hepatol 68(2):305–315

    Article  CAS  PubMed  Google Scholar 

  20. Dai YN, Tu YX, Meng D, Chen MJ, Zhang JJ, Gong YH, Tong YX, Wang MS, Pan HY, Huang HJ (2019) Serum proteomic changes as candidate biomarkers of intermediate liver fibrosis in chronic hepatitis B infection. OMICS 23(3):167–179

    Article  CAS  PubMed  Google Scholar 

  21. Yen YH, Kuo FY, Kee KM, Chang KC, Tsai MC, Hu TH, Lu SN, Wang JH, Hung CH, Chen CH (2018) APRI and FIB-4 in the evaluation of liver fibrosis in chronic hepatitis C patients stratified by AST level. PLoS One 13(6): e0199760

  22. Papadopoulos N, Vasileiadi S, Papavdi M, Sveroni E, Antonakaki P, Dellaporta E, Koutli E, Michalea S, Manolakopoulos S, Koskinas J, Deutsch M (2019) Liver fibrosis staging with combination of APRI and FIB-4 scoring systems in chronic hepatitis C as an alternative to transient elastography. Ann Gastroenterol 32(5):498–503

    PubMed  PubMed Central  Google Scholar 

  23. Chrostek L, Przekop D, Gruszewska E, Gudowska-Sawczuk M, Cylwik B (2019) Noninvasive indirect markers of liver fibrosis in alcoholics. Biomed Res Int 2019:3646975

    Article  PubMed  PubMed Central  Google Scholar 

  24. Yang M, Jiang L, Wang Y, Li X, Zou Z, Han T, Nan Y, Lu F, Zhao J (2019) Step layered combination of noninvasive fibrosis models improves diagnostic accuracy of advanced fibrosis in nonalcoholic fatty liver disease. J Gastrointestin Liver Dis 28(3):289–296

    Article  PubMed  Google Scholar 

  25. Pickhardt PJ, Graffy PM, Said A, Jones D, Welsh B, Zea R, Lubner MG (2019) Multiparametric CT for noninvasive staging of hepatitis C virus-related liver fibrosis: correlation with the [2]histopathologic fibrosis score. AJR Am J Roentgenol 212(3):547–553

    Article  PubMed  PubMed Central  Google Scholar 

  26. Lubner MG, Jones D, Said A, Kloke J, Lee S, Pickhardt PJ (2018) Accuracy of liver surface nodularity quantification on MDCT for staging hepatic fibrosis in patients with hepatitis C virus. Abdom Radiol (NY) 43(11):2980–2986

    Article  Google Scholar 

  27. Pickhardt PJ, Malecki K, Hunt OF, Beaumont C, Kloke J, Ziemlewicz TJ, Lubner MG (2017) Hepatosplenic volumetric assessment at MDCT for staging liver fibrosis. Eur Radiol 27(7):3060–3068

    Article  PubMed  Google Scholar 

  28. Parola M, Pinzani M (2019) Liver fibrosis: pathophysiology, pathogenetic targets and clinical issues. Mol Aspects Med 65:37–55

    Article  CAS  PubMed  Google Scholar 

  29. Zhang CY, Yuan WG, He P, Lei JH, Wang CX (2016) Liver fibrosis and hepatic stellate cells: etiology, pathological hallmarks and therapeutic targets. World J Gastroenterol 22(48):10512–10522

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Li H (2020) Angiogenesis in the progression from liver fibrosis to cirrhosis and hepatocelluar carcinoma. Expert Rev Gastroenterol Hepatol 15(3):217–233

    Article  PubMed  Google Scholar 

  31. Chiu NC, Su CW, Liu CA, Huang YH, Chiou YY (2017) Interval to vascularization development in cirrhotic precursor nodules in patients with hepatitis B and C virus co-infections. PLoS One 12(6): e0178841

Download references

Funding

Funding was provided by National Natural Science Foundation of China (Grant Nos. 81771893, 81471718).

Author information

Authors and Affiliations

  1. Department of Radiology, Shengjing Hospital of China Medical University, No. 36, Sanhao Street, Heping District, Shenyang, Liaoning, China

    Qiuju Li & Qiyong Guo

  2. Institute of Advanced Research, Infervision Medical Technology Co., Ltd., Beijing, China

    Han Kang & Rongguo Zhang

Authors
  1. Qiuju Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Han Kang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Rongguo Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Qiyong Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Qiyong Guo.

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

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, Q., Kang, H., Zhang, R. et al. Non-invasive precise staging of liver fibrosis using deep residual network model based on plain CT images. Int J CARS 17, 627–637 (2022). https://doi.org/10.1007/s11548-022-02573-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-022-02573-8

Keywords

Search

Navigation