Skip to main content
Log in

Deep residual nets model for staging liver fibrosis on plain CT images

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

Abstract

Purpose

The early diagnosis of liver fibrosis is crucial for the prevention of liver cirrhosis and liver cancer. As gold standard for staging liver fibrosis, liver biopsy is an invasive procedure that carries the risk of serious complications. The aim of this study was to evaluate the performance of the residual neural network (ResNet), a non-invasive methods, for staging liver fibrosis using plain CT images.

Methods

This retrospective study involved 347 patients subjected to liver CT scanning and liver biopsy. For each patient, we selected three axial images adjacent to the puncture location in the eighth or ninth inter-space on the right side. After processing and enhancement (rotation, translation, and amplification), these images were used as input data for the ResNet model. The model used a fivefold cross-validation method. In each fold, the images of approximately 80% of the total sample size (278 patients) were used for training the ResNet model, the other 20% (69 patients) were used for testing the trained network, with the liver biopsy pathology results as gold standard. The proportion of patients in each fibrosis stage was equal for training and test groups. The final result was the mean of the fivefold cross-validation in the test group. The performance of the ResNet model was evaluated for the test group by receiver operating characteristic (ROC) analysis.

Results

For the ResNet model, the area under the ROC curve (AUC) for assessing cirrhosis (F4), advanced fibrosis (F3 or higher), significant fibrosis (F2 or higher), and mild fibrosis (F1 or higher) was 0.97, 0.94, 0.90, and 0.91, respectively.

Conclusions

The ResNet model analysis of plain CT images exhibited high diagnostic efficiency for liver fibrosis staging. As a convenient, fast, and economical non-invasive diagnostic method, the ResNet model can be used to assist radiologists and clinicians in liver fibrosis evaluations.

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

Access this article

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

Similar content being viewed by others

References

  1. Afdhal NH, Nunes D (2004) Evaluation of liver fibrosis: a concise review. Am J Gastroenterol 99(6):1160–1174

    PubMed  Google Scholar 

  2. Friedman SL (2003) Liver fibrosis-from bench to bedside. J Hepatol 38(suppl 1):38–53

    Google Scholar 

  3. Enomoto M, Ikura Y, Tamori A, Kozuka R, Motoyama H, Kawamura E, Hagihara A, Fujii H, Uchida-Kobayashi S, Morikawa H, Murakami Y, Kawada N (2018) Short-term histological evaluations after achieving a sustained virologic response to direct-acting antiviral treatment for chronic hepatitis C. United European Gastroenterol J 6(9):1391–1400

    PubMed  PubMed Central  Google Scholar 

  4. Cadranel JF, Rufat P, Degos F (2000) Practices of liver biopsy in France: results of a prospective nationwide survey. Hepatology 32(3):477–481

    CAS  PubMed  Google Scholar 

  5. Takyar V, Etzion O, Heller T, Kleiner DE, Rotman Y, Ghany MG, Fryzek N, Williams VH, Rivera E, Auh S, Liang TJ, Hoofnagle JH, Koh C (2017) Complications of percutaneous liver biopsy with Klatskin needles- a 36-year single-center experience. Aliment Pharmacol Ther 45(5):744–753

    CAS  PubMed  PubMed Central  Google Scholar 

  6. Goldin RD, Goldin JG, Burt AD, Dhillon PA, Hubscher S, Wyatt J, Patel N (1996) Intra-observer and inter-observer variation in the histopathological assessment of chronic viral hepatitis. J Hepatol 25(5):649–654

    CAS  PubMed  Google Scholar 

  7. Carey E, Carey WD (2010) Noninvasive tests for liver disease, fibrosis, and cirrhosis: Is liver biopsy obsolete? Cleve Clin J Med 77(8):519–527

    PubMed  Google Scholar 

  8. Yoshio S, Atsushi N, Yoshito I (2014) Limitations of liver biopsy and non-invasive diagnostic tests for the diagnosis of nonalcoholic fatty liver disease/nonalcoholic steatohepatitis. World J Gastroenterol 20(2):475–485

    Google Scholar 

  9. Shi Y, Guo Q, Xia F, Dzyubak B, Glaser KJ, Li Q, Li J, Ehman RL (2014) MR elastography for the assessment of hepatic fibrosis in patients with chronic hepatitis B infection: does histologic necroinflammation influence the measurement of hepatic stiffness? Radiology 273(1):88–98

    PubMed  PubMed Central  Google Scholar 

  10. Shi Y, Xia F, Li QJ, Li JH, Yu B, Li Y, An H, Glaser KJ, Tao S, Ehman RL, Guo QY (2016) Magnetic resonance elastography for the evaluation of liver fibrosis in chronic hepatitis B and C by using both gradient-recalled echo and spin-echo echo planar imaging: a prospective study. Am J Gastroenterol 111(6):823–833

    PubMed  Google Scholar 

  11. Huwart L, Sempoux C, Salameh N, Jamart J, Annet L, Sinkus R, Peeters F, ter Beek LC, Horsmans Y, Van Beers BE (2007) Liver fibrosis: noninvasive assessment with MR elastography versus aspartate aminotransferase-to-platelet ratio index. Radiology 245(2):458–466

    PubMed  Google Scholar 

  12. Abe T, Kuroda H, Fujiwara Y, Miyasaka A, Kamiyama N, Takikawa Y (2018) Accuracy of 2D shear wave elastography in the diagnosis of liver fibrosis in patients with chronic hepatitis C. J Clin Ultrasound 46(5):319–327

    PubMed  Google Scholar 

  13. Herrmann E, de Lédinghen V, Cassinotto C, Chu WC, Leung VY, Ferraioli G, Filice C, Castera L, Vilgrain V, Ronot M, Dumortier J, Guibal A, Pol S, Trebicka J, Jansen C, Strassburg C, Zheng R, Zheng J, Francque S, Vanwolleghem T, Vonghia L, Manesis EK, Zoumpoulis P, Sporea I, Thiele M, Krag A, Cohen-Bacrie C, Criton A, Gay J, Deffieux T, Friedrich-Rust M (2018) Assessment of biopsy-proven liver fibrosis by two-dimensional shear wave elastography: an individual patient data-based meta-analysis. Hepatology 67(1):260–272

    CAS  PubMed  Google Scholar 

  14. Joyce AS, Suleman V, Sudhir V, Farin A, Munir G (2017) Ultrasound shear wave elastography and liver fibrosis: a prospective multicenter study. World J Hepatol 9(1):38–47

    Google Scholar 

  15. Lubner MG, Malecki K, Kloke J, Ganeshan B, Pickhardt PJ (2017) Texture analysis of the liver at MDCT for assessing hepatic fibrosis. Abdom Radiol (NY) 42(8):2069–2078

    Google Scholar 

  16. Daginawala N, Li B, Buch K, Yu H, Tischler B, Qureshi MM, Soto JA, Anderson S (2016) Using texture analyses of contrast enhanced CT to assess hepatic fibrosis. Eur J Radiol 85(3):511–517

    PubMed  Google Scholar 

  17. Yu H, Touret AS, Li B, O’Brien M, Qureshi MM, Soto JA, Jara H, Anderson SW (2017) Application of texture analysis on parametric T1 and T2 maps for detection of hepatic fibrosis. J Magn Reson Imaging 45(1):250–259

    PubMed  Google Scholar 

  18. Yu H, Buch K, Li B, O’Brien M, Soto J, Jara H, Anderson SW (2015) Utility of texture analysis for quantifying hepatic fibrosis on proton density MRI. J Magn Reson Imaging 42(5):1259–1265

    PubMed  Google Scholar 

  19. Barry B, Buch K, Soto JA, Jara H, Nakhmani A, Anderson SW (2014) Quantifying liver fibrosis through the application of texture analysis to diffusion weighted imaging. Magn Reson Imaging 32(1):84–90

    PubMed  Google Scholar 

  20. House MJ, Bangma SJ, Thomas M, Gan EK, Ayonrinde OT, Adams LA, Olynyk JK, St Pierre TG (2015) Texture-based classification of liver fibrosis using MRI. J Magn Reson Imaging 41(2):322–328

    PubMed  Google Scholar 

  21. Yokoo T, Wolfson T, Iwaisako K, Peterson MR, Mani H, Goodman Z, Changchien C, Middleton MS, Gamst AC, Mazhar SM, Kono Y, Ho SB, Sirlin CB (2015) Evaluation of liver fibrosis using texture analysis on combined-contrast-enhanced magnetic resonance images at 3.0T. Biomed Res Int 2015:387653

    PubMed  PubMed Central  Google Scholar 

  22. Chen Y, Luo Y, Huang W, Hu D, Zheng RQ, Cong SZ, Meng FK, Yang H, Lin HJ, Sun Y, Wang XY, Wu T, Ren J, Pei S, Zheng Y, He Y, Hu Y, Yang N, Yan H (2017) Machine-learning-based classification of real-time tissue elastography for hepatic fibrosis in patients with chronic hepatitis B. Comput Biol Med 89:18–23

    PubMed  Google Scholar 

  23. Friedrich-Rust M, Ong MF, Martens S, Sarrazin C, Bojunga J, Zeuzem S, Herrmann E (2008) Performance of transient elastography for the staging of liver fibrosis: a meta-analysis. Gastroenterology 134(4):960–974

    PubMed  Google Scholar 

  24. Talwalkar JA, Kurtz DM, Schoenleber SJ, West CP, Montori VM (2007) Ultrasound-based transient elastography for the detection of hepatic fibrosis: systematic review and meta-analysis. Clin Gastroenterol Hepatol 5(10):1214–1220

    PubMed  Google Scholar 

  25. 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

    PubMed  Google Scholar 

  26. 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 (2018) 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

    PubMed  PubMed Central  Google Scholar 

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

    PubMed  Google Scholar 

  28. 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

    CAS  Google Scholar 

  29. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Conf Proc Proc IEEE Conf Comput Vis Pattern Recognit 2016:770–778

    Google Scholar 

  30. Kingma DP, Ba JL (2017) Adam: a method for stochastic optimization, Cornell University Library. Published 2014. http://arXiv.org/abs/1412.6980. Accessed 1 June 2017

  31. Rockey DC, Bissell DM (2006) Noninvasive measures of liver fibrosis. Hepatology 43(2 suppl 1):S113–S120

    CAS  PubMed  Google Scholar 

  32. Lebensztejn DM, Skiba E, Sobaniec-Lotowska M, Kaczmarski M (2005) A simple noninvasive index (APRI) predicts advanced liver fibrosis in children with chronic hepatitis B. Hepatology 41(6):1434–1435

    PubMed  Google Scholar 

  33. Li C, Li R, Zhan W (2018) Progress in non-invasive detection of liver fibrosis. Cancer Biol Med 15(2):124–136

    CAS  PubMed  PubMed Central  Google Scholar 

  34. Goshima S, Kanematsu M, Kobayashi T, Furukawa T, Zhang X, Fujita H, Watanabe H, Kondo H, Moriyama N, Bae K (2012) Staging hepatic fibrosis: computeraided analysis of hepatic contours on gadolinium ethoxybenzyl diethylenetriaminepentaacetic acid-enhanced hepatocyte-phase magnetic resonance imaging. Hepatology 55(1):328–329

    PubMed  Google Scholar 

  35. 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 

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

    PubMed  Google Scholar 

  37. Huang ZP, Zhang XL, Zeng J, Zheng J, Wang P, Zheng RQ (2014) Study of detection times for liver stiffness evaluation by shear wave elastography. World J Gastroenterol 20(28):9578–9584

    PubMed  PubMed Central  Google Scholar 

Download references

Funding

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

Author information

Authors and Affiliations

Authors

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.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (DOC 69 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, Q., Yu, B., Tian, X. et al. Deep residual nets model for staging liver fibrosis on plain CT images. Int J CARS 15, 1399–1406 (2020). https://doi.org/10.1007/s11548-020-02206-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-020-02206-y

Keywords

Navigation