Skip to main content

Deep learning for staging liver fibrosis on CT: a pilot study

Abstract

Objectives

To investigate whether liver fibrosis can be staged by deep learning techniques based on CT images.

Methods

This clinical retrospective study, approved by our institutional review board, included 496 CT examinations of 286 patients who underwent dynamic contrast-enhanced CT for evaluations of the liver and for whom histopathological information regarding liver fibrosis stage was available. The 396 portal phase images with age and sex data of patients (F0/F1/F2/F3/F4 = 113/36/56/66/125) were used for training a deep convolutional neural network (DCNN); the data for the other 100 (F0/F1/F2/F3/F4 = 29/9/14/16/32) were utilised for testing the trained network, with the histopathological fibrosis stage used as reference. To improve robustness, additional images for training data were generated by rotating or parallel shifting the images, or adding Gaussian noise. Supervised training was used to minimise the difference between the liver fibrosis stage and the fibrosis score obtained from deep learning based on CT images (FDLCT score) output by the model. Testing data were input into the trained DCNNs to evaluate their performance.

Results

The FDLCT scores showed a significant correlation with liver fibrosis stage (Spearman's correlation coefficient = 0.48, p < 0.001). The areas under the receiver operating characteristic curves (with 95% confidence intervals) for diagnosing significant fibrosis (≥ F2), advanced fibrosis (≥ F3) and cirrhosis (F4) by using FDLCT scores were 0.74 (0.64–0.85), 0.76 (0.66–0.85) and 0.73 (0.62–0.84), respectively.

Conclusions

Liver fibrosis can be staged by using a deep learning model based on CT images, with moderate performance.

Key Points

Liver fibrosis can be staged by a deep learning model based on magnified CT images including the liver surface, with moderate performance.

Scores from a trained deep learning model showed moderate correlation with histopathological liver fibrosis staging.

Further improvement are necessary before utilisation in clinical settings.

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

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

Abbreviations

AUC:

Area under the receiver operating characteristic curve

DCNN:

Deep convolutional neural network

DICOM:

Digital Imaging and Communications in Medicine

FDLCT :

Fibrosis score obtained from deep learning based on CT images

IQR:

Interquartile range

JPEG:

Joint Photographic Experts Group

MRE:

Magnetic resonance elastography

ROC:

Receiver operating characteristic

ROI:

Region of interest

TE:

Transient elastography

References

  1. 1.

    Forner A, Llovet JM, Bruix J (2012) Hepatocellular carcinoma. Lancet 379:1245–1255

    Article  Google Scholar 

  2. 2.

    Schuppan D, Afdhal NH (2008) Liver cirrhosis. Lancet 371:838–851

    CAS  Article  Google Scholar 

  3. 3.

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

    CAS  Article  Google Scholar 

  4. 4.

    Ichida F, Tsuji T, Omata M et al (1996) New Inuyama classification; new criteria for histological assessment of chronic hepatitis. Int Hepatol Commun 6:112–119

    Article  Google Scholar 

  5. 5.

    Rockey DC, Caldwell SH, Goodman ZD, Nelson RC, Smith AD (2009) Liver biopsy. Hepatology 49:1017–1044

    Article  Google Scholar 

  6. 6.

    Horowitz JM, Venkatesh SK, Ehman RL et al (2017) Evaluation of hepatic fibrosis: a review from the society of abdominal radiology disease focus panel. Abdom Radiol (NY) 42:2037–2053

    Article  Google Scholar 

  7. 7.

    Foucher J, Chanteloup E, Vergniol J et al (2006) Diagnosis of cirrhosis by transient elastography (FibroScan): a prospective study. Gut 55:403–408

    CAS  Article  Google Scholar 

  8. 8.

    Huwart L, Sempoux C, Salameh N et al (2007) Liver fibrosis: noninvasive assessment with MR elastography versus aspartate aminotransferase-to-platelet ratio index. Radiology 245:458–466

    Article  Google Scholar 

  9. 9.

    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444

    CAS  Article  Google Scholar 

  10. 10.

    Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing System 25 (NIPS 2012). https://papersnipscc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks. Accessed 20 Jan 2018

  11. 11.

    Szegedy C, Liu W, Jia Y et al (2014) Going deeper with convolutions. Cornell University Library. https://arxivorg/abs/14094842. Accessed 20 Jan 2018

  12. 12.

    He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. Cornell University Library. https://arxivorg/abs/151203385. Accessed 20 Jan 2018

  13. 13.

    Andrearczyk V, Whelan PF (2016) Using filter banks in convolutional neural networks for texture classification. Cornell University Library. https://arxiv.org/abs/1601.02919. Accessed 20 Jan 2018

  14. 14.

    Lakhani P, Sundaram B (2017) Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology 284:574–582

    Article  Google Scholar 

  15. 15.

    Prevedello LM, Erdal BS, Ryu JL et al (2017) Automated critical test findings identification and online notification system using artificial intelligence in imaging. Radiology 285:923–931

    Article  Google Scholar 

  16. 16.

    Liu F, Jang H, Kijowski R, Bradshaw T, McMillan AB (2018) Deep learning MR imaging-based attenuation correction for PET/MR imaging. Radiology 286:676–684

    Article  Google Scholar 

  17. 17.

    Larson DB, Chen MC, Lungren MP, Halabi SS, Stence NV, Langlotz CP (2018) Performance of a deep-learning neural network model in assessing skeletal maturity on pediatric hand radiographs. Radiology 287:313–322

    Article  Google Scholar 

  18. 18.

    Leynes AP, Yang J, Wiesinger F et al (2017) Direct pseudoCT generation for pelvis PET/MRI attenuation correction using deep convolutional neural networks with multi-parametric MRI: zero echo-time and Dixon deep pseudoCT (ZeDD-CT). J Nucl Med. https://doi.org/10.2967/jnumed.117.198051

    Article  Google Scholar 

  19. 19.

    Gonzalez G, Ash SY, Vegas Sanchez-Ferrero G et al (2018) Disease staging and prognosis in smokers using deep learning in chest computed tomography. Am J Respir Crit Care Med 197:193–203

    Article  Google Scholar 

  20. 20.

    Chang K, Bai HX, Zhou H et al (2018) Residual convolutional neural network for determination of IDH status in low- and high-grade gliomas from MR imaging. Clin Cancer Res 24:1073–1081

    CAS  Article  Google Scholar 

  21. 21.

    Nakao T, Hanaoka S, Nomura Y et al (2018) Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography. J Magn Reson Imaging 47:948–953

    Article  Google Scholar 

  22. 22.

    Yasaka K, Akai H, Abe O, Kiryu S (2018) Deep learning with convolutional neural network for differentiation of liver masses at dynamic contrast-enhanced CT: a preliminary study. Radiology 286:887–896

    Article  Google Scholar 

  23. 23.

    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 287:146–155

    Article  Google Scholar 

  24. 24.

    Ben-Cohen A, Klang E, Diamant I et al (2017) CT image-based decision support system for categorization of liver metastases into primary cancer sites: initial results. Acad Radiol 24:1501–1509

    Article  Google Scholar 

  25. 25.

    Nair V, Hinton G (2010) Rectified linear units improve restricted Boltzmann machines. International conference on machine learning. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.165.6419&rank=1. Accessed 20 Jan 2018

  26. 26.

    Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. Cornell University Library. http://arxiv.org/abs/1502.03167. Accessed 20 Jan 2018

  27. 27.

    Yasaka K, Akai H, Kunimatsu A, Kiryu S, Abe O (2018) Deep learning with convolutional neural network in radiology. Jpn J Radiol. https://doi.org/10.1007/s11604-018-0726-3

    Article  Google Scholar 

  28. 28.

    Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12:2121–2159

    Google Scholar 

  29. 29.

    Kanda Y (2013) Investigation of the freely available easy-to-use software 'EZR' for medical statistics. Bone Marrow Transplant 48:452–458

    CAS  Article  Google Scholar 

  30. 30.

    Friedrich-Rust M, Ong MF, Martens S et al (2008) Performance of transient elastography for the staging of liver fibrosis: a meta-analysis. Gastroenterology 134:960–974

    Article  Google Scholar 

  31. 31.

    Singh S, Venkatesh SK, Wang Z et al (2015) Diagnostic performance of magnetic resonance elastography in staging liver fibrosis: a systematic review and meta-analysis of individual participant data. Clin Gastroenterol Hepatol 13(440-451):e446

    Google Scholar 

  32. 32.

    Kim YS, Jang YN, Song JS (2018) Comparison of gradient-recalled echo and spin-echo echo-planar imaging MR elastography in staging liver fibrosis: a meta-analysis. Eur Radiol 28:1709–1718

    Article  Google Scholar 

  33. 33.

    Pickhardt PJ, Malecki K, Hunt OF et al (2017) Hepatosplenic volumetric assessment at MDCT for staging liver fibrosis. Eur Radiol 27:3060–3068

    Article  Google Scholar 

Download references

Funding

The authors state that this work has not received any funding.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Shigeru Kiryu.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Koichiro Yasaka.

Conflict of interest

The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was waived by the institutional review board.

Ethical approval

Institutional review board approval was obtained.

Methodology

• retrospective

• diagnostic or prognostic study

• performed at one institution

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Yasaka, K., Akai, H., Kunimatsu, A. et al. Deep learning for staging liver fibrosis on CT: a pilot study. Eur Radiol 28, 4578–4585 (2018). https://doi.org/10.1007/s00330-018-5499-7

Download citation

Keywords

  • Liver cirrhosis
  • Artificial intelligence
  • Multidetector computed tomography
  • ROC curve