Skip to main content

Advertisement

SpringerLink
Log in

Deep learning–assisted LI-RADS grading and distinguishing hepatocellular carcinoma (HCC) from non-HCC based on multiphase CT: a two-center study

  • Imaging Informatics and Artificial Intelligence
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

To develop a deep learning (DL) method that can determine the Liver Imaging Reporting and Data System (LI-RADS) grading of high-risk liver lesions and distinguish hepatocellular carcinoma (HCC) from non-HCC based on multiphase CT.

Methods

This retrospective study included 1049 patients with 1082 lesions from two independent hospitals that were pathologically confirmed as HCC or non-HCC. All patients underwent a four-phase CT imaging protocol. All lesions were graded (LR 4/5/M) by radiologists and divided into an internal (n = 886) and external cohort (n = 196) based on the examination date. In the internal cohort, Swin-Transformer based on different CT protocols were trained and tested for their ability to LI-RADS grading and distinguish HCC from non-HCC, and then validated in the external cohort. We further developed a combined model with the optimal protocol and clinical information for distinguishing HCC from non-HCC.

Results

In the test and external validation cohorts, the three-phase protocol without pre-contrast showed κ values of 0.6094 and 0.4845 for LI-RADS grading, and its accuracy was 0.8371 and 0.8061, while the accuracy of the radiologist was 0.8596 and 0.8622, respectively. The AUCs in distinguishing HCC from non-HCC were 0.865 and 0.715 in the test and external validation cohorts, while those of the combined model were 0.887 and 0.808.

Conclusion

The Swin-Transformer based on three-phase CT protocol without pre-contrast could feasibly simplify LI-RADS grading and distinguish HCC from non-HCC. Furthermore, the DL model have the potential in accurately distinguishing HCC from non-HCC using imaging and highly characteristic clinical data as inputs.

Clinical relevance statement

The application of deep learning model for multiphase CT has proven to improve the clinical applicability of the Liver Imaging Reporting and Data System and provide support to optimize the management of patients with liver diseases.

Key Points

• Deep learning (DL) simplifies LI-RADS grading and helps distinguish hepatocellular carcinoma (HCC) from non-HCC.

• The Swin-Transformer based on the three-phase CT protocol without pre-contrast outperformed other CT protocols.

• The Swin-Transformer provide help in distinguishing HCC from non-HCC by using CT and characteristic clinical information as inputs.

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

Similar content being viewed by others

Abbreviations

AFP:

Alpha-fetoprotein

ALP:

Alkaline phosphatase

ALT:

Alanine transaminase

AP:

Arterial phase

AST:

Aspartate amino transferase

AUC:

Area under the ROC curve

CECT:

Contrast-enhanced computed tomography

CNNs:

Convolutional neural networks

CT:

Computed tomography

DICOM:

Digital Imaging and Communications in Medicine

DL:

Deep learning

DP:

Delayed phase

HCC:

Hepatocellular carcinoma

HCC-ICC:

Combined HCC and intrahepatic cholangiocarcinoma

HIFU:

High-intensity focused ultrasound

HU:

Hounsfield units

LI-RADS:

Liver Imaging Reporting and Data System

PACS:

The Picture Archiving and Communication System

PLT:

Platelet

Pre:

Pre-contrast phase

PT:

Prothrombin time

PVP:

Portal-venous phase

ROC:

Receiver operating characteristic

ROI:

Region of interest

TACE:

Transarterial chemoembolization

TBIL:

Total bilirubin

References

  1. Sung H, Ferlay J, Siegel RL et al (2021) Global Cancer Statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 71:209–249. https://doi.org/10.3322/caac.21660

    Article  PubMed  Google Scholar 

  2. Marrero JA, Kulik LM, Sirlin CB et al (2018) Diagnosis, staging, and management of hepatocellular carcinoma: 2018 Practice Guidance by the American Association for the Study of Liver Diseases. Hepatology 68:723–750. https://doi.org/10.1002/hep.29913

    Article  PubMed  Google Scholar 

  3. European Association for the Study of the Liver (2018) EASL Clinical Practice Guidelines: management of hepatocellular carcinoma. J Hepatol 69:182–236. https://doi.org/10.1016/j.jhep.2018.03.019

    Article  Google Scholar 

  4. Heimbach JK, Kulik LM, Finn RS et al (2018) AASLD guidelines for the treatment of hepatocellular carcinoma. Hepatology 67:358–380. https://doi.org/10.1002/hep.29086

    Article  PubMed  Google Scholar 

  5. Chernyak V, Fowler KJ, Kamaya A et al (2018) Liver Imaging Reporting and Data System (LI-RADS) version 2018: imaging of hepatocellular carcinoma in at-risk patients. Radiology. https://doi.org/10.1148/radiol.2018181494

    Article  PubMed  Google Scholar 

  6. Fowler KJ, Tang A, Santillan C et al (2018) Interreader reliability of LI-RADS version 2014 algorithm and imaging features for diagnosis of hepatocellular carcinoma: a large international multireader study. Radiology 286:173–185. https://doi.org/10.1148/radiol.2017170376

    Article  PubMed  Google Scholar 

  7. Ehman EC, Behr SC, Umetsu SE et al (2016) Rate of observation and inter-observer agreement for LI-RADS major features at CT and MRI in 184 pathology proven hepatocellular carcinomas. Abdom Radiol (NY) 41:963–969. https://doi.org/10.1007/s00261-015-0623-5

    Article  PubMed  PubMed Central  Google Scholar 

  8. Peng L, Wang C, Tian G et al (2022) Analysis of CT scan images for COVID-19 pneumonia based on a deep ensemble framework with DenseNet, Swin transformer, and RegNet. Front Microbiol 13:995323. https://doi.org/10.3389/fmicb.2022.995323

    Article  PubMed  PubMed Central  Google Scholar 

  9. Fan X, Feng X, Dong Y, Hou H (2022) COVID-19 CT image recognition algorithm based on transformer and CNN. Displays 72:102150. https://doi.org/10.1016/j.displa.2022.102150

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  10. Cao K, Deng T, Zhang C, Lu L, Li L (2022) A CNN-transformer fusion network for COVID-19 CXR image classification. PLoS One 17:e0276758. https://doi.org/10.1371/journal.pone.0276758

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  11. Yang M, He X, Xu L et al (2022) CT-based transformer model for non-invasively predicting the Fuhrman nuclear grade of clear cell renal cell carcinoma. Front Oncol 12. https://doi.org/10.3389/fonc.2022.961779

    Article  PubMed  PubMed Central  Google Scholar 

  12. Huang Y, Si Y, Hu B et al (2022) Transformer-based factorized encoder for classification of pneumoconiosis on 3D CT images. Comput Biol Med 150:106137. https://doi.org/10.1016/j.compbiomed.2022.106137

    Article  PubMed  Google Scholar 

  13. Wu Y, Qi S, Sun Y et al (2021) A vision transformer for emphysema classification using CT images. Phys Med Biol 66:245016. https://doi.org/10.1088/1361-6560/ac3dc8

    Article  Google Scholar 

  14. Liu Z, Lin Y, Cao Y et al (2021) Swin Transformer: hierarchical vision transformer using shifted windows. arXiv e-prints https://doi.org/10.48550/arXiv.2103.14030

  15. Wu J, Xu Q, Shen Y et al (2022) Swin Transformer improves the IDH mutation status prediction of gliomas free of MRI-based tumor segmentation. J Clin Med 11:4625. https://doi.org/10.3390/jcm11154625

    Article  PubMed  PubMed Central  Google Scholar 

  16. Zhao W, Chen W, Li G et al (2022) GMILT: a novel transformer network that can noninvasively predict EGFR mutation status. IEEE Trans Neural Netw Learn Syst.https://doi.org/10.1109/tnnls.2022.3190671

  17. Ranganathan P, Pramesh CS, Aggarwal R (2017) Common pitfalls in statistical analysis: measures of agreement. Perspect Clin Res. https://doi.org/10.4103/picr.PICR_123_17

    Article  PubMed  PubMed Central  Google Scholar 

  18. Yamashita R, Mittendorf A, Zhu Z et al (2020) Deep convolutional neural network applied to the liver imaging reporting and data system (LI-RADS) version 2014 category classification: a pilot study. Abdom Radiol (NY) 45:24–35. https://doi.org/10.1007/s00261-019-02306-7

    Article  PubMed  Google Scholar 

  19. Sheng R, Huang J, Zhang W et al (2021) A semi-automatic step-by-step expert-guided LI-RADS grading system based on gadoxetic acid-enhanced MRI. J Hepatocell Carcinoma. https://doi.org/10.2147/jhc.S316385

    Article  PubMed  PubMed Central  Google Scholar 

  20. Wu Y, White GM, Cornelius T et al (2020) Deep learning LI-RADS grading system based on contrast enhanced multiphase MRI for differentiation between LR-3 and LR-4/LR-5 liver tumors. Ann Transl Med 8:701. https://doi.org/10.21037/atm.2019.12.151

    Article  PubMed  PubMed Central  Google Scholar 

  21. Kamath A, Roudenko A, Hecht E et al (2019) CT/MR LI-RADS 2018: clinical implications and management recommendations. Abdom Radiol (NY) 44:1306–1322. https://doi.org/10.1007/s00261-018-1868-6

    Article  PubMed  Google Scholar 

  22. Furlan A, Marin D, Vanzulli A et al (2011) Hepatocellular carcinoma in cirrhotic patients at multidetector CT: hepatic venous phase versus delayed phase for the detection of tumour washout. Br J Radiol. https://doi.org/10.1259/bjr/18329080

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  23. Kim B, Lee JH, Kim JK et al (2018) The capsule appearance of hepatocellular carcinoma in gadoxetic acid-enhanced MR imaging: correlation with pathology and dynamic CT. Medicine (Baltimore) 97(25):e11142. https://doi.org/10.1097/MD.0000000000011142

    Article  PubMed  Google Scholar 

  24. Shi W, Kuang S, Cao S et al (2020) Deep learning assisted differentiation of hepatocellular carcinoma from focal liver lesions: choice of four-phase and three-phase CT imaging protocol. Abdom Radiol (NY) 45:2688–2697. https://doi.org/10.1007/s00261-020-02485-8

    Article  PubMed  Google Scholar 

  25. Zhou J, Wang W, Lei B et al (2020) Automatic detection and classification of focal liver lesions based on deep convolutional neural networks: a preliminary study. Front Oncol 10:581210. https://doi.org/10.3389/fonc.2020.581210

    Article  PubMed  Google Scholar 

  26. Lee H, Lee H, Hong H et al (2021) Classification of focal liver lesions in CT images using convolutional neural networks with lesion information augmented patches and synthetic data augmentation. Med Phys 48(9):5029–5046. https://doi.org/10.1002/mp.15118

    Article  PubMed  Google Scholar 

  27. 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. https://doi.org/10.1148/radiol.2017170706

    Article  PubMed  Google Scholar 

  28. Sato M, Morimoto K, Kajihara S et al (2019) Machine-learning approach for the development of a novel predictive model for the diagnosis of hepatocellular carcinoma. Sci Rep 9:7704. https://doi.org/10.1038/s41598-019-44022-8

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  29. Nakai H, Fujimoto K, Yamashita R et al (2021) Convolutional neural network for classifying primary liver cancer based on triple-phase CT and tumor marker information: a pilot study. Jpn J Radiol 39:690–702. https://doi.org/10.1007/s11604-021-01106-8

    Article  CAS  PubMed  Google Scholar 

  30. Johnson PJ, Berhane S, Kagebayashi C et al (2015) Assessment of liver function in patients with hepatocellular carcinoma: a new evidence-based approach-the ALBI grade. J Clin Oncol 33(6):550. https://doi.org/10.1200/JCO.2014.57.9151

    Article  PubMed  Google Scholar 

  31. Yip TC, Chan HL, Wong VW et al (2017) Impact of age and gender on risk of hepatocellular carcinoma after hepatitis B surface antigen seroclearance. J Hepatol 67:902–908. https://doi.org/10.1016/j.jhep.2017.06.019

    Article  CAS  PubMed  Google Scholar 

  32. Lersritwimanmaen P, Nimanong S (2018) Hepatocellular carcinoma surveillance: benefit of serum alfa-fetoprotein in real-world practice. Euroasian J Hepatogastroenterol 8:83. https://doi.org/10.5005/jp-journals-10018-1268

    Article  PubMed  PubMed Central  Google Scholar 

  33. Tahata Y, Sakamori R, Yamada R et al (2022) Risk of hepatocellular carcinoma after sustained virologic response in hepatitis C virus patients without advanced liver fibrosis. Hepatol Res 52:824–832. https://doi.org/10.1111/hepr.13806

    Article  CAS  PubMed  Google Scholar 

  34. Smucny J, Shi G, Lesh TA, Carter CS, Davidson I (2022) Data augmentation with Mixup: enhancing performance of a functional neuroimaging-based prognostic deep learning classifier in recent onset psychosis. Neuroimage Clin 36:103214. https://doi.org/10.1016/j.nicl.2022.103214

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgements

The authors would like to thank Drs. Yudong Wang, Qianrui Fan, Jiangfen Wu, and Master Weidao Chen (all from Institute of Research, InferVision, Ocean International Center, Chaoyang District, Beijing 100025, China) who provided technical support for the model construction of this study.

Funding

This study has received funding by Chongqing medical scientific research project (Joint project of Chongqing Health Commission and Science and Technology Bureau) (Grant No. 2022ZDXM026).

Author information

Authors and Affiliations

  1. Department of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, 400010, People’s Republic of China

    Yang Xu, Xiaojuan He, Rao Song, Yangyang Liu, Haiping Zhang & Dajing Guo

  2. Department of Radiology, The First Affiliated Hospital of Army Military Medical University, Chongqing, 400038, People’s Republic of China

    Chaoyang Zhou & Jian Wang

  3. Institute of Research, Ocean International Center, InferVision, Chaoyang District, Beijing, 100025, China

    Yudong Wang, Qianrui Fan, Weidao Chen & Jiangfen Wu

Authors
  1. Yang Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chaoyang Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiaojuan He
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Rao Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yangyang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Haiping Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Yudong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Qianrui Fan
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Weidao Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Jiangfen Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Jian Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Dajing Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Jian Wang or Dajing Guo.

Ethics declarations

Guarantor

The scientific guarantors of this publication are Dajing Guo.

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 from the Second Affiliated Hospital of Chongqing Medical University and the First Affiliated Hospital of Army Military Medical University.

Methodology

  • retrospective

  • diagnostic study

  • multicenter study

Additional information

Publisher's note

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

Yang Xu and Chaoyang Zhou are joint first authors.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (PDF 155 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xu, Y., Zhou, C., He, X. et al. Deep learning–assisted LI-RADS grading and distinguishing hepatocellular carcinoma (HCC) from non-HCC based on multiphase CT: a two-center study. Eur Radiol 33, 8879–8888 (2023). https://doi.org/10.1007/s00330-023-09857-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-023-09857-w

Keywords

Search

Navigation