Skip to main content
SpringerLink
Log in

An index based on deep learning–measured spleen volume on CT for the assessment of high-risk varix in B-viral compensated cirrhosis

European Radiology volume 31, pages 3355–3365 (2021)Cite this article

Abstract

Objectives

Deep learning enables an automated liver and spleen volume measurements on CT. The purpose of this study was to develop an index combining liver and spleen volumes and clinical factors for detecting high-risk varices in B-viral compensated cirrhosis.

Methods

This retrospective study included 419 patients with B-viral compensated cirrhosis who underwent endoscopy and CT from 2007 to 2008 (derivation cohort, n = 239) and from 2009 to 2010 (validation cohort, n = 180). The liver and spleen volumes were measured on CT images using a deep learning algorithm. Multivariable logistic regression analysis of the derivation cohort developed an index to detect endoscopically confirmed high-risk varix. The cumulative 5-year risk of varix bleeding was evaluated with patients stratified by their index values.

Results

The index of spleen volume-to-platelet ratio was devised from the derivation cohort. In the validation cohort, the cutoff index value for balanced sensitivity and specificity (> 3.78) resulted in the sensitivity of 69.4% and the specificity of 78.5% for detecting high-risk varix, and the cutoff index value for high sensitivity (> 1.63) detected all high-risk varices. The index stratified all patients into the low (index value ≤ 1.63; n = 118), intermediate (n = 162), and high (index value > 3.78; n = 139) risk groups with cumulative 5-year incidences of varix bleeding of 0%, 1.0%, and 12.0%, respectively (p < .001).

Conclusion

The spleen volume-to-platelet ratio obtained using deep learning–based CT analysis is useful to detect high-risk varices and to assess the risk of varix bleeding.

Key Points

• The criterion of spleen volume to platelet > 1.63 detected all high-risk varices in the validation cohort, while the absence of visible varix did not exclude all high-risk varices.

• Visual varix grade ≥ 2 detected high-risk varix with a high specificity (96.5–100%).

• Combining spleen volume-to-platelet ratio ≤ 1.63 and visual varix grade of 0 identified low-risk patients who had no high-risk varix and varix bleeding on 5-year follow-up.

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

Access options

Buy single article

Instant access to the full article PDF.

USD 39.95

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

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

Abbreviations

AUC:

Area under the ROC curve

LOA:

Limit of agreement

LR:

Likelihood ratio

NPV:

Negative predictive value

PPV:

Positive predictive value

ROC:

Receiver operating characteristics

Spleen vol/platelet:

Spleen volume-to-platelet ratio

References

  1. D’Amico G, Morabito A, D’Amico M et al (2018) Clinical states of cirrhosis and competing risks. J Hepatol 68:563–576

    Article  Google Scholar 

  2. Garcia-Tsao G, Abraldes JG, Berzigotti A, Bosch J (2017) Portal hypertensive bleeding in cirrhosis: risk stratification, diagnosis, and management: 2016 practice guidance by the American Association for the Study of Liver Diseases. Hepatology 65:310–335

    Article  Google Scholar 

  3. de Franchis R, Baveno VIF (2015) Expanding consensus in portal hypertension: report of the Baveno VI consensus workshop: stratifying risk and individualizing care for portal hypertension. J Hepatol 63:743–752

    Article  Google Scholar 

  4. Zhang C, Thabut D, Kamath PS, Shah VH (2011) Oesophageal varices in cirrhotic patients: from variceal screening to primary prophylaxis of the first oesophageal variceal bleeding. Liver Int 31:108–119

    Article  CAS  Google Scholar 

  5. de Franchis R, Pascal JP, Ancona E et al (1992) Definitions, methodology and therapeutic strategies in portal hypertension. A consensus development workshop, Baveno, Lake Maggiore, Italy, April 5 and 6, 1990. J Hepatol 15:256–261

    Article  Google Scholar 

  6. Berzigotti A, Seijo S, Arena U et al (2013) Elastography, spleen size, and platelet count identify portal hypertension in patients with compensated cirrhosis. Gastroenterology 144:102–111 e101

    Article  Google Scholar 

  7. Takuma Y, Morimoto Y, Takabatake H et al (2017) Measurement of spleen stiffness with acoustic radiation force impulse imaging predicts mortality and hepatic decompensation in patients with liver cirrhosis. Clin Gastroenterol Hepatol 15:1782–1790 e1784

    Article  Google Scholar 

  8. Giannini E, Botta F, Borro P et al (2003) Platelet count/spleen diameter ratio: proposal and validation of a non-invasive parameter to predict the presence of oesophageal varices in patients with liver cirrhosis. Gut 52:1200–1205

    Article  CAS  Google Scholar 

  9. Thabut D, Trabut JB, Massard J et al (2006) Non-invasive diagnosis of large oesophageal varices with FibroTest in patients with cirrhosis: a preliminary retrospective study. Liver Int 26:271–278

    Article  Google Scholar 

  10. Vizzutti F, Arena U, Romanelli RG et al (2007) Liver stiffness measurement predicts severe portal hypertension in patients with HCV-related cirrhosis. Hepatology 45:1290–1297

    Article  Google Scholar 

  11. Kim H, Choi D, Gwak GY et al (2009) Evaluation of esophageal varices on liver computed tomography: receiver operating characteristic analyses of the performance of radiologists and endoscopists. J Gastroenterol Hepatol 24:1534–1540

    Article  Google Scholar 

  12. Wong GL, Liang LY, Kwok R et al (2019) Low risk of variceal bleeding in patients with cirrhosis after variceal screening stratified by liver/spleen stiffness. Hepatology 70:971–981

    Article  Google Scholar 

  13. Abe H, Midorikawa Y, Matsumoto N et al (2019) Prediction of esophageal varices by liver and spleen MR elastography. Eur Radiol 29:6611–6619

    Article  Google Scholar 

  14. Kim BK, Han KH, Park JY et al (2010) A liver stiffness measurement-based, noninvasive prediction model for high-risk esophageal varices in B-viral liver cirrhosis. Am J Gastroenterol 105:1382–1390

    Article  Google Scholar 

  15. Iranmanesh P, Vazquez O, Terraz S et al (2014) Accurate computed tomography-based portal pressure assessment in patients with hepatocellular carcinoma. J Hepatol 60:969–974

    Article  Google Scholar 

  16. Perri RE, Chiorean MV, Fidler JL et al (2008) A prospective evaluation of computerized tomographic (CT) scanning as a screening modality for esophageal varices. Hepatology 47:1587–1594

    Article  Google Scholar 

  17. Yu NC, Margolis D, Hsu M, Raman SS, Lu DS (2011) Detection and grading of esophageal varices on liver CT: comparison of standard and thin-section multiplanar reconstructions in diagnostic accuracy. AJR Am J Roentgenol 197:643–649

    Article  Google Scholar 

  18. Yan SP, Wu H, Wang GC, Chen Y, Zhang CQ, Zhu Q (2015) A new model combining the liver/spleen volume ratio and classification of varices predicts HVPG in hepatitis B patients with cirrhosis. Eur J Gastroenterol Hepatol 27:335–343

    Article  Google Scholar 

  19. Son JH, Lee SS, Lee Y et al (2020) Assessment of liver fibrosis severity using computed tomography-based liver and spleen volumetric indices in patients with chronic liver disease. Eur Radiol. https://doi.org/10.1007/s00330-020-06665-4

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

    Article  Google Scholar 

  21. Ahn Y, Yoon JS, Lee SS et al (2020) Deep learning algorithm for automated segmentation and volume measurement of the liver and spleen using portal venous phase computed tomography images. Korean J Radiol 21:987–997

    Article  Google Scholar 

  22. Chen L-C ZY, Papandreou G, Schroff F, Adam H (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. European Conference on Computer Vision (ECCV), Munich

  23. Idezuki Y (1995) General rules for recording endoscopic findings of esophagogastric varices (1991). Japanese Society for Portal Hypertension. World J Surg 19:420–422 discussion 423

    Article  CAS  Google Scholar 

  24. Landis JR, Koch GG (1977) The measurement of observer agreement for categorical data. Biometrics 33:159–174

    Article  CAS  Google Scholar 

  25. Bohning D, Holling H, Patilea V (2011) A limitation of the diagnostic-odds ratio in determining an optimal cut-off value for a continuous diagnostic test. Stat Methods Med Res 20:541–550

    Article  Google Scholar 

  26. Ronot M, Lambert S, Elkrief L et al (2014) Assessment of portal hypertension and high-risk oesophageal varices with liver and spleen three-dimensional multifrequency MR elastography in liver cirrhosis. Eur Radiol 24:1394–1402

    PubMed  Google Scholar 

  27. Shin SU, Lee JM, Yu MH et al (2014) Prediction of esophageal varices in patients with cirrhosis: usefulness of three-dimensional MR elastography with echo-planar imaging technique. Radiology 272:143–153

    Article  Google Scholar 

  28. European Association for the Study of the Liver (2018) EASL clinical practice guidelines for the management of patients with decompensated cirrhosis. J Hepatol 69:406–460

  29. Rockey DC, Caldwell SH, Goodman ZD, Nelson RC, Smith AD, American Association for the Study of Liver Diseases (2009) Liver biopsy. Hepatology 49:1017–1044

Download references

Funding

This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (Grant Number, 2020R1F1A1048826) and the Bio and Medical Technology Development Program of the NRF funded by the Ministry of Science and ICT, and Future Planning (Grant Number, NRF-2016M3A7918706).

Author information

Author notes

  1. Chul-min Lee

    Present address: Department of Radiology, Hanyang University Medical Center, Hanyang University School of Medicine, 222-1 Wangsimni-ro, Seongdong-gu, Seoul, 04763, South Korea

Authors and Affiliations

  1. Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, 88 Olympic-ro 43-gil, Songpa-Gu, Seoul, 05505, South Korea

    Chul-min Lee, Seung Soo Lee & So Jung Lee

  2. Department of Gastroenterology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, South Korea

    Won-Mook Choi & Kang Mo Kim

  3. Clinical Research Center, Asan Medical Center, Seoul, South Korea

    Yu Sub Sung

  4. SmartCareworks Inc., 1201, 6, Changgyeonggung-ro, Jung-gu, Seoul, 04559, South Korea

    Sunho Lee

  5. Department of Brain and Cognitive Engineering, Korea University, 145 Anam-ro, Anam-dong, Seongbuk-gu, Seoul, 02841, South Korea

    Jee Seok Yoon & Heung-Il Suk

  6. Department of Artificial Intelligence, Korea University, 145 Anam-ro, Anam-dong, Seongbuk-gu, Seoul, South Korea

    Heung-Il Suk

Authors
  1. Chul-min Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Seung Soo Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Won-Mook Choi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Kang Mo Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yu Sub Sung
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Sunho Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. So Jung Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Jee Seok Yoon
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Heung-Il Suk
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Seung Soo Lee.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Seung Soo Lee.

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 (S2019-0013-0002).

Methodology

• retrospective

• diagnostic or prognostic study

• performed at one institution

Additional information

Publisher’s note

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

Electronic supplementary material

ESM 1

(DOCX 3049 kb)

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lee, Cm., Lee, S.S., Choi, WM. et al. An index based on deep learning–measured spleen volume on CT for the assessment of high-risk varix in B-viral compensated cirrhosis. Eur Radiol 31, 3355–3365 (2021). https://doi.org/10.1007/s00330-020-07430-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-020-07430-3

Keywords

search

Navigation