Abstract
Background and aims
Highly accurate noninvasive methods for predicting gastroesophageal varices needing treatment (VNT) are desired. Radiomics is a newly emerging technology of image analysis. This study aims to develop and validate a novel noninvasive method based on radiomics for predicting VNT in cirrhosis.
Methods
In this retrospective–prospective study, a total of 245 cirrhotic patients were divided as the training set, internal validation set and external validation set. Radiomics features were extracted from portal-phase computed tomography (CT) images of each patient. A radiomics signature (Rad score) was constructed with the least absolute shrinkage and selection operator algorithm and tenfold cross-validation in the training set. Combined with independent risk factors, a radiomics nomogram was built with a multivariate logistic regression model.
Results
The Rad score, consisting of 14 features from the gastroesophageal region and 5 from the splenic hilum region, was effective for VNT classification. The diagnostic performance was further improved by combining the Rad score with platelet counts, achieving an AUC of 0.987 (95% CI 0.969–1.00), 0.973 (95% CI 0.939–1.00) and 0.947 (95% CI 0.876–1.00) in the training set, internal validation set and external validation set, respectively. In efficacy and safety assessment, the radiomics nomogram could spare more than 40% of endoscopic examinations with a low risk of missing VNT (< 5%), and no more than 8.3% of unnecessary endoscopic examinations still be performed.
Conclusions
In this study, we developed and validated a novel, diagnostic radiomics-based nomogram which is a reliable and noninvasive method to predict VNT in cirrhotic patients.
Clinical trials registration
NCT04210297.
Similar content being viewed by others
Data availability
All data included in this study are available upon request by contact with the corresponding author.
Abbreviations
- GEV:
-
Gastroesophageal varices
- VNT:
-
Varices needing treatment
- ALT:
-
Alanine aminotransferase
- AST:
-
Aspartate aminotransferase
- GGT:
-
Gamma-glutamyl transpeptidase
- AKP:
-
Alkaline phosphatase
- TBIL:
-
Total bilirubin
- ALB:
-
Albumin
- HGB:
-
Hemoglobin
- PLT:
-
Platelet count
- AFP:
-
Alpha-fetoprotein
- INR:
-
International normalized ratio
- HBV:
-
Hepatitis B virus
- PBC:
-
Primary biliary cirrhosis
- AIH:
-
Autoimmune hepatitis
- NPV:
-
Negative predictive value
- ACC:
-
Accuracy
- SD:
-
Standard deviation
- ROC:
-
Receiver-operator characteristic
- AUC:
-
Area under the curve
- PSR:
-
Platelet–spleen ratio
- APRI:
-
AST-to-platelet ratio index
- FIB-4:
-
Fibrosis-4 score
References
Jakab SS, Garcia-Tsao G. Evaluation and management of esophageal and gastric varices in patients with cirrhosis. Clin Liver Dis 2020;24:335–350. https://doi.org/10.1016/j.cld.2020.04.011 (Elsevier Inc).
Takehara T, Sakamori R. Remaining challenges for the noninvasive diagnosis of esophageal varices in liver cirrhosis. Esophagus 2020;17:19–24. https://doi.org/10.1007/s10388-019-00699-4 (Springer Singapore).
Amitrano L, Guardascione MA, Manguso F, Bennato R, Bove A, Denucci C, et al. The effectiveness of current acute variceal bleed treatments in unselected cirrhotic patients: refining short-term prognosis and risk factors. Am J Gastroenterol 2012;107(12):1872–1878.
Reiberger T, Püspök A, Schoder M, Baumann-Durchschein F, Bucsics T, Datz C, et al. Austrian consensus guidelines on the management and treatment of portal hypertension (Billroth III). Wien Klin Wochenschr 2017;129:135–158.
Tripathi D, Stanley AJ, Hayes PC, Patch D, Millson C, Mehrzad H, et al. UK guidelines on the management of variceal haemorrhage in cirrhotic patients. Gut 2015;64:1680–1704.
De Franchis R, Abraldes JG, Bajaj J, Berzigotti A, Bosch J, Burroughs AK, et al. Expanding consensus in portal hypertension report of the Baveno VI Consensus Workshop: stratifying risk and individualizing care for portal hypertension. J Hepatol 2015;63(3):743–752.
Augustin S, Pons M, Genesca J. Validating the Baveno VI recommendations for screening varices. J Hepatol 2017;66:459–460. https://doi.org/10.1016/j.jhep.2016.09.027 (European Association for the Study of the Liver).
Jangouk P, Turco L, De Oliveira A, Schepis F, Villa E, Garcia-Tsao G. Validating, deconstructing and refining Baveno criteria for ruling out high-risk varices in patients with compensated cirrhosis. Liver Int 2017;37:1177–1183.
Maurice JB, Brodkin E, Arnold F, Navaratnam A, Paine H, Khawar S, et al. Validation of the Baveno VI criteria to identify low risk cirrhotic patients not requiring endoscopic surveillance for varices. J Hepatol 2016;65:899–905. https://doi.org/10.1016/j.jhep.2016.06.021 (European Association for the Study of the Liver).
Somsouk M, To’o K, Ali M, Vittinghoff E, Yeh BM, Yee J, et al. Esophageal varices on computed tomography and subsequent variceal hemorrhage. Abdom Imaging 2014;39:251–256.
Yu NC, Margolis D, Hsu M, Raman SS, Lu DSK. Detection and grading of esophageal varices on liver CT: comparison of standard and thin-section multiplanar reconstructions in diagnostic accuracy. Am J Roentgenol 2011;197:643–649.
Manchec B, Pham E, Noor M, Pepe J, Feranec N, Contreras F, et al. Contrast-enhanced CT may identify high-risk esophageal varices in patients with cirrhosis. Am J Roentgenol 2020;215(3):617–623.
Calame P, Ronot M, Bouveresse S, Cervoni JP, Vilgrain V, Delabrousse É. Predictive value of CT for first esophageal variceal bleeding in patients with cirrhosis: value of para-umbilical vein patency. Eur J Radiol 2017;87:45–52. https://doi.org/10.1016/j.ejrad.2016.12.006 (Elsevier Ireland Ltd).
Kimura N, Yokoyama J, Terai S. Utility of measuring paraesophageal varices using computed tomography to select endoscopic treatment for patients with esophageal varices. Dig Endosc 2019;31:335.
Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology 2016;278(2):563–577.
Lambin P, Rios-velazquez E, Leijenaar R, Carvalho S, Granton P, Zegers CML, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 2015;48:441–446.
Wan S, Wei Y, Zhang X, Liu X, Zhang W, He Y, et al. Multiparametric radiomics nomogram may be used for predicting the severity of esophageal varices in cirrhotic patients. Ann Transl Med 2020;8:186.
Huang Y, Huang F, Yang L, Hu W, Liu Y, Lin Z, et al. Development and validation of a radiomics signature as a non-invasive complementary predictor of gastroesophageal varices and high-risk varices in compensated advanced chronic liver disease: a multicenter study. J Gastroenterol Hepatol 2020. https://doi.org/10.1111/jgh.15306.
Liu F, Ning Z, Liu Y, Liu D, Tian J, Luo H, et al. Development and validation of a radiomics signature for clinically significant portal hypertension in cirrhosis (CHESS1701): a prospective multicenter study. EBioMedicine 2018;36:151–158. https://doi.org/10.1016/j.ebiom.2018.09.023 (The Authors).
Tsochatzis EA, Bosch J, Burroughs AK. Liver cirrhosis. Lancet 2014. https://doi.org/10.1016/S0140-6736(14)60121-5 (Elsevier Ltd).
Razek AAKA. Editorial for “preoperative MRI-based radiomic machine-learning nomogram may accurately distinguish between benign and malignant soft tissue lesions: a two-center study.” J Magn Reson Imaging 2020;52:883–884.
Tseng Y, Ma L, Li S, Luo T, Luo J, Zhang W, et al. Application of CT-based radiomics in predicting portal pressure and patient outcome in portal hypertension. Eur J Radiol 2020;126:108927. https://doi.org/10.1016/j.ejrad.2020.108927 (Elsevier).
Berzigotti A, Boyer TD, Castéra L, De Franchis R, Genescà J, Pinzani M. Reply to “points to be considered when using transient elastography for diagnosis of portal hypertension according to the Baveno’s VI consensus.” J Hepatol 2015;63:1049–1050. https://doi.org/10.1016/j.jhep.2015.06.036 (European Association for the Study of the Liver).
Ma X, Wang L, Wu H, Feng Y, Han X, Bu H, et al. Spleen stiffness is superior to liver stiffness for predicting esophageal varices in chronic liver disease: a meta-analysis. PLoS One 2016;11:1–15.
Giunta M, Conte D, Fraquelli M. Role of spleen elastography in patients with chronic liver diseases. World J Gastroenterol 2016;22:7857–7867.
Colecchia A, Marasco G, Taddia M, Montrone L, Eusebi LH, Mandolesi D, et al. Liver and spleen stiffness and other noninvasive methods to assess portal hypertension in cirrhotic patients. Eur J Gastroenterol Hepatol 2015;27:992–1001.
Tseng Y, Li F, Wang J, Chen S, Jiang W, Shen X, et al. Spleen and liver stiffness for noninvasive assessment of portal hypertension in cirrhotic patients with large esophageal varices. J Clin Ultrasound 2018;46:442–449.
Manatsathit W, Samant H, Kapur S, Ingviya T, Esmadi M, Wijarnpreecha K, et al. Accuracy of liver stiffness, spleen stiffness, and LS-spleen diameter to platelet ratio score in detection of esophageal varices: systemic review and meta-analysis. J Gastroenterol Hepatol 2018;33:1696–1706.
Kim SH, Kim YJ, Lee JM, Choi KD, Chung YJ, Han JK, et al. Esophageal varices in patients with cirrhosis: multidetector CT esophagography—comparison with endoscopy. Radiology 2007;242(3):759–768.
Razek AAKA, Abdalla A, Omran E, Fathy A, Zalata K. Diagnosis and quantification of hepatic fibrosis in children with diffusion weighted MR imaging. Eur J Radiol 2011;78:129–134. https://doi.org/10.1016/j.ejrad.2009.10.012 (Elsevier Ireland Ltd).
Razek AAKA, Massoud SMA, Azziz MRA, El-Bendary MM, Zalata K, Motawea EM. Prediction of esophageal varices in cirrhotic patients with apparent diffusion coefficient of the spleen. Abdom Imaging 2015;40:1465–1469. https://doi.org/10.1007/s00261-015-0391-2 (Springer US).
Besheer T, Elalfy H, El-Maksoud MA, El-Bendary M, El-Razek AA, Taman S, et al. Diffusion-weighted magnetic resonance imaging and micro-RNA in the diagnosis of hepatic fibrosis in chronic hepatitis C virus. World J Gastroenterol 2019;25:1366–1377.
Funding
No funding received from any funding agency.
Author information
Authors and Affiliations
Contributions
Study design: YL, YG and JQ. Data collection: YL, QW and SZ. Technical support: LL, JQ, DY and ZL. Statistical analysis of data: YL. Manuscript writing: YL. Critical revision of the manuscript: YG, BC and YL.
Corresponding authors
Ethics declarations
Conflict of interest
The authors Yiken Lin, Lijuan Li, Dexin Yu, Zhuyun Liu, Shuhong Zhang, Qiuzhi Wang, Yueyue Li, Baoquan Cheng, Jianping Qiao and Yanjing Gao declared that they have no conflict of interest.
Ethical approval
Ethical committee approval was granted by the Medical Ethics Committee of involved institutions. All procedures involving human participants were performed following the Helsinki declaration and its later amendments. No animal participants was used for this manuscript.
Informed consent
The informed consent was obtained from all patients enrolled as the validation sets and was waived in the training set for the retrospective analysis. All authors reviewed and approved the final version of the manuscript.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Lin, Y., Li, L., Yu, D. et al. A novel radiomics–platelet nomogram for the prediction of gastroesophageal varices needing treatment in cirrhotic patients. Hepatol Int 15, 995–1005 (2021). https://doi.org/10.1007/s12072-021-10208-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12072-021-10208-4