Korean Journal of Radiology

  • 제23권12호
  • /
  • Pages.1269-1280
  • /
  • 2022
  • /
  • 1229-6929(pISSN)
  • /
  • 2005-8330(eISSN)
대한영상의학회 (The Korean Society of Radiology)
권호 표지
DOI QR코드

DOI QR Code

Prediction of Decompensation and Death in Advanced Chronic Liver Disease Using Deep Learning Analysis of Gadoxetic Acid-Enhanced MRI

  • Subin Heo (Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Seung Soo Lee (Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • So Yeon Kim (Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Young-Suk Lim (Department of Gastroenterology, Liver Center, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Hyo Jung Park (Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Jee Seok Yoon (Department of Brain and Cognitive Engineering, Korea University) ;
  • Heung-Il Suk (Department of Brain and Cognitive Engineering, Korea University) ;
  • Yu Sub Sung (Clinical Research Center, Asan Medical Center) ;
  • Bumwoo Park (Health Innovation Big Data Center, Asan Institute for Life Sciences, Asan Medical Center) ;
  • Ji Sung Lee (Department of Clinical Epidemiology and Biostatistics, Asan Medical Center, University of Ulsan College of Medicine)
  • 투고 : 2022.07.20
  • 심사 : 2022.10.11
  • 발행 : 2022.12.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Objective: This study aimed to evaluate the usefulness of quantitative indices obtained from deep learning analysis of gadoxetic acid-enhanced hepatobiliary phase (HBP) MRI and their longitudinal changes in predicting decompensation and death in patients with advanced chronic liver disease (ACLD). Materials and Methods: We included patients who underwent baseline and 1-year follow-up MRI from a prospective cohort that underwent gadoxetic acid-enhanced MRI for hepatocellular carcinoma surveillance between November 2011 and August 2012 at a tertiary medical center. Baseline liver condition was categorized as non-ACLD, compensated ACLD, and decompensated ACLD. The liver-to-spleen signal intensity ratio (LS-SIR) and liver-to-spleen volume ratio (LS-VR) were automatically measured on the HBP images using a deep learning algorithm, and their percentage changes at the 1-year follow-up (ΔLS-SIR and ΔLS-VR) were calculated. The associations of the MRI indices with hepatic decompensation and a composite endpoint of liver-related death or transplantation were evaluated using a competing risk analysis with multivariable Fine and Gray regression models, including baseline parameters alone and both baseline and follow-up parameters. Results: Our study included 280 patients (153 male; mean age ± standard deviation, 57 ± 7.95 years) with non-ACLD, compensated ACLD, and decompensated ACLD in 32, 186, and 62 patients, respectively. Patients were followed for 11-117 months (median, 104 months). In patients with compensated ACLD, baseline LS-SIR (sub-distribution hazard ratio [sHR], 0.81; p = 0.034) and LS-VR (sHR, 0.71; p = 0.01) were independently associated with hepatic decompensation. The ΔLS-VR (sHR, 0.54; p = 0.002) was predictive of hepatic decompensation after adjusting for baseline variables. ΔLS-VR was an independent predictor of liver-related death or transplantation in patients with compensated ACLD (sHR, 0.46; p = 0.026) and decompensated ACLD (sHR, 0.61; p = 0.023). Conclusion: MRI indices automatically derived from the deep learning analysis of gadoxetic acid-enhanced HBP MRI can be used as prognostic markers in patients with ACLD.

키워드

과제정보

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (NRF-2020R1F1A1048826).

참고문헌

  1. de Franchis R; Baveno VI Faculty. Expanding consensus in portal hypertension: report of the Baveno VI Consensus Workshop: stratifying risk and individualizing care for portal hypertension. J Hepatol 2015;63:743-752
  2. D'Amico G, Garcia-Tsao G, Pagliaro L. Natural history and prognostic indicators of survival in cirrhosis: a systematic review of 118 studies. J Hepatol 2006;44:217-231
  3. Shearer JE, Jones R, Parker R, Ferguson J, Rowe IA. The natural history of advanced chronic liver disease defined by transient elastography. Clin Gastroenterol Hepatol 2022 Mar 23 [Epub]. https://doi.org/10.1016/j.cgh.2022.03.015
  4. Kim HD, Lim YS, Han S, An J, Kim GA, Kim SY, et al. Evaluation of early-stage hepatocellular carcinoma by magnetic resonance imaging with gadoxetic acid detects additional lesions and increases overall survival. Gastroenterology 2015;148:1371-1382
  5. Lee YJ, Lee JM, Lee JS, Lee HY, Park BH, Kim YH, et al. Hepatocellular carcinoma: diagnostic performance of multidetector CT and MR imaging-a systematic review and meta-analysis. Radiology 2015;275:97-109
  6. Kim HL, An J, Park JA, Park SH, Lim YS, Lee EK. Magnetic resonance imaging is cost-effective for hepatocellular carcinoma surveillance in high-risk patients with cirrhosis. Hepatology 2019;69:1599-1613
  7. Kim SY, An J, Lim YS, Han S, Lee JY, Byun JH, et al. MRI with liver-specific contrast for surveillance of patients with cirrhosis at high risk of hepatocellular carcinoma. JAMA Oncol 2017;3:456-463
  8. European Association for the Study of the Liver. EASL clinical practice guidelines: management of hepatocellular carcinoma. J Hepatol 2018;69:182-236
  9. Asenbaum U, Ba-Ssalamah A, Mandorfer M, Nolz R, Furtner J, Reiberger T, et al. Effects of portal hypertension on gadoxetic acid-enhanced liver magnetic resonance: diagnostic and prognostic implications. Invest Radiol 2017;52:462-469
  10. Yamada A, Hara T, Li F, Fujinaga Y, Ueda K, Kadoya M, et al. Quantitative evaluation of liver function with use of gadoxetate disodium-enhanced MR imaging. Radiology 2011;260:727-733
  11. Park HJ, Yoon JS, Lee SS, Suk HI, Park B, Sung YS, et al. Deep learning-based assessment of functional liver capacity using gadoxetic acid-enhanced hepatobiliary phase MRI. Korean J Radiol 2022;23:720-731
  12. Iranmanesh P, Vazquez O, Terraz S, Majno P, Spahr L, Poncet A, et al. Accurate computed tomography-based portal pressure assessment in patients with hepatocellular carcinoma. J Hepatol 2014;60:969-974
  13. Son JH, Lee SS, Lee Y, Kang BK, Sung YS, Jo S, et al. Assessment of liver fibrosis severity using computed tomography-based liver and spleen volumetric indices in patients with chronic liver disease. Eur Radiol 2020;30:3486-3496
  14. Lee CM, Lee SS, Choi WM, Kim KM, Sung YS, Lee S, 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 2021;31:3355-3365
  15. Suh CH, Kim SY, Kim KW, Lim YS, Lee SJ, Lee MG, et al. Determination of normal hepatic elasticity by using real-time shear-wave elastography. Radiology 2014;271:895-900
  16. Paisant A, Lemoine S, Cassinotto C, de Ledinghen V, Ronot M, Irles-Depe M, et al. Reliability criteria of two-dimensional shear wave elastography: analysis of 4277 measurements in 788 patients. Clin Gastroenterol Hepatol 2022;20:400-408.e10
  17. Barr RG, Wilson SR, Rubens D, Garcia-Tsao G, Ferraioli G. Update to the society of radiologists in ultrasound liver elastography consensus statement. Radiology 2020;296:263-274
  18. D'Amico G, Morabito A, D'Amico M, Pasta L, Malizia G, Rebora P, et al. Clinical states of cirrhosis and competing risks. J Hepatol 2018;68:563-576
  19. Fine JP, Gray RJ. A proportional hazards model for the subdistribution of a competing risk. J Am Stat Assoc 1999;94:496-509
  20. Mojtahed A, Nunez L, Connell J, Fichera A, Nicholls R, Barone A, et al. Repeatability and reproducibility of deep-learning-based liver volume and Couinaud segment volume measurement tool. Abdom Radiol (NY) 2022;47:143-151
  21. Williams B, Mandrekar JN, Mandrekar SJ, Cha SS, Furth AF. Finding optimal cutpoints for continuous covariates with binary and time-to-event outcomes. Rochester, MN: Mayo Clinic 2006
  22. Aalen O. Nonparametric estimation of partial transition probabilities in multiple decrement models. Ann Statist 1978;6:534-545
  23. Gray RJ. A class of K-sample tests for comparing the cumulative incidence of a competing risk. Ann Stat 1988;16:1141-1154
  24. Murata Y, Abe M, Hiasa Y, Azemoto N, Kumagi T, Furukawa S, et al. Liver/spleen volume ratio as a predictor of prognosis in primary biliary cirrhosis. J Gastroenterol 2008;43:632-636
  25. Kwon JH, Lee SS, Yoon JS, Suk HI, Sung YS, Kim HS, et al. Liver-to-spleen volume ratio automatically measured on CT predicts decompensation in patients with B viral compensated cirrhosis. Korean J Radiol 2021;22:1985-1995
  26. Bastati N, Beer L, Mandorfer M, Poetter-Lang S, Tamandl D, Bican Y, et al. Does the functional liver imaging score derived from gadoxetic acid-enhanced MRI predict outcomes in chronic liver disease? Radiology 2020;294:98-107
  27. Yoon JH, Lee JM, Kim E, Okuaki T, Han JK. Quantitative liver function analysis: volumetric T1 mapping with fast multisection B1 inhomogeneity correction in hepatocyte-specific contrast-enhanced liver MR imaging. Radiology 2017;282:408-417