Advertisement

European Radiology

, Volume 29, Issue 5, pp 2175–2184 | Cite as

Quantitative ultrasound and machine learning for assessment of steatohepatitis in a rat model

  • An TangEmail author
  • François Destrempes
  • Siavash Kazemirad
  • Julian Garcia-Duitama
  • Bich N. Nguyen
  • Guy Cloutier
Ultrasound

Abstract

Objectives

To develop a machine learning model based on quantitative ultrasound (QUS) parameters to improve classification of steatohepatitis with shear wave elastography in rats by using histopathology scoring as the reference standard.

Methods

This study received approval from the institutional animal care committee. Sixty male Sprague-Dawley rats were either fed a standard chow or a methionine- and choline-deficient diet. Ultrasound-based radiofrequency images were recorded in vivo to generate QUS and elastography maps. Random forests classification models and a bootstrap method were used to identify the QUS parameters that improved the classification accuracy of elastography. Receiver-operating characteristic analyses were performed.

Results

For classification of not steatohepatitis vs borderline or steatohepatitis, the area under the receiver-operating characteristic curve (AUC) increased from 0.63 for elastography alone to 0.72 for a model that combined elastography and QUS techniques (p < 0.001). For detection of liver steatosis grades 0 vs ≥ 1, ≤ 1 vs ≥ 2, ≤ 2 vs 3, respectively, the AUCs increased from 0.70, 0.65, and 0.69 to 0.78, 0.78, and 0.75 (p < 0.001). For detection of liver inflammation grades 0 vs ≥ 1, ≤ 1 vs ≥ 2, ≤ 2 vs 3, respectively, the AUCs increased from 0.58, 0.77, and 0.78 to 0.66, 0.84, and 0.87 (p < 0.001). For staging of liver fibrosis grades 0 vs ≥ 1, ≤ 1 vs ≥ 2, and ≤ 2 vs ≥ 3, respectively, the AUCs increased from 0.79, 0.92, and 0.91 to 0.85, 0.98, and 0.97 (p < 0.001).

Conclusion

QUS parameters improved the classification accuracy of steatohepatitis, liver steatosis, inflammation, and fibrosis compared to shear wave elastography alone.

Key Points

• Quantitative ultrasound and shear wave elastography improved classification accuracy of liver steatohepatitis and its histological features (liver steatosis, inflammation, and fibrosis) compared to elastography alone.

• A machine learning approach based on random forest models and incorporating local attenuation and homodyned-K tissue modeling shows promise for classification of nonalcoholic steatohepatitis.

• Further research should be performed to demonstrate the applicability of this multi-parametric QUS approach in a human cohort and to validate the combinations of parameters providing the highest classification accuracy.

Keywords

Nonalcoholic steatohepatitis Non-alcoholic fatty liver disease Machine learning Ultrasonography Elasticity imaging techniques 

Abbreviations

AUC

Area under the receiver-operating characteristic curve

CAP

Controlled attenuation parameter

HKD

Homodyned-K distributions

HPS

Hematoxylin phloxine saffron

IQR

Inter-quartile range

MCD

Methionine and choline deficient

NAFLD

Nonalcoholic fatty liver disease

NASH

Nonalcoholic steatohepatitis

QUS

Quantitative ultrasound

ROC

Receiver operating characteristic

ROI

Region of interest

SH

Steatohepatitis

Notes

Acknowledgments

We thank Mr. Jamal Ait Ichou for his assistance in the literature review.

Funding

This study has received funding by Fonds de Recherche du Québec—Nature et Technologies (FRQNT) (PR-174387), Canadian Institutes of Health Research, Institute of Nutrition, Metabolism, and Diabetes (grant nos. 273738 and 301520), Quebec Bio-imaging Network (QBIN/RBIQ #5886), New Researcher Startup Grant from the Centre de Recherche du Centre Hospitalier de l’Université de Montréal, and by a Chercheur-Boursier Junior 2 from the Fonds de Recherche du Québec en Santé and Fondation de l’association des radiologistes du Québec (FRQS-ARQ #34939) to An Tang.

Compliance with ethical standards

Guarantor

The scientific guarantor if this publication is An Tang.

Conflict of interest

The authors declare that they have no conflict of interest.

Statistics and biometry

One of the authors has significant statistical expertise.

Informed consent

Approval from the institutional animal care committee was obtained.

Ethical approval

Institutional review board approval was obtained.

Study subjects or cohorts overlap

The study cohorts have been previously reported in [24]. That prior article focused on a comparison between low-frequency versus high-frequency ultrasonographic shear wave elastography for the detection of steatohepatitis. In contrast, the present article investigates a machine learning model based on quantitative ultrasound parameters to improve classification of steatohepatitis compared to shear wave elastography alone.

Methodology

• Diagnostic study

• Experimental

• Performed at one institution

Supplementary material

330_2018_5915_MOESM1_ESM.docx (45 kb)
ESM 1 (DOCX 44 kb)

References

  1. 1.
    Vernon G, Baranova A, Younossi ZM (2011) Systematic review: the epidemiology and natural history of non-alcoholic fatty liver disease and non-alcoholic steatohepatitis in adults. Aliment Pharmacol Ther 34:274–285CrossRefGoogle Scholar
  2. 2.
    Kleiner DE, Brunt EM, Van Natta M et al (2005) Design and validation of a histological scoring system for nonalcoholic fatty liver disease. Hepatology 41:1313–1321CrossRefGoogle Scholar
  3. 3.
    Sanyal AJ, Brunt EM, Kleiner DE et al (2011) Endpoints and clinical trial design for nonalcoholic steatohepatitis. Hepatology 54:344–353CrossRefGoogle Scholar
  4. 4.
    Fernández-Salazar L, Velayos B, Aller R, Lozano F, Garrote JA, González JM (2011) Percutaneous liver biopsy: patients’ point of view. Scand J Gastroenterol 46:727–731CrossRefGoogle Scholar
  5. 5.
    Myers RP, Fong A, Shaheen AA (2008) Utilization rates, complications and costs of percutaneous liver biopsy: a population-based study including 4275 biopsies. Liver Int 28:705–712CrossRefGoogle Scholar
  6. 6.
    Reeder SB, Cruite I, Hamilton G, Sirlin CB (2011) Quantitative assessment of liver fat with magnetic resonance imaging and spectroscopy. J Magn Reson Imaging 34:spconeCrossRefGoogle Scholar
  7. 7.
    Tang A, Desai A, Hamilton G et al (2015) Accuracy of MR imaging-estimated proton density fat fraction for classification of dichotomized histologic steatosis grades in nonalcoholic fatty liver disease. Radiology 274:416–425CrossRefGoogle Scholar
  8. 8.
    Yokoo T, Serai SD, Pirasteh A et al (2018) Linearity, bias, and precision of hepatic proton density fat fraction measurements by using MR imaging: a meta-analysis. Radiology 286:486–498CrossRefGoogle Scholar
  9. 9.
    Petitclerc L, Sebastiani G, Gilbert G, Cloutier G, Tang A (2017) Liver fibrosis: review of current imaging and MRI quantification techniques. J Magn Reson Imaging 45:1276–1295CrossRefGoogle Scholar
  10. 10.
    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 e446CrossRefGoogle Scholar
  11. 11.
    Salameh N, Larrat B, Abarca-Quinones J et al (2009) Early detection of steatohepatitis in fatty rat liver by using MR elastography. Radiology 253:90–97CrossRefGoogle Scholar
  12. 12.
    Yin M, Glaser KJ, Manduca A et al (2017) Distinguishing between hepatic inflammation and fibrosis with MR Elastography. Radiology 284:694–705CrossRefGoogle Scholar
  13. 13.
    Zhang E, Wartelle-Bladou C, Lepanto L, Lachaine J, Cloutier G, Tang A (2015) Cost-utility analysis of nonalcoholic steatohepatitis screening. Eur Radiol 25:3282–3294CrossRefGoogle Scholar
  14. 14.
    Park CC, Nguyen P, Hernandez C et al (2017) Magnetic resonance elastography vs transient elastography in detection of fibrosis and noninvasive measurement of steatosis in patients with biopsy-proven nonalcoholic fatty liver disease. Gastroenterology 152:598–607.e592CrossRefGoogle Scholar
  15. 15.
    de Lédinghen V, Wong GL, Vergniol J et al (2016) Controlled attenuation parameter for the diagnosis of steatosis in non-alcoholic fatty liver disease. J Gastroenterol Hepatol 31:848–855CrossRefGoogle Scholar
  16. 16.
    Chan WK, Nik Mustapha NR, Mahadeva S (2014) Controlled attenuation parameter for the detection and quantification of hepatic steatosis in nonalcoholic fatty liver disease. J Gastroenterol Hepatol 29:1470–1476CrossRefGoogle Scholar
  17. 17.
    Kumar M, Rastogi A, Singh T et al (2013) Controlled attenuation parameter for non-invasive assessment of hepatic steatosis: does etiology affect performance? J Gastroenterol Hepatol 28:1194–1201CrossRefGoogle Scholar
  18. 18.
    Lin SC, Heba E, Wolfson T et al (2015) Noninvasive diagnosis of nonalcoholic fatty liver disease and quantification of liver fat using a new quantitative ultrasound technique. Clin Gastroenterol Hepatol 13:1337–1345.e1336CrossRefGoogle Scholar
  19. 19.
    Paige JS, Bernstein GS, Heba E et al (2017) A pilot comparative study of quantitative ultrasound, conventional ultrasound, and MRI for predicting histology-determined steatosis grade in adult nonalcoholic fatty liver disease. AJR Am J Roentgenol 208:W168–w177CrossRefGoogle Scholar
  20. 20.
    Friedrich-Rust M, Nierhoff J, Lupsor M et al (2012) Performance of acoustic radiation force impulse imaging for the staging of liver fibrosis: a pooled meta-analysis. J Viral Hepat 19:e212–e219CrossRefGoogle Scholar
  21. 21.
    Friedrich-Rust M, Ong MF, Martens S et al (2008) Performance of transient elastography for the staging of liver fibrosis: a meta-analysis. Gastroenterology 134:960–974CrossRefGoogle Scholar
  22. 22.
    Oelze ML, Mamou J (2016) Review of quantitative ultrasound: envelope statistics and backscatter coefficient imaging and contributions to diagnostic ultrasound. IEEE Trans Ultrason Ferroelectr Freq Control 63:336–351CrossRefGoogle Scholar
  23. 23.
    Mamou J, Oelze ML (2013) Quantitative ultrasound in soft tissues. Springer, DordrechtGoogle Scholar
  24. 24.
    Kazemirad S, Zhang E, Nguyen BN et al (2017) Detection of steatohepatitis in a rat model by using spectroscopic shear-wave US elastography. Radiology 282:726–733CrossRefGoogle Scholar
  25. 25.
    Rinella ME, Elias MS, Smolak RR, Fu T, Borensztajn J, Green RM (2008) Mechanisms of hepatic steatosis in mice fed a lipogenic methionine choline-deficient diet. J Lipid Res 49:1068–1076CrossRefGoogle Scholar
  26. 26.
    Hebbard L, George J (2011) Animal models of nonalcoholic fatty liver disease. Nat Rev Gastroenterol Hepatol 8:35–44CrossRefGoogle Scholar
  27. 27.
    Kazemirad S, Bernard S, Hybois S, Tang A, Cloutier G (2016) Ultrasound shear wave viscoelastography: model-independent quantification of the complex shear modulus. IEEE Trans Ultrason Ferroelectr Freq Control 63:1399–1408CrossRefGoogle Scholar
  28. 28.
    Bercoff J, Tanter M, Fink M (2004) Supersonic shear imaging: a new technique for soft tissue elasticity mapping. IEEE Trans Ultrason Ferroelectr Freq Control 51:396–409CrossRefGoogle Scholar
  29. 29.
    Garcia D, Le Tarnec L, Muth S, Montagnon E, Porée J, Cloutier G (2013) Stolt’s f-k migration for plane wave ultrasound imaging. IEEE Trans Ultrason Ferroelectr Freq Control 60:1853–1867CrossRefGoogle Scholar
  30. 30.
    Ophir J, Céspedes I, Ponnekanti H, Yazdi Y, Li X (1991) Elastography: a quantitative method for imaging the elasticity of biological tissues. Ultrason Imaging 13:111–134CrossRefGoogle Scholar
  31. 31.
    Bernal M, Nenadic I, Urban MW, Greenleaf JF (2011) Material property estimation for tubes and arteries using ultrasound radiation force and analysis of propagating modes. J Acoust Soc Am 129:1344–1354CrossRefGoogle Scholar
  32. 32.
    Destrempes F, Meunier J, Giroux MF, Soulez G, Cloutier G (2011) Segmentation of plaques in sequences of ultrasonic B-mode images of carotid arteries based on motion estimation and a Bayesian model. IEEE Trans Biomed Eng 58:2202–2211.  https://doi.org/10.1109/TBME.2011.2127476
  33. 33.
    Destrempes F, Porée J, Cloutier G (2013) Estimation method of the homodyned K-distribution based on the mean intensity and two log-moments. SIAM J Imaging Sci 6:1499–1530CrossRefGoogle Scholar
  34. 34.
    Destrempes F, Franceschini E, Yu FT, Cloutier G (2016) Unifying concepts of statistical and spectral quantitative ultrasound techniques. IEEE Trans Med Imaging 35:488–500CrossRefGoogle Scholar
  35. 35.
    Bigelow TA, Labyed Y (2013) Attenuation compensation and estimation. In: Mamou J, Oelze ML (eds) Quantitative ultrasound in soft tissues. Springer, Dordrecht, pp 71–93Google Scholar
  36. 36.
    Montaldo G, Tanter M, Bercoff J, Benech N, Fink M (2009) Coherent plane-wave compounding for very high frame rate ultrasonography and transient elastography. IEEE Trans Ultrason Ferroelectr Freq Control 56:489–506CrossRefGoogle Scholar
  37. 37.
    Breiman L (2001) Random forests. Mach Learn 45:5–32CrossRefGoogle Scholar
  38. 38.
    He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21:1263–1284CrossRefGoogle Scholar
  39. 39.
    Efron B, Tibshirani R (1997) Improvements on cross-validation: the 632+ bootstrap method. J Am Stat Assoc 92:548–560Google Scholar
  40. 40.
    DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44:837–845CrossRefGoogle Scholar
  41. 41.
    Davis J, Goadrich M (2006) The relationship between precision-recall and ROC curves. Proceedings of the 23rd international conference on machine learning. ACM, pp 233–240Google Scholar
  42. 42.
    Parker KJ, Doyley MM, Rubens DJ (2011) Imaging the elastic properties of tissue: the 20 year perspective. Phys Med Biol 56:R1–R29CrossRefGoogle Scholar
  43. 43.
    Barr RG (2014) Elastography in clinical practice. Radiol Clin North Am 52:1145–1162CrossRefGoogle Scholar
  44. 44.
    Iredale JP (2007) Models of liver fibrosis: exploring the dynamic nature of inflammation and repair in a solid organ. J Clin Invest 117:539–548CrossRefGoogle Scholar
  45. 45.
    Zeng X, Xu C, He D et al (2015) Influence of hepatic inflammation on FibroScan findings in diagnosing fibrosis in patients with chronic hepatitis B. Ultrasound Med Biol 41:1538–1544CrossRefGoogle Scholar
  46. 46.
    Dong DR, Hao MN, Li C et al (2015) Acoustic radiation force impulse elastography, FibroScan(®), Forns’ index and their combination in the assessment of liver fibrosis in patients with chronic hepatitis B, and the impact of inflammatory activity and steatosis on these diagnostic methods. Mol Med Rep 11:4174–4182CrossRefGoogle Scholar
  47. 47.
    Chen J, Talwalkar JA, Yin M, Glaser KJ, Sanderson SO, Ehman RL (2011) Early detection of nonalcoholic steatohepatitis in patients with nonalcoholic fatty liver disease by using MR elastography. Radiology 259:749–756CrossRefGoogle Scholar
  48. 48.
    Yoneda M, Suzuki K, Kato S et al (2010) Nonalcoholic fatty liver disease: US-based acoustic radiation force impulse elastography. Radiology 256:640–647CrossRefGoogle Scholar
  49. 49.
    Mohareri O, Ruszkowski A, Lobo J et al (2014) Multi-parametric 3D quantitative ultrasound vibro-elastography imaging for detecting palpable prostate tumors. Med Image Comput Comput Assist Interv 17:561–568Google Scholar
  50. 50.
    Roy-Cardinal M, Destrempes F, Soulez G, Cloutier G (2016) Homodyned K-distribution parametric maps combined with elastograms for carotid artery plaque assessment. 2016 IEEE International Ultrasonics Symposium (IUS) pp 1–4Google Scholar
  51. 51.
    Wang QB, Zhu H, Liu HL, Zhang B (2012) Performance of magnetic resonance elastography and diffusion-weighted imaging for the staging of hepatic fibrosis: a meta-analysis. Hepatology 56:239–247CrossRefGoogle Scholar

Copyright information

© European Society of Radiology 2018

Authors and Affiliations

  1. 1.Department of RadiologyCentre hospitalier de l’Université de Montréal (CHUM)QuébecCanada
  2. 2.Department of Radiology, Radio-oncology and Nuclear MedicineUniversité de Montréal and CRCHUMQuébecCanada
  3. 3.Laboratory of Medical Image AnalysisCentre de recherche du Centre hospitalier de l’Université de Montréal (CRCHUM)QuébecCanada
  4. 4.Université de MontréalInstitute of Biomedical EngineeringQuébecCanada
  5. 5.Laboratory of Biorheology and Medical Ultrasonics (LBUM)Centre de recherche du Centre hospitalier de l’Université de Montréal (CRCHUM)QuébecCanada
  6. 6.School of Mechanical EngineeringIran University of Science and TechnologyTehranIran
  7. 7.Department of PathologyCentre hospitalier de l’Université de Montréal (CHUM)QuébecCanada
  8. 8.Department of Pathology and Cellular BiologyUniversité de MontréalQuébecCanada

Personalised recommendations