nach oben

Erschienen in:

08.04.2020 | Imaging Informatics and Artificial Intelligence

Diagnostic accuracy of texture analysis and machine learning for quantification of liver fibrosis in MRI: correlation with MR elastography and histopathology

verfasst von: Khoschy Schawkat, Alexander Ciritsis, Sophie von Ulmenstein, Hanna Honcharova-Biletska, Christoph Jüngst, Achim Weber, Christoph Gubler, Joachim Mertens, Caecilia S. Reiner

Erschienen in: European Radiology | Ausgabe 8/2020

Einloggen, um Zugang zu erhalten

Abstract

Objectives

To compare the diagnostic accuracy of texture analysis (TA)–derived parameters combined with machine learning (ML) of non-contrast-enhanced T1w and T2w fat-saturated (fs) images with MR elastography (MRE) for liver fibrosis quantification.

Methods

In this IRB-approved prospective study, liver MRIs of participants with suspected chronic liver disease who underwent liver biopsy between August 2015 and May 2018 were analyzed. Two readers blinded to clinical and histopathological findings performed TA. The participants were categorized into no or low-stage (0–2) and high-stage (3–4) fibrosis groups. Confusion matrices were calculated using a support vector machine combined with principal component analysis. The diagnostic accuracy of ML-based TA of liver fibrosis and MRE was assessed by area under the receiver operating characteristic curves (AUC). Histopathology served as reference standard.

Results

A total of 62 consecutive participants (40 men; mean age ± standard deviation, 48 ± 13 years) were included. The accuracy of TA and ML on T1w was 85.7% (95% confidence interval [CI] 63.7–97.0) and 61.9% (95% CI 38.4–81.9) on T2w fs for classification of liver fibrosis into low-stage and high-stage fibrosis. The AUC for TA on T1w was similar to MRE (0.82 [95% CI 0.59–0.95] vs. 0.92 [95% CI 0.71–0.99], p = 0.41), while the AUC for T2w fs was significantly lower compared to MRE (0.57 [95% CI 0.34–0.78] vs. 0.92 [95% CI 0.71–0.99], p = 0.008).

Conclusion

Our results suggest that liver fibrosis can be quantified with TA-derived parameters of T1w when combined with a ML algorithm with similar accuracy compared to MRE.

Key Points

• Liver fibrosis can be categorized into low-stage fibrosis (0–2) and high-stage fibrosis (3–4) using texture analysis–derived parameters of T1-weighted images with a machine learning approach.

• For the differentiation of low-stage fibrosis and high-stage fibrosis, the diagnostic accuracy of texture analysis on T1-weighted images combined with a machine learning algorithm is similar compared to MR elastography.

Nur mit Berechtigung zugänglich

Standish RA, Cholongitas E, Dhillon A, Burroughs AK, Dhillon AP (2006) An appraisal of the histopathological assessment of liver fibrosis. Gut 55(4):569–578

Ellis EL, Mann DA (2012) Clinical evidence for the regression of liver fibrosis. J Hepatol 56(5):1171–1180CrossRef

Regev A, Berho M, Jeffers LJ et al (2002) Sampling error and intraobserver variation in liver biopsy in patients with chronic HCV infection. Am J Gastroenterol 97(10):2614–2618CrossRef

Ratziu V, Charlotte F, Heurtier A et al (2005) Sampling variability of liver biopsy in nonalcoholic fatty liver disease. Gastroenterology 128(7):1898–1906CrossRef

Friedrich-Rust M, Wunder K, Kriener S et al (2009) Liver fibrosis in viral hepatitis: noninvasive assessment with acoustic radiation force impulse imaging versus transient elastography. Radiology 252(2):595–604CrossRef

Gennisson J-L, Deffieux T, Fink M, Tanter M (2013) Ultrasound elastography: principles and techniques. Diagn Interv Imaging 94(5):487–495CrossRef

Yin M, Talwalkar JA, Glaser KJ et al (2007) Assessment of hepatic fibrosis with magnetic resonance elastography. Clin Gastroenterol Hepatol 5(10):1207–1213.e2CrossRef

Xanthakos SA, Podberesky DJ, Serai SD et al (2014) Use of magnetic resonance elastography to assess hepatic fibrosis in children with chronic liver disease. J Pediatr 164(1):186–188CrossRef

Yasar TK, Wagner M, Bane O et al (2016) Interplatform reproducibility of liver and spleen stiffness measured with MR elastography. J Magn Reson Imaging 43(5):1064–1072CrossRef

10.

Trout AT, Dillman JR, Xanthakos S et al (2016) Prospective assessment of correlation between US acoustic radiation force impulse and MR elastography in a pediatric population: dispersion of US shear-wave speed measurement matters. Radiology 281(2):544–552CrossRef

11.

Trout AT, Serai S, Mahley AD et al (2016) Liver stiffness measurements with MR elastography: agreement and repeatability across imaging systems, field strengths, and pulse sequences. Radiology 281(3):793–804CrossRef

12.

Ichikawa S, Motosugi U, Morisaka H et al (2015) Validity and reliability of magnetic resonance elastography for staging hepatic fibrosis in patients with chronic hepatitis B. Magn Reson Med Sci 14(3):211–221CrossRef

13.

Wagner M, Besa C, Ayache JB et al (2016) Magnetic resonance elastography of the liver: qualitative and quantitative comparison of gradient echo and spin echo echoplanar imaging sequences. Invest Radiol 51(9):575–581CrossRef

14.

Lefebvre T, Wartelle-Bladou C, Wong P et al (2019) Prospective comparison of transient, point shear wave, and magnetic resonance elastography for staging liver fibrosis. Eur Radiol. https://doi.org/10.1007/s00330-019-06331-4

15.

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 45:1276–1295

16.

Tang A, Cloutier G, Szeverenyi NM, Sirlin CB (2015) Ultrasound elastography and MR elastography for assessing liver fibrosis: part 2, diagnostic performance, confounders, and future directions. AJR Am J Roentgenol 205(1):33–40

17.

Lubner MG, Smith AD, Sandrasegaran K, Sahani DV, Pickhardt PJ (2017) CT texture analysis: definitions, applications, biologic correlates, and challenges. Radiographics 37:1483–1503

18.

Ingrisch M, Schneider MJ, Nörenberg D et al (2017) Radiomic analysis reveals prognostic information in T1-weighted baseline magnetic resonance imaging in patients with glioblastoma. Invest Radiol 52(6):360–366CrossRef

19.

Aerts HJWL, Velazquez ER, Leijenaar RTH et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:4006CrossRef

20.

Lubner MG, Malecki K, Kloke J, Ganeshan B, Pickhardt PJ (2017) Texture analysis of the liver at MDCT for assessing hepatic fibrosis. Abdom Radiol (NY) 42(8):2069–2078

21.

Daginawala N, Li B, Buch K et al (2016) Using texture analyses of contrast enhanced CT to assess hepatic fibrosis. Eur J Radiol 85(3):511–517CrossRef

22.

Kato H, Kanematsu M, Zhang X et al (2007) Computer-aided diagnosis of hepatic fibrosis: preliminary evaluation of MRI texture analysis using the finite difference method and an artificial neural network. AJR Am J Roentgenol 189(1):117–122

23.

Barry B, Buch K, Soto JA, Jara H, Nakhmani A, Anderson SW (2014) Quantifying liver fibrosis through the application of texture analysis to diffusion weighted imaging. Magn Reson Imaging 32(1):84–90

24.

Bahl G, Cruite I, Wolfson T et al (2012) Noninvasive classification of hepatic fibrosis based on texture parameters from double contrast-enhanced magnetic resonance images. J Magn Reson Imaging 36(5):1154–1161CrossRef

25.

Marcon M, Ciritsis A, Rossi C et al (2019) Diagnostic performance of machine learning applied to texture analysis-derived features for breast lesion characterisation at automated breast ultrasound: a pilot study. Eur Radiol Exp 3(1):44CrossRef

26.

Erickson BJ, Korfiatis P, Akkus Z, Kline TL (2017) Machine learning for medical imaging. Radiographics 37(2):505–515CrossRef

27.

Choy G, Khalilzadeh O, Michalski M et al (2018) Current applications and future impact of machine learning in radiology. Radiology 288(2):318–328CrossRef

28.

Goodman ZD (2007) Grading and staging systems for inflammation and fibrosis in chronic liver diseases. J Hepatol 47(4):598–607CrossRef

29.

Batts KP, Ludwig J (1995) Chronic hepatitis. An update on terminology and reporting. Am J Surg Pathol 19(12):1409–1417CrossRef

30.

Brunt EM, Kleiner DE, Wilson LA et al (2011) Nonalcoholic fatty liver disease (NAFLD) activity score and the histopathologic diagnosis in NAFLD: distinct clinicopathologic meanings. Hepatology 53(3):810–820CrossRef

31.

Szczypiński PM, Strzelecki M, Materka A, Klepaczko A (2009) MaZda-A software package for image texture analysis. Comput Methods Programs Biomed 94(1):66–76CrossRef

32.

Collewet G, Strzelecki M, Mariette F (2004) Influence of MRI acquisition protocols and image intensity normalization methods on texture classification. Magn Reson Imaging 22(1):81–91CrossRef

33.

Fawcett T (2006) An introduction to ROC analysis. Pattern Recogn Lett 27:861–874CrossRef

34.

Kayaalti Ö, Aksebzeci BH, Karahan IÖ et al (2014) Liver fibrosis staging using CT image texture analysis and soft computing. Appl Soft Comput J 25:399–413CrossRef

35.

Varenika V, Fu Y, Maher JJ et al (2013) Hepatic fibrosis: evaluation with semiquantitative contrast-enhanced CT. Radiology 266(1):151–158CrossRef

36.

House MJ, Bangma SJ, Thomas M et al (2015) Texture-based classification of liver fibrosis using MRI. J Magn Reson Imaging 41(2):322–328CrossRef

37.

Yu H, Buch K, Li B et al (2015) Utility of texture analysis for quantifying hepatic fibrosis on proton density MRI. J Magn Reson Imaging 42(5):1259–1265CrossRef

38.

Yokoo T, Wolfson T, Iwaisako K et al (2015) Evaluation of liver fibrosis using texture analysis on combined-contrast-enhanced magnetic resonance images at 3.0T. Biomed Res Int 2015:387653CrossRef

39.

Cannella R, Borhani AA, Tublin M, Behari J, Furlan A (2019) Diagnostic value of MR-based texture analysis for the assessment of hepatic fibrosis in patients with nonalcoholic fatty liver disease (NAFLD). Abdom Radiol (NY) 44(5):1816–1824

40.

Zhang X, Gao X, Liu BJ et al (2015) Effective staging of fibrosis by the selected texture features of liver: which one is better, CT or MR imaging? Comput Med Imaging Graph 46(Pt 2):227–236CrossRef

41.

Berenguer R, Pastor-Juan MDR, Canales-Vázquez J et al (2018) Radiomics of CT features may be nonreproducible and redundant: influence of CT acquisition parameters. Radiology 288(2):407–415CrossRef

42.

Landis JR, Koch GG (1977) The measurement of observer agreement for categorical data. Biometrics 33(1):159–174

43.

He L, Li H, Dudley JA et al (2019) Machine learning prediction of liver stiffness using clinical and T2-weighted MRI radiomic data. AJR Am J Roentgenol 213(3):592–601

44.

Yasaka K, Akai H, Kunimatsu A, Abe O, Kiryu S (2017) Liver fibrosis: deep convolutional neural network for staging by using gadoxetic acid–enhanced hepatobiliary phase MR images. Radiology 287(1):146–155

Titel: Diagnostic accuracy of texture analysis and machine learning for quantification of liver fibrosis in MRI: correlation with MR elastography and histopathology
verfasst von: Khoschy Schawkat
Alexander Ciritsis
Sophie von Ulmenstein
Hanna Honcharova-Biletska
Christoph Jüngst
Achim Weber
Christoph Gubler
Joachim Mertens
Caecilia S. Reiner
Publikationsdatum: 08.04.2020
Verlag: Springer Berlin Heidelberg
Erschienen in: European Radiology / Ausgabe 8/2020
Print ISSN: 0938-7994
Elektronische ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-020-06831-8

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Springer Medizin

Diagnostic accuracy of texture analysis and machine learning for quantification of liver fibrosis in MRI: correlation with MR elastography and histopathology