Abstract
Purpose
Detection of early-stage liver fibrosis has direct clinical implications on patient management and treatment. The aim of this paper is to develop a non-invasive, cost-effective method for classifying liver disease between “non-fibrosis” (F0) and “fibrosis” (F1–F4), and to evaluate the classification performance quantitatively.
Methods
Image data from 75 patients who underwent a simultaneous liver biopsy and non-contrast CT examination were used for this study. Non-contrast CT image texture features such as wavelet-based features, standard deviation of variance filter, and mean CT number were calculated in volumes of interest (VOIs) positioned within the liver parenchyma. In addition, a combined feature was calculated using logistic regression with L2-norm regularization to further improve fibrosis detection. Based on the final pathology from the liver biopsy, the patients were labelled either as “non-fibrosis” or “fibrosis”. Receiver-operating characteristic (ROC) curve, area under the ROC curve (AUROC), specificity, sensitivity, and accuracy were determined for the algorithm to differentiate between “non-fibrosis” and “fibrosis”.
Results
The combined feature showed the highest classification performance with an AUROC of 0.86, compared to the wavelet-based feature (AUROC, 0.76), the standard deviation of variance filter (AUROC, 0.65), and mean CT number (AUROC, 0.84). The combined feature’s specificity, sensitivity, and accuracy were 0.66, 0.88, and 0.76, respectively, showing the most promising results.
Conclusion
A new non-invasive and cost-effective method was developed to classify liver diseases between “non-fibrosis” (F0) and “fibrosis” (F1–F4). The proposed method makes it possible to detect liver fibrosis in asymptomatic patients using non-contrast CT images for better patient management and treatment.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ginès P, Graupera I, Lammert F, Angeli P, Caballeria L, Krag A, Guha IN, Murad SD, Castera L (2016) Screening for liver fibrosis in the general population: a call for action. Lancet Gastroenterol Hepatol 1:256–260
Friedman SL (1993) The cellular basis of hepatic fibrosis. In: Seminars in medicine of the Beth Israel Hospital Boston. Mechanisms and treatment strategies. New Engl J Med 328(25):1828–1835
Ishak KG (2000) Pathologic features of chronic hepatitis: a review and update. Am J Clin Pathol 113(1):40–55
Chalasani N, Younossi Z, Lavine JE, Diehl AM, Brunt EM, Cusi K, Charlton M, Sanyal AJ (2012) The diagnosis and management of non-alcoholic fatty liver disease: practice guideline by the american association for the study of liver diseases, American College of Gastroenterology, and the American Gastroenterological Association. Hepatology 55:2005–2023. https://doi.org/10.1002/HEP.25762
Coulon S, Heindryckx F, Geerts A, Steenkiste CV, Colle I, Vlierberghe HV (2011) Angiogenesis in chronic liver disease and its complications. Liver Int 31:146–162. https://doi.org/10.1111/J.1478-3231.2010.02369.X
Goodman ZD (2007) Grading and staging systems for inflammation and fibrosis in chronic liver diseases. J Hepatol 47(4):598–607. https://doi.org/10.1016/j.jhep.2007.07.006
Elesawy BH, El-hafez AA, Dorghamb LS, El-Askary A (2014) Limited reliability of five non-invasive biomarkers in predicting hepatic fibrosis in chronic HCV mono-infected patients opposed to METAVIR scoring. Pathol Res Pract 210(12):922–928. https://doi.org/10.1016/j.prp.2014.07.005
Guha IN, Parkes J, Roderick P, Chattopadhyay D, Cross R, Harris S, Kaye P, Burt AD, Ryder SD, Aithal GP, Day CP, Rosenberg WM (2008) Non-invasive markers of fibrosis in nonalcoholic fatty liver disease: validating the European Liver Fibrosis Panel and exploring simple markers. Hepatology 47(2):455–460. https://doi.org/10.1002/hep.21984
Li Q, Yu B, Tian X, Cui X, Zhang R, Guo Q (2020) Deep residual nets model for staging liver fibrosis on plain CT images. Int J CARS 15:1399–1406. https://doi.org/10.1007/s11548-020-02206-y
Li Q, Kang H, Zhang R, Guo Q (2022) Non-invasive precise staging of liver fibrosis using deep residual network model based on plain CT images. Int J CARS 17:627–637. https://doi.org/10.1007/s11548-022-02573-8
Lubner MG, Jones D, Kloke J, Said A, Pickhardt PJ (2019) CT texture analysis of the liver for assessing hepatic fibrosis in patients with hepatitis C virus. Br J Radiol 92:20180153. https://doi.org/10.1259/bjr.20180153
Lubner MG, Malecki K, Kloke J, Ganeshan B, Pickhardt PJ (2017) Texture analysis of the liver at MDCT for assessing hepatic fibrosis. Abdom Radiol 42:2069–2078. https://doi.org/10.1007/s00261-017-1096-5
Pickhardt PJ, Graffy PM, Said A, Jones D, Welsh B, Zea R, Lubner MG (2019) Multiparametric CT for non-invasive staging of hepatitis C virus-related liver fibrosis: correlation with the histopathologic fibrosis score. AJR Am J Roentgenol 212(3):547–553. https://doi.org/10.2214/AJR.18.20284
Homayounieh F, Saini S, Mostafavi L, Khera RD, Sühling M, Schmidt B, Singh R, Flohr T, Kalra MK (2020) Accuracy of radiomics for differentiating diffuse liver diseases on non-contrast CT. Int J CARS 15:1727–1736. https://doi.org/10.1007/s11548-020-02212-0
Daginawala N, Li B, Buch K, Yu H, Tischler B, Qureshi MM, Soto JA, Anderson S (2016) Using texture analyses of contrast enhanced CT to assess hepatic fibrosis. Eur J Radiol 85:511–517. https://doi.org/10.1016/J.EJRAD.2015.12.009
Budai BK, Tóth A, Borsos P, Frank VG, Shariati S, Fejér B, Folhoffer A, Szalay F, Bérczi V, Kaposi PN (2020) Three-dimensional CT texture analysis of anatomic liver segments can differentiate between low-grade and high-grade fibrosis. BMC Med Imaging 20:1–11. https://doi.org/10.1186/s12880-020-00508-w
Kayaalti Ö, Aksebzeci BH, Karahan IÖ, Deniz K, Öztürk M, Yılmaz B, Kara S, Asyalı MH (2014) Liver fibrosis staging using CT image texture analysis and soft computing. Appl Soft Comput 25:399–413. https://doi.org/10.1016/J.ASOC.2014.08.065
Yeung J, Ganeshan B, Endozo R, Hall A, Wan S, Groves A, Taylor SA, Bandula S (2020) Equilibrium CT Texture analysis for the evaluation of hepatic fibrosis: preliminary evaluation against histopathology and extracellular volume fraction. J Pers Med 10(2):46. https://doi.org/10.3390/JPM10020046
Hyodo T, Yada N, Maenishi O, Matsuki M, Murakami T (2018) Hepatic steatosis and fibrosis: evaluation with CT imaging. Kanzo 59(8):393–406. https://doi.org/10.2957/kanzo.59.393
Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3(6):610–621
Galloway MM (1975) Texture analysis using gray level run lengths. Comput Graphics Image Process 4(2):172–179. https://doi.org/10.1016/S0146-664X(75)80008-6
Rachidi M, Marchadier A, Gadois C, Lespessailles E, Chappard C, Benhamou CL (2008) Laws’ masks descriptors applied to bone texture analysis: an innovativeand discriminant tool in osteoporosis. Skeletal Radiol 37(6):541–548. https://doi.org/10.1007/s00256-008-0463-2
Amadasun M, King R (1989) Textural features corresponding to textural properties. IEEE Trans Syst Man Cybern 19(5):1264–1274. https://doi.org/10.1109/21.44046
Lewin M, Poujol-Robert A, Boëlle PY, Wendum D, Lasnier E, Viallon M (2007) Diffusion-weighted magnetic resonance imaging for the assessment of fibrosis in chronic hepatitis C. Hepatology 46(3):658–665
Fang C, Jaffer OS, Yusuf GT, Konstantatou E, Quinlan DJ, Agarwal K, Quaglia A, Sidhu PS (2018) Reducing the number of measurements in liver point shear-wave elastography: factors that influence the number and reliability of measurements in assessment of liver fibrosis in clinical practice. Radiology 287(3):844–852
Schmeltzer PA, Talwalkar JA (2011) Non-invasive tools to assess hepatic fibrosis: ready for prime time? Gastroenterol Clin N Am 40(3):507–521
Glaser KJ, Manduca A, Ehman RL (2012) Review of MR elastography applications and recent developments. J Magn Reson Imaging 36(4):757–774
Funding
This work was funded by Canon Medical Systems Corporation.
Author information
Authors and Affiliations
Contributions
Conceptualization: RH, SO, PR Acquisition: PR, CF, BH Analysis: RH, CH Software: RH Writing—original draft preparation: RH Writing—review and editing: TS, YF, SO, BH Revise: All Supervision: PR, TS Approval: All.
Corresponding author
Ethics declarations
Conflict of interest
Ryo Hirano, Yasuko Fujisawa, Shigeharu Ohyu, Chihiro Hattori, Takuya Sakaguchi are employee of Canon Medical Systems Corporation. Christin Farrell is employee of Canon Medical Systems Canada Limited. Bernice Hoppel is employee of Canon Medical Systems USA, Inc. Patrik Rogalla has received research grants from Canon Medical Systems Corporation.
Ethical approval
This work was approved by Research Ethics Board (REB) of University of Toronto (18–5652).
Informed consent
Patients informed consent was performed before data acquisition.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Ryo Hirano and Patrik Rogalla equally contributed to this work.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Hirano, R., Rogalla, P., Farrell, C. et al. Development of a classification method for mild liver fibrosis using non-contrast CT image. Int J CARS 17, 2041–2049 (2022). https://doi.org/10.1007/s11548-022-02724-x
Received:
Accepted:
Published:
Version of record:
Issue date:
DOI: https://doi.org/10.1007/s11548-022-02724-x