Skip to main content

Advertisement

SpringerLink
Log in

Accuracy of radiomics for differentiating diffuse liver diseases on non-contrast CT

  • Original Article
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Purpose

Radiomics help move cross-sectional imaging into the domain of quantitative imaging to assess the lesions, their stoma as well as in their temporal monitoring. We applied and assessed the accuracy of radiomics for differentiating healthy liver from diffuse liver diseases (cirrhosis, steatosis, amiodarone deposition, and iron overload) on non-contrast abdomen CT images in an institutional-reviewed board-approved, retrospective study.

Methods

Our study included 300 adult patients (mean age 63 ± 16 years; 171 men, 129 women) who underwent non-contrast abdomen CT and had either a healthy liver (n = 100 patients) or an evidence of diffuse liver disease (n = 200). The diffuse liver diseases included steatosis (n = 50), cirrhosis (n = 50), hyperdense liver due to amiodarone deposition (n = 50), or iron overload (n = 50). We manually segmented the liver in one section at the level of the porta hepatis (all 300 patients) and then over the entire liver volume (50 patients). Radiomics were estimated for the liver, and statistical comparison was performed with multiple logistic regression and random forest classifier.

Results

With random forest classifier, the AUC for radiomics ranged between 0.72 (iron overload vs. healthy liver) and 0.98 (hepatic steatosis vs. healthy liver) for differentiating diffuse liver disease from the healthy liver. Combined root mean square and gray-level co-occurrence matrix had the highest AUC (AUC:0.99, p < 0.01) for differentiating healthy liver from steatosis. Radiomics were more accurate for differentiating healthy liver from amiodarone (AUC:0.93) than from iron overload (AUC:0.79).

Conclusion

Radiomics enable differentiation of healthy liver from hepatic steatosis, cirrhosis, amiodarone deposition, and iron overload from a single section of non-contrast abdominal CT. The high accuracy of radiomics coupled with rapid segmentation of the region of interest, radiomics estimation, and statistical analyses within the same prototype makes a compelling case for bringing radiomics to clinical use for improving reporting in evaluation of healthy liver and diffuse liver diseases.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Abbreviations

CT:

Computed tomography

IRB:

Institutional ethical board

MRI:

Magnetic resonance imaging

AUC:

Area under the curve

NIH:

National institute of health

USA:

United states of America

HU:

Hounsfield unit

HIPAA:

Health Insurance Portability and Accountability Act

EPIC:

Electronic privacy information center

PACS:

Picture archiving communication system

ROI:

Region of interest

kV:

Kilovolt

GLCM:

Gray-level co-occurrence matrix

GLRLM:

Gray-level run length

GLSZM:

Gray-level size zone matrix

NGTDM:

Neighboring gray tone difference matrix

GLDM:

Gray-level dependence matrix

ROC:

Receiver operating characteristic

MCC:

Maximum correlation coefficient

Imc1:

Informational measure of correlation 1

References

  1. National Center for Health Statistics (2017) Chronic Liver Disease and Cirrhosis. Retrieved 6/18/19 from https://www.cdc.gov/nchs/fastats/liver-disease.htm

  2. Spengler EK, Loomba R (2015) Recommendations for diagnosis, referral for liver biopsy, and treatment of nonalcoholic fatty liver disease and nonalcoholic steatohepatitis. Mayo Clin Proc 90(9):1233–1246

    Article  Google Scholar 

  3. Li Q, Dhyani M, Grajo JR, Sirlin C, Samir AE (2018) Current status of imaging in nonalcoholic fatty liver disease. World J Hepatol 10(8):530–542

    Article  Google Scholar 

  4. Zeb I, Li D, Nasir K, Katz R, Larijani VN, Budoff MJ (2012) Computed tomography scans in the evaluation of fatty liver disease in a population-based study: the multi-ethnic study of atherosclerosis. Acad Radiol 19(7):811–818

    Article  Google Scholar 

  5. Yeom SK, Lee CH, Cha SH, Park CM (2015) Prediction of liver cirrhosis, using diagnostic imaging tools. World J Hepatol 7(17):2069–2079

    Article  Google Scholar 

  6. Hashmi A, Keswani NR, Kim S, Graham DY (2016) Hepatic dysfunction in patients receiving intravenous amiodarone. South Med J 109(2):83–86

    Article  CAS  Google Scholar 

  7. Kim BB, Kim DM, Choi DH, Chung JW, Koh YY, Chang KS, Hong SP (2014) Amiodarone toxicity showing high liver density on CT scan with normal liver function and plasma amiodarone levels in a long-term amiodarone user. Int J Cardiol 172(2):494–495

    Article  Google Scholar 

  8. Patrick D, White FE, Adams PC (1984) Long-term amiodarone therapy: a cause of increased hepatic attenuation on CT. Br J Radiol 57(679):573–576

    Article  CAS  Google Scholar 

  9. Siegelman ES, Mitchell DG, Semelka RC (1996) Abdominal iron deposition: metabolism, MR findings, and clinical importance. Radiology 199(1):13–22

    Article  CAS  Google Scholar 

  10. Queiroz-Andrade M, Blasbalg R, Ortega CD, Rodstein MA, Baroni RH, Rocha MS, Cerri GG (2009) MR imaging findings of iron overload. Radiographics 29(6):1575–1589

    Article  Google Scholar 

  11. Guyader D, Gandon Y, Deugnier Y, Jouanolle H, Loreal O, Simon M, Bourel M, Carsin M, Brissot P (1989) Evaluation of computed tomography in the assessment of liver iron overload. A study of 46 cases of idiopathic hemochromatosis. Gastroenterology 97(3):737–743

    Article  CAS  Google Scholar 

  12. 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(3):511–517

    Article  Google Scholar 

  13. Lubner MG, Jones D, Kloke J, Said A, Pickhardt PJ (2018) CT texture analysis of the liver for assessing hepatic fibrosis in patients with hepatitis C virus. Br J Radiol 11:20180153

    Article  Google Scholar 

  14. Li W, Huang Y, Zhuang BW, Liu GJ, Hu HT, Li X, Liang JY, Wang Z, Huang XW, Zhang CQ, Ruan SM, Xie XY, Kuang M, Lu MD, Chen LD, Wang W (2019) Multiparametric ultrasomics of significant liver fibrosis: a machine learning-based analysis. Eur Radiol 29(3):1496–1506

    Article  Google Scholar 

  15. Pickhardt PJ, Graffy PM, Said A, Jones D, Welsh B, Zea R, Lubner MG (2019) Multiparametric CT for noninvasive staging of hepatitis C virus-related liver fibrosis: correlation with the histopathologic fibrosis score. AJR Am J Roentgenol 212(3):547–553

    Article  Google Scholar 

  16. Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278(2):563–577

    Article  Google Scholar 

  17. Xu X, Zhang HL, Liu QP, Sun SW, Zhang J, Zhu FP, Yang G, Yan X, Zhang YD, Liu XS (2019) Radiomic analysis of contrast-enhanced CT predicts microvascular invasion and outcome in hepatocellular carcinoma. J Hepatol 70(6):1133–1144

    Article  Google Scholar 

  18. Rizzo S, Botta F, Raimondi S, Origgi D, Fanciullo C, Morganti AG, Bellomi M (2018) Radiomics: the facts and the challenges of image analysis. Eur Radiol Exp 2(1):36

    Article  Google Scholar 

  19. Wels MG, Lades F, Muehlberg A, Suehling M. General purpose radiomics for multi-modal clinical research. In: Proceedings of the SPIE 10950, medical imaging 2019: computer-aided diagnosis, 10950-150

  20. Liu X, Guo S, Yang B, Ma S, Zhang H, Li J, Sun C, Jin L, Li X, Yang Q, Fu Y (2018) Automatic organ segmentation for CT scans based on super-pixel and convolutional neural networks. J Digit Imaging 31(5):748–760

    Article  Google Scholar 

  21. Gibson E, Giganti F, Hu Y, Bonmati E, Bandula S, Gurusamy K, Davidson B, Pereira SP, Clarkson MJ, Barratt DC (2018) Automatic multi-organ segmentation on abdominal CT with dense V-networks. IEEE Trans Med Imaging 37(8):1822–1834

    Article  Google Scholar 

  22. Midya A, Chakraborty J, Gönen M, Do RKG, Simpson AL (2018) Influence of CT acquisition and reconstruction parameters on radiomic feature reproducibility. J Med Imaging (Bellingham) 5(1):011020

    Google Scholar 

  23. Berenguer R, Pastor-Juan MDR, Canales-Vázquez J, Castro-García M, Villas MV, Mansilla Legorburo F, Sabater S (2018) Radiomics of CT features may be nonreproducible and redundant: influence of CT acquisition parameters. Radiology 288(2):407–415

    Article  Google Scholar 

Download references

Funding

This work is an unfunded project.

Author information

Authors and Affiliations

  1. Department of Radiology, Massachusetts General Hospital, Harvard Medical School, 75 Blossom Court, Room 248, Boston, MA, 02114, USA

    Fatemeh Homayounieh, Sanjay Saini, Leila Mostafavi, Ruhani Doda Khera, Ramandeep Singh & Mannudeep K. Kalra

  2. Siemens Healthcare GmbH, Diagnostic Imaging Computed Tomography, Siemensstr. 3, 91301, Forchheim, Germany

    Michael Sühling, Bernhard Schmidt & Thomas Flohr

Authors
  1. Fatemeh Homayounieh
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sanjay Saini
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Leila Mostafavi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ruhani Doda Khera
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Michael Sühling
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Bernhard Schmidt
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Ramandeep Singh
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Thomas Flohr
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Mannudeep K. Kalra
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Fatemeh Homayounieh.

Ethics declarations

Conflict of interest

Michael Sühling, Bernhard Schmidt, and Thomas Flohr are employees of Siemens Healthineers. Mannudeep K. Kalra has received research Grant from Siemens Healthineers and Riverain for unrelated projects. The rest of authors declare that they have no conflict of interest.

Availability of data and material

Data are not available to be shared due to our institutional (Massachusetts General Hospital) policies.

Ethics approval

All procedures performed in this study involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards. This article does not contain any studies with animals performed by any of the authors.

Consent to participate

This study is a retrospective study and for this type of study formal consent is not required.

Consent for publication

This study has not been published or is not currently submitted or under review in other journals, and we are looking forward to be published in International Journal of Computer Assisted Radiology and Surgery (IJCARS).

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Homayounieh, F., Saini, S., Mostafavi, L. et al. Accuracy of radiomics for differentiating diffuse liver diseases on non-contrast CT. Int J CARS 15, 1727–1736 (2020). https://doi.org/10.1007/s11548-020-02212-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-020-02212-0

Keywords

Search

Navigation