Skip to main content

Advertisement

SpringerLink
Log in

Harmonization of radiomic feature distributions: impact on classification of hepatic tissue in CT imaging

  • Imaging Informatics and Artificial Intelligence
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

Following the craze for radiomic features (RF), their lack of reliability raised the question of the generalizability of classification models. Inter-site harmonization of images therefore becomes a central issue. We compared RF harmonization processing designed to detect liver diseases in CT images.

Methods

We retrospectively analyzed 76 multi-center portal CT series of non-diseased (NDL) and diseased liver (DL) patients. In each series, we positioned volumes of interest in spleen and liver, then extracted 9 RF (histogram and texture). We evaluated two RF harmonization approaches. First, in each series, we computed the Z-score of liver measurements based on those computed in the spleen. Second, we evaluated the ComBat method according to each imaging center; parameters were computed in the spleen and applied to the liver. We compared RF distributions and classification performances before/after harmonization. We classified NDL versus spleen and versus DL tissues.

Results

The RF distributions were all different between liver and spleen (p < 0.05). The Z-score harmonization outperformed for the detection of liver versus spleen: AUC = 93.1% (p < 0.001). For the detection of DL versus NDL, in a case/control setting, we found no differences between the harmonizations: mean AUC = 73.6% (p = 0.49). Using the whole datasets, the performances were improved using ComBat (p = 0.05) AUC = 82.4% and degraded with Z-score AUC = 67.4% (p = 0.008).

Conclusions

Data harmonization requires to first focus on data structuring to not degrade the performances of subsequent classifications. Liver tissue classification after harmonization of spleen-based RF is a promising strategy for improving the detection of DL tissue.

Key Points

• Variability of acquisition parameter makes radiomics of CT features non-reproducible.

• Data harmonization can help circumvent the inter-site variability of acquisition protocols.

• Inter-site harmonization must be carefully implemented and requires designing consistent data sets.

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.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Abbreviations

AUC:

Area under the curve

CI:

Confidence interval

CT:

Computed tomography

FOV:

Field of view

GLCM:

Gray-level co-occurrence matrix

GLZLM:

Gray-level zone length matrix

HCC:

Hepatocellular carcinoma

HU:

Hounsfield unit

ICC:

Intrahepatic cholangiocarcinoma

KNN:

K-nearest neighbor

LDA:

Linear discriminant analysis

NGLDM:

Neighboring gray-level dependence matrix

Nnet:

Neural network

QIB:

Quantitative imaging biomarker

RF:

Random forest

ROC:

Receiver operating characteristic

ROI:

Region of interest

SVM:

Support vector machine

VOI:

Volume of interest

References

  1. Alic L, Niessen WJ, Veenland JF (2014) Quantification of heterogeneity as a biomarker in tumor imaging: a systematic review. PLoS One 9:e110300. https://doi.org/10.1371/journal.pone.0110300

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  2. Traverso A, Wee L, Dekker A, Gillies R (2018) Repeatability and reproducibility of radiomic features: a systematic review. Int J Radiat Oncol Biol Phys 102:1143–1158. https://doi.org/10.1016/j.ijrobp.2018.05.053

    Article  PubMed  PubMed Central  Google Scholar 

  3. Lubner MG, Smith AD, Sandrasegaran K, Sahani DV, Pickhardt PJ (2017) CT texture analysis: definitions, applications, biologic correlates, and challenges. Radiographics 37:1483–1503. https://doi.org/10.1148/rg.2017170056

  4. Hatt M, Tixier F, Pierce L, Kinahan PE, Le Rest CC, Visvikis D (2017) Characterization of PET/CT images using texture analysis: the past, the present… any future? Eur J Nucl Med Mol Imaging 44:151–165. https://doi.org/10.1007/s00259-016-3427-0

  5. Eisenhauer EA, Therasse P, Bogaerts J et al (2009) New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1). Eur J Cancer 45:228–247. https://doi.org/10.1016/j.ejca.2008.10.026

    Article  CAS  Google Scholar 

  6. Kumar V, Gu Y, Basu S et al (2012) Radiomics: the process and the challenges. Magn Reson Imaging 30:1234–1248. https://doi.org/10.1016/j.mri.2012.06.010

    Article  PubMed  PubMed Central  Google Scholar 

  7. O’Connor JPB, Aboagye EO, Adams JE et al (2017) Imaging biomarker roadmap for cancer studies. Nat Rev Clin Oncol 14:169–186. https://doi.org/10.1038/nrclinonc.2016.162

    Article  CAS  PubMed  Google Scholar 

  8. Kalendralis P, Traverso A, Shi Z et al (2019) Multicenter CT phantoms public dataset for radiomics reproducibility tests. Med Phys 46:1512–1518. https://doi.org/10.1002/mp.13385

    Article  PubMed  Google Scholar 

  9. Mackin D, Fave X, Zhang L et al (2015) Measuring CT scanner variability of radiomics features. Invest Radiol 50:757–765. https://doi.org/10.1097/RLI.0000000000000180

    Article  PubMed  PubMed Central  Google Scholar 

  10. Simon P, Uma V (2018) Review of texture descriptors for texture classification. Data Eng Intell Comp 542:159–176. https://doi.org/10.1007/978-981-10-3223-3_15

    Article  Google Scholar 

  11. Ger RB, Zhou S, Chi PCM et al (2018) Comprehensive investigation on controlling for CT imaging variabilities in radiomics studies. Sci Rep 8:1–14. https://doi.org/10.1038/s41598-018-31509-z

    Article  CAS  Google Scholar 

  12. Berenguer R, Del Rosario Pastor-Juan M, Canales-Vázquez J et al (2018) Radiomics of CT features may be nonreproducible and redundant: influence of CT acquisition parameters. Radiology 288:407–415. https://doi.org/10.1148/radiol.2018172361

    Article  PubMed  Google Scholar 

  13. Johnson WE, Li C, Rabinovic A (2007) Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostatistics 8:118–127. https://doi.org/10.1093/biostatistics/kxj037

    Article  PubMed  Google Scholar 

  14. Orlhac F, Frouin F, Nioche C, Ayache N, Buvat I (2019) Validation of a method to compensate multicenter effects affecting CT radiomics. Radiology 291:53–59. https://doi.org/10.1148/radiol.2019182023

  15. Nioche C, Orlhac F, Boughdad S et al (2018) Lifex: a freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity. Cancer Res 78:4786–4789. https://doi.org/10.1158/0008-5472.CAN-18-0125

    Article  CAS  PubMed  Google Scholar 

  16. Orlhac F, Soussan M, Chouahnia K, Martinod E, Buvat I (2015) 18F-FDG PET-derived textural indices reflect tissue-specific uptake pattern in non-small cell lung cancer. PLoS One 10:1–16. https://doi.org/10.1371/journal.pone.0145063

  17. Caramella C, Allorant A, Orlhac F et al (2018) Can we trust the calculation of texture indices of CT images? A phantom study. Med Phys 45:1529–1536. https://doi.org/10.1002/mp.12809

    Article  PubMed  Google Scholar 

  18. Burke Ó, Benton S, Szafranski P et al (2016) Extending the scope of pooled analyses of individual patient biomarker data from heterogeneous laboratory platforms and cohorts using merging algorithms. Pregnancy Hypertens 6:53–59. https://doi.org/10.1016/j.preghy.2015.12.002

    Article  PubMed  Google Scholar 

  19. Mergo PJ, Ros PR, Buetow PC, Buck JL (1994) Diffuse disease of the liver: radiologic-pathologic correlation. Radiographics 14:1291–1307. https://doi.org/10.1148/radiographics.14.6.7855342

    Article  CAS  PubMed  Google Scholar 

  20. Ahmed AM, Ebid ME, Ajlan AM, Al-Mallah MH (2017) Low-dose attenuation correction in diagnosis of non-alcoholic fatty liver disease. Abdom Radiol (NY) 42:2454–2459. https://doi.org/10.1007/s00261-017-1166-8

    Article  Google Scholar 

  21. Team RDC (2011) R: a language and environment for statistical computing. R Found Stat Comput 1:409

    Google Scholar 

  22. Nygaard V, Rødland EA, Hovig E (2016) Methods that remove batch effects while retaining group differences may lead to exaggerated confidence in downstream analyses. Biostatistics 17:29–39. https://doi.org/10.1093/biostatistics/kxv027

    Article  PubMed  Google Scholar 

  23. Perrin T, Midya A, Yamashita R et al (2018) Short-term reproducibility of radiomic features in liver parenchyma and liver malignancies on contrast-enhanced CT imaging. Abdom Radiol (NY) 43:3271–3278. https://doi.org/10.1007/s00261-018-1600-6

    Article  Google Scholar 

  24. Brenet Defour L, Mulé S, Tenenhaus A et al (2019) Hepatocellular carcinoma: CT texture analysis as a predictor of survival after surgical resection. Eur Radiol 29:1231–1239. https://doi.org/10.1007/s00330-018-5679-5

    Article  PubMed  Google Scholar 

  25. Chen S, Zhu Y, Liu Z, Liang C (2017) Texture analysis of baseline multiphasic hepatic computed tomography images for the prognosis of single hepatocellular carcinoma after hepatectomy: A retrospective pilot study. Eur J Radiol 90:198–204. https://doi.org/10.1016/j.ejrad.2017.02.035

    Article  PubMed  Google Scholar 

  26. Park HJ, Kim JH, Choi S et al (2017) Prediction of therapeutic response of hepatocellular carcinoma to transcatheter arterial chemoembolization based on pretherapeutic dynamic CT and textural findings. AJR Am J Roentgenol 209:W211–W220. https://doi.org/10.2214/AJR.16.17398

    Article  PubMed  Google Scholar 

  27. Chang C-C, Chen H-H, Chang Y-C et al (2017) Computer-aided diagnosis of liver tumors on computed tomography images. Comput Methods Programs Biomed 145:45–51. https://doi.org/10.1016/j.cmpb.2017.04.008

    Article  PubMed  Google Scholar 

  28. Reinert CP, Kloth C, Fritz J, Nikolaoua K, Horgera M (2018) Discriminatory CT-textural features in splenic infiltration of lymphoma versus splenomegaly in liver cirrhosis versus normal spleens in controls and evaluation of their role for longitudinal lymphoma monitoring. Eur J Radiol 104:129–135. https://doi.org/10.1016/j.ejrad.2018.05.010

  29. Cozzi L, Dinapoli N, Fogliata A et al (2017) Radiomics based analysis to predict local control and survival in hepatocellular carcinoma patients treated with volumetric modulated arc therapy. BMC Cancer 17:1–10. https://doi.org/10.1186/s12885-017-3847-7

    Article  Google Scholar 

  30. Beckers RCJ, Trebeschi S, Maas M et al (2018) CT texture analysis in colorectal liver metastases and the surrounding liver parenchyma and its potential as an imaging biomarker of disease aggressiveness, response and survival. Eur J Radiol 102:15–21. https://doi.org/10.1016/j.ejrad.2018.02.031

    Article  CAS  PubMed  Google Scholar 

  31. Lee SJ, Zea R, Kim DH, Lubner MG, Deming DA, Pickhardt PJ (2018) CT texture features of liver parenchyma for predicting development of metastatic disease and overall survival in patients with colorectal cancer. Eur Radiol 28:1520–1528. https://doi.org/10.1007/s00330-017-5111-6

Download references

Acknowledgments

We gratefully acknowledge Sebastien Patriti, Mahaut Macrez, and Nicholas Terry for their support in this study.

Funding

This study did not receive any funding.

Author information

Authors and Affiliations

  1. Median Technologies, 06560, Valbonne, France

    Hubert Beaumont

  2. Centre Antoine Lacassagne, 06100, Nice, France

    Antoine Iannessi

  3. Centre Hospitalier Princesse Grâce, Avenue Pasteur, 98000, Monaco, Monaco

    Anne-Sophie Bertrand & Jean Michel Cucchi

  4. Hopital La Pitié Salpêtrière, 75000, Paris, France

    Olivier Lucidarme

Authors
  1. Hubert Beaumont
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Antoine Iannessi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Anne-Sophie Bertrand
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jean Michel Cucchi
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Olivier Lucidarme
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hubert Beaumont.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Hubert Beaumont.

Conflict of interest

The authors of this manuscript, Hubert Beaumont, as employee, declares relationships with Median Technologies.

Other authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was obtained from patients.

Ethical approval

For our retrospective study that did not include interaction or intervention with human subjects or include any access to identifiable private information, no IRB approval was required.

Study subjects or cohorts overlap

Study subjects or cohort were involved in other studies

Methodology

• Retrospective

• Experimental

• Performed at multiple institution

Additional information

Publisher’s note

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

Supplementary Information

ESM 1

(DOCX 574 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Beaumont, H., Iannessi, A., Bertrand, AS. et al. Harmonization of radiomic feature distributions: impact on classification of hepatic tissue in CT imaging. Eur Radiol 31, 6059–6068 (2021). https://doi.org/10.1007/s00330-020-07641-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-020-07641-8

Keywords

Search

Navigation