Skip to main content

Advertisement

SpringerLink
Log in

A simple and robust classification tree for differentiation between benign and malignant lesions in MR-mammography

  • Breast
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

In the face of multiple available diagnostic criteria in MR-mammography (MRM), a practical algorithm for lesion classification is needed. Such an algorithm should be as simple as possible and include only important independent lesion features to differentiate benign from malignant lesions. This investigation aimed to develop a simple classification tree for differential diagnosis in MRM.

Methods

A total of 1,084 lesions in standardised MRM with subsequent histological verification (648 malignant, 436 benign) were investigated. Seventeen lesion criteria were assessed by 2 readers in consensus. Classification analysis was performed using the chi-squared automatic interaction detection (CHAID) method. Results include the probability for malignancy for every descriptor combination in the classification tree.

Results

A classification tree incorporating 5 lesion descriptors with a depth of 3 ramifications (1, root sign; 2, delayed enhancement pattern; 3, border, internal enhancement and oedema) was calculated. Of all 1,084 lesions, 262 (40.4 %) and 106 (24.3 %) could be classified as malignant and benign with an accuracy above 95 %, respectively. Overall diagnostic accuracy was 88.4 %.

Conclusions

The classification algorithm reduced the number of categorical descriptors from 17 to 5 (29.4 %), resulting in a high classification accuracy. More than one third of all lesions could be classified with accuracy above 95 %.

Key Points

• A practical algorithm has been developed to classify lesions found in MR-mammography.

• A simple decision tree consisting of five criteria reaches high accuracy of 88.4 %.

• Unique to this approach, each classification is associated with a diagnostic certainty.

• Diagnostic certainty of greater than 95 % is achieved in 34 % of all cases.

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
Fig. 6

Similar content being viewed by others

References

  1. Warner E, Messersmith H, Causer P, Eisen A, Shumak R, Plewes D (2008) Systematic review: using magnetic resonance imaging to screen women at high risk for breast cancer. Ann Intern Med 148:671–679

    Article  PubMed  Google Scholar 

  2. Baum F, Fischer U, Vosshenrich R, Grabbe E (2002) Classification of hypervascularized lesions in CE MR imaging of the breast. Eur Radiol 12:1087–1092

    Article  PubMed  CAS  Google Scholar 

  3. Williams TC, DeMartini WB, Partridge SC, Peacock S, Lehman CD (2007) Breast MR imaging: computer-aided evaluation program for discriminating benign from malignant lesions. Radiology 244:94–103

    Article  PubMed  Google Scholar 

  4. Kaiser WA, Zeitler E (1989) MR imaging of the breast: fast imaging sequences with and without Gd-DTPA. Preliminary observations. Radiology 170:681–686

    PubMed  CAS  Google Scholar 

  5. Kuhl CK, Mielcareck P, Klaschik S et al (1999) Dynamic breast MR imaging: are signal intensity time course data useful for differential diagnosis of enhancing lesions? Radiology 211:101–110

    PubMed  CAS  Google Scholar 

  6. Benndorf M, Baltzer PAT, Kaiser WA (2011) Assessing the degree of collinearity among the lesion features of the MRI BI-RADS lexicon. Eur J Radiol 80:e322–e324

    Article  PubMed  Google Scholar 

  7. Malich A, Fischer DR, Wurdinger S et al (2005) Potential MRI interpretation model: differentiation of benign from malignant breast masses. AJR Am J Roentgenol 185:964–970

    Article  PubMed  Google Scholar 

  8. Nunes LW, Schnall MD, Orel SG et al (1997) Breast MR imaging: interpretation model. Radiology 202:833–841

    PubMed  CAS  Google Scholar 

  9. Tozaki M, Fukuda K (2006) High-spatial-resolution MRI of non-masslike breast lesions: interpretation model based on BI-RADS MRI descriptors. AJR Am J Roentgenol 187:330–337

    Article  PubMed  Google Scholar 

  10. Tozaki M, Igarashi T, Matsushima S, Fukuda K (2005) High-spatial-resolution MR imaging of focal breast masses: interpretation model based on kinetic and morphological parameters. Radiat Med 23:43–50

    PubMed  Google Scholar 

  11. Demartini WB, Kurland BF, Gutierrez RL, Blackmore CC, Peacock S, Lehman CD (2011) Probability of malignancy for lesions detected on breast MRI: a predictive model incorporating BI-RADS imaging features and patient characteristics. Eur Radiol 21:1609–1617

    Article  PubMed  Google Scholar 

  12. Schnall MD, Blume J, Bluemke DA et al (2006) Diagnostic architectural and dynamic features at breast MR imaging: multicenter study. Radiology 238:42–53

    Article  PubMed  Google Scholar 

  13. Kass GV (1980) An exploratory technique for investigating large quantities of categorical data. Appl Stat 29:119

    Article  Google Scholar 

  14. Dietzel M, Baltzer PA, Vag T et al (2010) Differential diagnosis of breast lesions 5 mm or less: is there a role for magnetic resonance imaging? J Comput Assist Tomogr 34:456–464

    Article  PubMed  Google Scholar 

  15. Dietzel M, Baltzer PAT, Vag T et al (2010) Application of breast MRI for prediction of lymph node metastases - systematic approach using 17 individual descriptors and a dedicated decision tree. Acta Radiol 51(8):885–894

    Article  PubMed  Google Scholar 

  16. Dietzel M, Baltzer PA, Vag T et al (2010) Magnetic resonance mammography of invasive lobular versus ductal carcinoma: systematic comparison of 811 patients reveals high diagnostic accuracy irrespective of typing. J Comput Assist Tomogr 34(4):587–595

    Article  PubMed  Google Scholar 

  17. Dietzel M, Baltzer PA, Vag T et al (2011) Potential of MR mammography to predict tumor grading of invasive breast cancer. Rofo 183(9):826–833

    Article  PubMed  CAS  Google Scholar 

  18. Dietzel M, Baltzer PAT, Dietzel A et al (2012) Artificial Neural Networks for differential diagnosis of breast lesions in MR-Mammography: a systematic approach addressing the influence of network architecture on diagnostic performance using a large clinical database. Eur J Radiol 81(7):1508–1513

    Article  PubMed  Google Scholar 

  19. Dietzel M, Baltzer PAT, Dietzel A et al (2010) Application of artificial neural networks for the prediction of lymph node metastases to the ipsilateral axilla - initial experience in 194 patients using magnetic resonance mammography. Acta Radiol 51(8):851–858

    Article  PubMed  Google Scholar 

  20. Dietzel M, Baltzer PAT, Vag T, Gajda M, Camara O, Kaiser WA (2010) The hook sign for differential diagnosis of malignant from benign lesions in magnetic resonance mammography: experience in a study of 1084 histologically verified cases. Acta Radiol 51(2):137–143

    Article  PubMed  Google Scholar 

  21. Dietzel M, Baltzer PAT, Vag T et al (2010) The adjacent vessel sign on breast MRI: new data and a subgroup analysis for 1,084 histologically verified cases. Korean J Radiol 11(2):178–186

    Article  PubMed  Google Scholar 

  22. Dietzel M, Baltzer PAT, Vag T et al (2010) The necrosis sign in magnetic resonancemammography: diagnostic accuracy in 1,084 histologically verified breast lesions. Breast J 16(6):603–608

    Article  PubMed  Google Scholar 

  23. Dietzel M, Baltzer PA, Vag T et al (2011) Magnetic resonance mammography in small vs. advanced breast lesions - systematic comparison reveals significant impact of lesion size on diagnostic accuracy in 936 histologically verified breast lesions. Rofo 183(2):126–135

    Article  PubMed  CAS  Google Scholar 

  24. Bland JM (2000) An introduction to medical statistics. Oxford University Press, Oxford

  25. Sardanelli F, Boetes C, Borisch B et al (2010) Magnetic resonance imaging of the breast: recommendations from the EUSOMA working group. Eur J Cancer 46:1296–1316

    Article  PubMed  Google Scholar 

  26. Warren RML, Thompson D, Pointon LJ et al (2006) Evaluation of a prospective scoring system designed for a multicenter breast MR imaging screening study. Radiology 239:677–685

    Article  PubMed  Google Scholar 

  27. Gutierrez RL, DeMartini WB, Eby PR, Kurland BF, Peacock S, Lehman CD (2009) BI-RADS lesion characteristics predict likelihood of malignancy in breast MRI for masses but not for nonmasslike enhancement. AJR Am J Roentgenol 193:994–1000

    Article  PubMed  Google Scholar 

  28. Baltzer PAT, Benndorf M, Dietzel M, Gajda M, Runnebaum IB, Kaiser WA (2010) False-positive findings at contrast-enhanced breast MRI: a BI-RADS descriptor study. AJR Am J Roentgenol 194:1658–1663

    Article  PubMed  Google Scholar 

  29. Fischer DR, Wurdinger S, Boettcher J, Malich A, Kaiser WA (2005) Further signs in the evaluation of magnetic resonance mammography: a retrospective study. Invest Radiol 40:430–435

    Article  PubMed  Google Scholar 

  30. Sakamoto N, Tozaki M, Higa K et al (2008) Categorization of non-mass-like breast lesions detected by MRI. Breast Cancer 15:241–246

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

This work was presented at the European Congress of Radiology 2012. Subsets of the database investigated in this study have been used in previous publications in different contexts.

Author information

Authors and Affiliations

  1. Department of Radiology, Medical University Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria

    Pascal A. T. Baltzer

  2. Department of Neuroradiology, University hospital Erlangen, Erlangen, Germany

    Matthias Dietzel

  3. Institute of Diagnostic and Interventional Radiology 1, University Hospital Jena, Jena, Germany

    Werner A. Kaiser

Authors
  1. Pascal A. T. Baltzer
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Matthias Dietzel
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Werner A. Kaiser
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Pascal A. T. Baltzer.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Baltzer, P.A.T., Dietzel, M. & Kaiser, W.A. A simple and robust classification tree for differentiation between benign and malignant lesions in MR-mammography. Eur Radiol 23, 2051–2060 (2013). https://doi.org/10.1007/s00330-013-2804-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-013-2804-3

Keywords

Search

Navigation