SpringerLink
Log in

Assessment of breast lesions by the Kaiser score for differential diagnosis on MRI: the added value of ADC and machine learning modeling

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

    We’re sorry, something doesn't seem to be working properly.

    Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Abstract

Objectives

To evaluate the diagnostic performance of Kaiser score (KS) adjusted with the apparent diffusion coefficient (ADC) (KS+) and machine learning (ML) modeling.

Methods

A dataset of 402 malignant and 257 benign lesions was identified. Two radiologists assigned the KS. If a lesion with KS > 4 had ADC > 1.4 × 10−3 mm2/s, the KS was reduced by 4 to become KS+. In order to consider the full spectrum of ADC as a continuous variable, the KS and ADC values were used to train diagnostic models using 5 ML algorithms. The performance was evaluated using the ROC analysis, compared by the DeLong test. The sensitivity, specificity, and accuracy achieved using the threshold of KS > 4, KS+ > 4, and ADC ≤ 1.4 × 10−3 mm2/s were obtained and compared by the McNemar test.

Results

The ROC curves of KS, KS+, and all ML models had comparable AUC in the range of 0.883–0.921, significantly higher than that of ADC (0.837, p < 0.0001). The KS had sensitivity = 97.3% and specificity = 59.1%; and the KS+ had sensitivity = 95.5% with significantly improved specificity to 68.5% (p < 0.0001). However, when setting at the same sensitivity of 97.3%, KS+ could not improve specificity. In ML analysis, the logistic regression model had the best performance. At sensitivity = 97.3% and specificity = 65.3%, i.e., compared to KS, 16 false-positives may be avoided without affecting true cancer diagnosis (p = 0.0015).

Conclusion

Using dichotomized ADC to modify KS to KS+ can improve specificity, but at the price of lowered sensitivity. Machine learning algorithms may be applied to consider the ADC as a continuous variable to build more accurate diagnostic models.

Key Points

• When using ADC to modify the Kaiser score to KS+, the diagnostic specificity according to the results of two independent readers was improved by 9.4–9.7%, at the price of slightly degraded sensitivity by 1.5–1.8%, and overall had improved accuracy by 2.6–2.9%.

• When the KS and the continuous ADC values were combined to train models by machine learning algorithms, the diagnostic specificity achieved by the logistic regression model could be significantly improved from 59.1 to 65.3% (p = 0.0015), while maintaining at the high sensitivity of KS = 97.3%, and thus, the results demonstrated the potential of ML modeling to further evaluate the contribution of ADC.

• When setting the sensitivity at the same levels, the modified KS+ and the original KS have comparable specificity; therefore, KS+ with consideration of ADC may not offer much practical help, and the original KS without ADC remains as an excellent robust diagnostic method.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Abbreviations

ADC:

Apparent diffusion coefficient

AUC:

Area under ROC curve

BI-RADS:

Breast Imaging Reporting and Data System

BPE:

Background parenchymal enhancement

CI:

Confidence interval

DCE:

Dynamic contrast-enhanced

DCIS:

Ductal carcinoma in situ

DWI:

Diffusion-weighted imaging

ICC:

Intraclass correlation coefficient

KS:

Kaiser score

LDA:

Linear discriminant analysis

LR:

Logistic regression

ML:

Machine learning

MRI:

Magnetic resonance imaging

NB:

Naive Bayes

ROC:

Receiver operator characteristic

ROI:

Region of interest

SVM_L:

Linear kernel support vector machine

SVM_R:

Radial kernel support vector machine

VIBRANT:

Volume imaging for breast assessment

References

  1. Mann RM, Cho N, Moy L (2019) Breast MRI: state of the art. Radiology 292:520–536

    Article  Google Scholar 

  2. Mann RM, Kuhl CK, Moy L (2019) Contrast-enhanced MRI for breast cancer screening. J Magn Reson Imaging 50:377–390

    Article  Google Scholar 

  3. Sumkin JH, Berg WA, Carter GJ et al (2019) Diagnostic performance of MRI, molecular breast imaging, and contrast-enhanced mammography in women with newly diagnosed breast cancer. Radiology 293:531–540

    Article  Google Scholar 

  4. D’Orsi CJ, Sickles EA, Mendelson EB, Morris EA (2013) ACR BI-RADS atlas, breast imaging reporting and data system. American College of Radiology, Reston

  5. Eghtedari M, Chong A, Rakow-Penner R, Ojeda-Fournier H (2021) Current status and future of BI-RADS in multimodality imaging, from the AJR Special Series on Radiology Reporting and Data Systems. AJR Am J Roentgenol 216:860–873

    Article  Google Scholar 

  6. Rawashdeh M, Lewis S, Zaitoun M, Brennan P (2018) Breast lesion shape and margin evaluation: BI-RADS based metrics understate radiologists’ actual levels of agreement. Comput Biol Med 96:294–298

    Article  Google Scholar 

  7. Pinker K, Moy L, Sutton EJ et al (2018) Diffusion-weighted imaging with apparent diffusion coefficient map** for breast cancer detection as a stand-alone parameter: comparison with dynamic contrast-enhanced and multiparametric magnetic resonance imaging. Invest Radiol 53:587–595

    Article  Google Scholar 

  8. Dietzel M, Baltzer PAT (2018) How to use the Kaiser score as a clinical decision rule for diagnosis in multiparametric breast MRI: a pictorial essay. Insights Imaging 9:325–335

    Article  Google Scholar 

  9. Baltzer PA, Dietzel M, Kaiser WA (2013) A simple and robust classification tree for differentiation between benign and malignant lesions in MR-mammography. Eur Radiol 23:2051–2060

    Article  Google Scholar 

  10. Baltzer P, Toth D Breast MRI lesion classification tree (Kaiser score). Available at: http://www.meduniwien.ac.at/kaiser-score/. Accessed 6 Sept 2020

  11. Milos RI, Pipan F, Kalovidouri A et al (2020) The Kaiser score reliably excludes malignancy in benign contrast-enhancing lesions classified as BI-RADS 4 on breast MRI high-risk screening exams. Eur Radiol 30:6052–6061

    Article  Google Scholar 

  12. Marino MA, Clauser P, Woitek R et al (2016) A simple scoring system for breast MRI interpretation: does it compensate for reader experience? Eur Radiol 26:2529–2537

    Article  Google Scholar 

  13. Wengert GJ, Pipan F, Almohanna J et al (2020) Impact of the Kaiser score on clinical decision-making in BI-RADS 4 mammographic calcifications examined with breast MRI. Eur Radiol 30:1451–1459

    Article  CAS  Google Scholar 

  14. Jajodia A, Sindhwani G, Pasricha S et al (2021) Application of the Kaiser score to increase diagnostic accuracy in equivocal lesions on diagnostic mammograms referred for MR mammography. Eur J Radiol 134:109413

    Article  Google Scholar 

  15. Le Bihan D (2003) Looking into the functional architecture of the brain with diffusion MRI. Nat Rev Neurosci 4:469–480

    Article  Google Scholar 

  16. Hagmann P, Jonasson L, Maeder P, Thiran JP, Wedeen VJ, Meuli R (2006) Understanding diffusion MR imaging techniques: from scalar diffusion-weighted imaging to diffusion tensor imaging and beyond. Radiographics 26(Suppl 1):S205–S223

    Article  Google Scholar 

  17. Bickel H, Pinker-Domenig K, Bogner W et al (2015) Quantitative apparent diffusion coefficient as a noninvasive imaging biomarker for the differentiation of invasive breast cancer and ductal carcinoma in situ. Invest Radiol 50:95–100

    Article  CAS  Google Scholar 

  18. Woodhams R, Matsunaga K, Iwabuchi K et al (2005) Diffusion-weighted imaging of malignant breast tumors: the usefulness of apparent diffusion coefficient (ADC) value and ADC map for the detection of malignant breast tumors and evaluation of cancer extension. J Comput Assist Tomogr 29:644–649

    Article  Google Scholar 

  19. Baltzer A, Dietzel M, Kaiser CG, Baltzer PA (2016) Combined reading of contrast enhanced and diffusion weighted magnetic resonance imaging by using a simple sum score. Eur Radiol 26:884–891

    Article  Google Scholar 

  20. Dietzel M, Krug B, Clauser P et al (2021) A multicentric comparison of apparent diffusion coefficient map** and the Kaiser score in the assessment of breast lesions. Invest Radiol 56:274–282

    Article  CAS  Google Scholar 

  21. Meng L, Zhao X, Lu L et al (2021) A comparative assessment of MR BI-RADS 4 breast lesions with Kaiser score and apparent diffusion coefficient value. Front Oncol 11:779642

    Article  Google Scholar 

  22. Baltzer P, Mann RM, Iima M et al (2020) Diffusion-weighted imaging of the breast-a consensus and mission statement from the EUSOBI International Breast Diffusion-Weighted Imaging working group. Eur Radiol 30:1436–1450

    Article  Google Scholar 

  23. Cicchetti DV (1994) Guidelines, criteria, and rules of thumb for evaluating normed and standardized assessment instruments in psychology. Psychol Assess 6:284–290

    Article  Google Scholar 

  24. Istomin A, Masarwah A, Vanninen R, Okuma H, Sudah M (2021) Diagnostic performance of the Kaiser score for characterizing lesions on breast MRI with comparison to a multiparametric classification system. Eur J Radiol 138:109659

    Article  Google Scholar 

  25. Baltzer PAT, Kaiser WA, Dietzel M (2015) Lesion type and reader experience affect the diagnostic accuracy of breast MRI: a multiple reader ROC study. Eur J Radiol 84:86–91

    Article  Google Scholar 

  26. Clauser P, Krug B, Bickel H et al (2021) Diffusion-weighted imaging allows for downgrading MR BI-RADS 4 lesions in contrast-enhanced MRI of the breast to avoid unnecessary biopsy. Clin Cancer Res 27:1941–1948

    Article  CAS  Google Scholar 

  27. Kul S, Metin Y, Kul M, Metin N, Eyuboglu I, Ozdemir O (2018) Assessment of breast mass morphology with diffusion-weighted MRI: beyond apparent diffusion coefficient. J Magn Reson Imaging 48:1668–1677

    Article  Google Scholar 

  28. Kawashima H, Miyati T, Ohno N et al (2018) Differentiation between phyllodes tumours and fibroadenomas using intravoxel incoherent motion magnetic resonance imaging: comparison with conventional diffusion-weighted imaging. Br J Radiol 91:20170687

    Article  Google Scholar 

  29. Pinker K, Bickel H, Helbich TH et al (2013) Combined contrast-enhanced magnetic resonance and diffusion-weighted imaging reading adapted to the “Breast Imaging Reporting and Data System” for multiparametric 3-T imaging of breast lesions. Eur Radiol 23:1791–1802

    Article  CAS  Google Scholar 

  30. Daimiel Naranjo I, Lo Gullo R, Saccarelli C et al (2021) Diagnostic value of diffusion-weighted imaging with synthetic b-values in breast tumors: comparison with dynamic contrast-enhanced and multiparametric MRI. Eur Radiol 31:356–367

    Article  Google Scholar 

  31. Ei Khouli RH, Jacobs MA, Mezban SD et al (2010) Diffusion-weighted imaging improves the diagnostic accuracy of conventional 3.0-T breast MR imaging. Radiology 256:64–73

    Article  Google Scholar 

  32. Baltzer PAT, Bickel H, Spick C et al (2018) Potential of noncontrast magnetic resonance imaging with diffusion-weighted imaging in characterization of breast lesions: intraindividual comparison with dynamic contrast-enhanced magnetic resonance imaging. Invest Radiol 53:229–235

    Article  Google Scholar 

  33. Zhang M, Horvat JV, Bernard-Davila B et al (2019) Multiparametric MRI model with dynamic contrast-enhanced and diffusion-weighted imaging enables breast cancer diagnosis with high accuracy. J Magn Reson Imaging 49:864–874

    Article  Google Scholar 

  34. Kim SY, Lee HS, Kim EK, Kim MJ, Moon HJ, Yoon JH (2016) Effect of background parenchymal enhancement on pre-operative breast magnetic resonance imaging: how it affects interpretation and the role of second-look ultrasound in patient management. Ultrasound Med Biol 42:2766–2774

    Article  Google Scholar 

  35. DeMartini WB, Liu F, Peacock S, Eby PR, Gutierrez RL, Lehman CD (2012) Background parenchymal enhancement on breast MRI: impact on diagnostic performance. AJR Am J Roentgenol 198:W373–W380

    Article  Google Scholar 

  36. Horvat JV, Durando M, Milans S et al (2018) Apparent diffusion coefficient map** using diffusion-weighted MRI: impact of background parenchymal enhancement, amount of fibroglandular tissue and menopausal status on breast cancer diagnosis. Eur Radiol 28:2516–2524

    Article  Google Scholar 

Download references

Funding

This work was supported by the Key Laboratory of Intelligent Medical Imaging of Wenzhou (No. 2021HZSY0057), the Key Laboratory of Alzheimer’s Disease of Zhejiang Province, Institute of Aging, Wenzhou Medical University, Wenzhou, Zhejiang, China, Wenzhou Science & Technology Bureau (No. Y20180185), the Medical Health Science and Technology Project of Zhejiang Province Health Commission (No. 2019KY102), the National Cancer Institute of the National Institutes of Health under award numbers P30 CA062203, R01 CA127927, and R21 CA208938, and the UC Irvine Comprehensive Cancer Center using UCI Anti-Cancer Challenge funds.

Author information

Author notes

  1. Zhong-Wei Chen and You-Fan Zhao contributed equally as the first authors.

Authors and Affiliations

  1. Department of Radiology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, People’s Republic of China

    Zhong-Wei Chen, You-Fan Zhao, Hui-Ru Liu, Jie-Jie Zhou, Hai-Wei Miao, Shu-**n Ye, Yun He, **n-Miao Liu & Mei-Hao Wang

  2. Department of Radiological Sciences, University of California, Irvine, CA, USA

    Min-Ying Su

  3. Department of Medical Imaging and Radiological Sciences, Kaohsiung Medical University, Kaohsiung, Taiwan

    Min-Ying Su

Authors
  1. Zhong-Wei Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. You-Fan Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hui-Ru Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jie-Jie Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hai-Wei Miao
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Shu-**n Ye
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Yun He
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. **n-Miao Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Min-Ying Su
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Mei-Hao Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Min-Ying Su or Mei-Hao Wang.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Min-Ying Su, PhD.

Conflict of interest

The 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 waived by the Institutional Review Board of the First Affiliated Hospital of Wenzhou Medical University.

Ethical approval

Institutional Review Board approval was obtained from Institutional Review Board of the First Affiliated Hospital of Wenzhou Medical University (approval number 2021-R007).

Methodology

• retrospective

• diagnostic study

• performed at one 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 21 kb)

ESM 2

(DOCX 23 kb)

ESM 3

(DOCX 23 kb)

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, ZW., Zhao, YF., Liu, HR. et al. Assessment of breast lesions by the Kaiser score for differential diagnosis on MRI: the added value of ADC and machine learning modeling. Eur Radiol 32, 6608–6618 (2022). https://doi.org/10.1007/s00330-022-08899-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-022-08899-w

Keywords

Search

Navigation