Skip to main content
SpringerLink
Log in

CAD and Machine Learning for Breast MRI

  • Chapter
  • First Online:
Breast MRI for High-risk Screening

Abstract

A typical breast MRI exam results in thousands of image slices from multiple sequences, collected over multiple time points and with different tissue contrasts. Computerized support systems help the radiologist to navigate through these images by detecting and characterizing parenchymal lesions. This chapter divides computerized systems for breast MRI into three main categories: computer-aided evaluation (CAE) systems that provide improved visualization of the image data and support the radiologists workflow; computer-aided diagnosis systems (CADx) that provide an estimate of the probability of a specific lesion being a cancer; and computer-aided detection and diagnosis (CADD) systems that first identify possible lesions and then classify them in terms of probability of being malignant or benign. Various steps of these automated systems are described such as lesion segmentation, feature extraction (including kinetic, morphological, and texture features), and lesion classification (by means of feature selection, training, and evaluation of classifiers). Moreover, systems for fully automated lesion detection as well as systems for motion correction (image registration) and breast segmentation are described. Finally, challenges that have hindered the widespread adoption of CAD systems for routine breast MRI clinical practice and opportunities for future research aimed at their improvement are illustrated.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 79.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 99.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 139.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Abbreviations

3D:

Three-dimensional

3TP :

Three-time-point

ANN:

Artificial neural network

ASM :

Angular second moment

AUC :

Area under the curve

BI-RADS :

Breast Imaging Reporting and Data System

CAD:

Computer-aided detection/diagnosis

CADD :

Computer-aided detection and diagnosis

CADe :

Computer-aided detection

CADx :

Computer-aided diagnosis

CAE :

Computer-aided evaluation

CNN:

Convolutional neural networks

DCE :

Dynamic contrast-enhanced

LDA:

Linear discriminant analysis

LOO :

Leave-one-out

MRI :

Magnetic resonance imaging

PK :

Pharmacokinetic

ROC :

Receiver operating characteristic

ROI :

Region of interest

SER:

Signal enhancement ratio

SVM:

Support vector machines

References

  1. Morris EA, Comstock CE, Lee CH (2013) ACR BI-RADS® Magnetic Resonance Imaging. In: American College of Radiology. Breast Imaging Reporting and Data System® (BI-RADS®). 5th edition. American College of Radiology, Reston, VA, USA

    Google Scholar 

  2. Tofts PS, Brix G, Buckley DL et al (1999) Estimating kinetic parameters from dynamic contrast-enhanced T(1)-weighted MRI of a diffusable tracer: standardized quantities and symbols. J Magn Reson Imaging 10:223–232

    Article  PubMed  CAS  Google Scholar 

  3. Furman-Haran E, Degani H (2002) Parametric analysis of breast MRI. J Comput Assist Tomogr 26:376–386

    Article  PubMed  Google Scholar 

  4. Lehman CD, Peacock S, DeMartini WB, Chen X (2006) A new automated software system to evaluate breast MR examinations: improved specificity without decreased sensitivity. AJR Am J Roentgenol 187:51–56

    Article  PubMed  Google Scholar 

  5. Arazi-Kleinman T, Causer PA, Jong RA, Hill K, Warner E (2009) Can breast MRI computer-aided detection (CAD) improve radiologist accuracy for lesions detected at MRI screening and recommended for biopsy in a high-risk population? Clin Radiol 64:1166–1174

    Article  PubMed  CAS  Google Scholar 

  6. Baltzer PA, Freiberg C, Beger S et al (2009) Clinical MR-mammography: are computer-assisted methods superior to visual or manual measurements for curve type analysis? A systematic approach. Acad Radiol 16:1070–1076

    Article  PubMed  Google Scholar 

  7. Kelcz F, Furman-Haran E, Grobgeld D, Degani H (2002) Clinical testing of high-spatial-resolution parametric contrast-enhanced MR imaging of the breast. AJR Am J Roentgenol 179:1485–1492

    Article  PubMed  Google Scholar 

  8. Dorrius MD, Jansen-van der Weide MC, van Ooijen PM, Pijnappel RM, Oudkerk M (2011) Computer-aided detection in breast MRI: a systematic review and meta-analysis. Eur Radiol 21:1600–1608

    Article  PubMed  PubMed Central  Google Scholar 

  9. Liney GP, Sreenivas M, Gibbs P, Garcia-Alvarez R, Turnbull LW (2006) Breast lesion analysis of shape technique: semiautomated vs. manual morphological description. J Magn Reson Imaging 23:493–498

    Article  PubMed  Google Scholar 

  10. Chen W, Giger ML, Bick U (2006) A fuzzy c-means (FCM)-based approach for computerized segmentation of breast lesions in dynamic contrast-enhanced MR images. Acad Radiol 13:63–72

    Article  PubMed  Google Scholar 

  11. Cui Y, Tan Y, Zhao B et al (2009) Malignant lesion segmentation in contrast-enhanced breast MR images based on the marker-controlled watershed. Med Phys 36:4359–4369

    Article  PubMed  PubMed Central  Google Scholar 

  12. Levman J, Warner E, Causer P, Martel A (2014) Semi-automatic region-of-interest segmentation based computer-aided diagnosis of mass lesions from dynamic contrast-enhanced magnetic resonance imaging based breast cancer screening. J Digit Imaging 27:670–678

    Article  PubMed  PubMed Central  Google Scholar 

  13. Zheng Y, Englander S, Baloch S et al (2009) STEP: spatiotemporal enhancement pattern for MR-based breast tumor diagnosis. Med Phys 36:3192–3204

    Article  PubMed  PubMed Central  Google Scholar 

  14. Baltzer PAT, 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  PubMed  Google Scholar 

  15. Chen W, Giger ML, Lan L, Bick U (2004) Computerized interpretation of breast MRI: Investigation of enhancement-variance dynamics. Med Phys 31:1076–1082

    Article  PubMed  Google Scholar 

  16. Lucht RE, Knopp MV, Brix G (2001) Classification of signal-time curves from dynamic MR mammography by neural networks. Magn Reson Imaging 19:51–57

    Article  PubMed  CAS  Google Scholar 

  17. Levman J, Leung T, Causer P, Plewes D, Martel AL (2008) Classification of dynamic contrast-enhanced magnetic resonance breast lesions by support vector machines. IEEE Trans Med Imaging 27:688–696

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  18. Jansen SA, Fan X, Karczmar GS, Abe H, Schmidt RA, Newstead GM (2008) Differentiation between benign and malignant breast lesions detected by bilateral dynamic contrast-enhanced MRI: a sensitivity and specificity study. Magn Reson Med 59:747–754

    Article  PubMed  PubMed Central  Google Scholar 

  19. Gallego-Ortiz C, Martel AL (2016) Improving the accuracy of computer-aided diagnosis for breast MR imaging by differentiating between mass and nonmass lesions. Radiology 278:679–688

    Article  PubMed  Google Scholar 

  20. Stoutjesdijk MJ, Veltman J, Huisman H et al (2007) Automated analysis of contrast enhancement in breast MRI lesions using mean shift clustering for ROI selection. J Magn Reson Imaging 26:606–614

    PubMed  Google Scholar 

  21. Schlossbauer T, Leinsinger G, Wismuller A et al (2008) Classification of small contrast enhancing breast lesions in dynamic magnetic resonance imaging using a combination of morphological criteria and dynamic analysis based on unsupervised vector-quantization. Invest Radiol 43:56–64

    PubMed  PubMed Central  Google Scholar 

  22. Chen W, Giger ML, Bick U, Newstead GM (2006) Automatic identification and classification of characteristic kinetic curves of breast lesions on DCE-MRI. Med Phys 33:2878–2887

    PubMed  Google Scholar 

  23. Agliozzo S, De Luca M, Bracco C et al (2012) Computer-aided diagnosis for dynamic contrast-enhanced breast MRI of mass-like lesions using a multiparametric model combining a selection of morphological, kinetic, and spatiotemporal features. Med Phys 39:1704–1715

    PubMed  CAS  Google Scholar 

  24. Gilhuijs KG, Giger ML, Bick U (1998) Computerized analysis of breast lesions in three dimensions using dynamic magnetic-resonance imaging. Med Phys 25:1647–1654

    PubMed  CAS  Google Scholar 

  25. Levman JE, Martel AL (2011) A margin sharpness measurement for the diagnosis of breast cancer from magnetic resonance imaging examinations. Acad Radiol 18:1577–1581

    PubMed  Google Scholar 

  26. Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 6:610–621

    Google Scholar 

  27. Gibbs P, Turnbull LW (2003) Textural analysis of contrast-enhanced MR images of the breast. Magn Reson Med 50:92–98

    PubMed  Google Scholar 

  28. Chen W, Giger ML, Li H, Bick U, Newstead GM (2007) Volumetric texture analysis of breast lesions on contrast-enhanced magnetic resonance images. Magn Reson Med 58:562–571

    PubMed  Google Scholar 

  29. Ertaş G, Gülçür HO, Tunaci M (2007) Improved lesion detection in MR mammography: three-dimensional segmentation, moving voxel sampling, and normalized maximum intensity-time ratio entropy. Acad Radiol 14:151–161

    PubMed  Google Scholar 

  30. Breiman L (2001) Random forests. Mach Learn 45:5–32

    Google Scholar 

  31. Gubern-Mérida A, Martí R, Melendez J et al (2015) Automated localization of breast cancer in DCE-MRI. Med Image Anal 20:265–274

    Article  PubMed  Google Scholar 

  32. Gallego-Ortiz C, Martel AL (2016) Interpreting extracted rules from ensemble of trees: application to computer-aided diagnosis of breast MRI. ICML workshop on human interpretability in machine learning (WHI 2016) arXiv:1606.08288. https://arxiv.org/abs/1606.08288. Accessed 30 Jun 2020

  33. Chen W, Giger ML, Newstead GM, Bick U, Jansen SA, Li H, Lan L (2010) Computerized assessment of breast lesion malignancy using DCE-MRI robustness study on two independent clinical datasets from two manufacturers. Acad Radiol 17:822–829

    Article  PubMed  PubMed Central  Google Scholar 

  34. Nie K, Chen J-H, Yu HJ, Chu Y, Nalcioglu O, Su M-Y (2008) Quantitative analysis of lesion morphology and texture features for diagnostic prediction in breast MRI. Acad Radiol 15:1513–1525

    Article  PubMed  PubMed Central  Google Scholar 

  35. Rakoczy M, McGaughey D, Korenberg MJ, Levman J, Martel AL (2013) Feature selection in computer-aided breast cancer diagnosis via dynamic contrast-enhanced magnetic resonance images. J Digit Imaging 26:198–208

    Article  PubMed  Google Scholar 

  36. Mayer D, Vomweg TW, Faber H et al (2006) Fully automatic breast cancer diagnosis in contrast enhanced MRI. Int J CARS 1(Suppl 1):325–343

    Google Scholar 

  37. Renz DM, Böttcher J, Diekmann F et al (2012) Detection and classification of contrast-enhancing masses by a fully automatic computer-assisted diagnosis system for breast MRI. J Magn Reson Imaging 35:1077–1088

    Article  PubMed  Google Scholar 

  38. Vignati A, Giannini V, De Luca M et al (2011) Performance of a fully automatic lesion detection system for breast DCE-MRI. J Magn Reson Imaging 34:1341–1351

    Article  PubMed  Google Scholar 

  39. Huang YH, Chang YC, Huang CS, Chen JH, Chang RF (2014) Computerized breast mass detection using multi-scale Hessian-based analysis for dynamic contrastenhanced MRI. J Digit Imaging 27:649–660

    Article  PubMed  PubMed Central  Google Scholar 

  40. Wu H, Gallego-Ortiz C, Martel A (2015) Deep artificial neural network approach to automated lesion segmentation in breast DCE-MRI. MICCAI-BIA 2015, Proceedings of the 3rd MICCAI workshop on breast image analysis, pp 73–80

    Google Scholar 

  41. Le QV (2013) Building high-level features using large scale unsupervised learning. 2013 IEEE international conference on acoustics, speech and signal processing: 8595–8598

    Google Scholar 

  42. Wu H (2016) Automatic computer aided diagnosis of breast cancer in dynamic contrast enhanced magnetic resonance images. Master’s thesis, University of Toronto. https://tspace.library.utoronto.ca/handle/1807/76158. Accessed 30 Jun 2020

  43. Herrmann KH, Wurdinger S, Fischer DR et al (2007) Application and assessment of a robust elastic motion correction algorithm to dynamic MRI. Eur Radiol 17:259–264

    Article  PubMed  Google Scholar 

  44. Martel AL, Froh MS, Brock KK, Plewes DB, Barber DC (2007) Evaluating an optical-flow-based registration algorithm for contrast-enhanced magnetic resonance imaging of the breast. Phys Med Biol 52:3803–3816

    Article  PubMed  CAS  Google Scholar 

  45. Rueckert D, Sonoda LI, Hayes C, Hill DL, Leach MO, Hawkes DJ (1999) Nonrigid registration using free-form deformations: application to breast MR images. IEEE Trans Med Imaging 18:712–721

    Article  PubMed  CAS  Google Scholar 

  46. Rohlfing T, Maurer CR Jr, Bluemke DA, Jacobs MA (2003) Volume-preserving nonrigid registration of MR breast images using free-form deformation with an incompressibility constraint. IEEE Trans Med Imaging 22:730–741

    Article  PubMed  Google Scholar 

  47. Ebrahimi M, Martel AL (2009) A general PDE-framework for registration of contrast enhanced images. Med Image Comput Assist Interv 12:811–819

    Google Scholar 

  48. Schnabel JA, Tanner C, Castellano-Smith AD et al (2003) Validation of nonrigid image registration using finite-element methods: application to breast MR images. IEEE Trans Med Imaging 22:238–247

    Article  PubMed  Google Scholar 

  49. Mehrabian H, Richmond L, Lu Y, Martel AL (2018) Deformable registration for longitudinal breast MRI screening. J Digit Imaging 31(5):718–726

    Google Scholar 

  50. Nie K, Chen JH, Chan S et al (2008) Development of a quantitative method for analysis of breast density based on three-dimensional breast MRI. Med Phys 35:5253–5262

    Article  PubMed  PubMed Central  Google Scholar 

  51. Martel AL, Gallego-Ortiz C, Lu Y (2016) Breast segmentation in MRI using Poisson surface reconstruction initialized with random forest edge detection. Proc. SPIE 9784, Medical Imaging 2016: Image Processing, 97841B. Accessed 27 August 2017

    Google Scholar 

  52. Ribes S, Didierlaurent D, Decoster N et al (2014) Automatic segmentation of breast MR images through a Markov random field statistical model. IEEE Trans Med Imaging 33:1986–1996

    PubMed  CAS  Google Scholar 

  53. Dalmış MU, Litjens G, Holland K et al (2017) Using deep learning to segment breast and fibroglandular tissue in MRI volumes. Med Phys 44:533–546

    PubMed  Google Scholar 

  54. Gubern-Mérida A, Kallenberg M, Mann RM, Marti R, Karssemeijer N (2015) Breast segmentation and density estimation in breast MRI: a fully automatic framework. IEEE J Biomed Heal Informatics 19:349–357

    Google Scholar 

  55. Fashandi H, Kuling G, Lu Y, Wu H, Martel AL (2019) An investigation of the effect of fat suppression and dimensionality on the accuracy of breast MRI segmentation using U-nets. Med Phys 46(3):1230–1244

    Google Scholar 

  56. Meinel LA, Stolpen AH, Berbaum KS, Fajardo LL, Reinhardt JM (2007) Breast MRI lesion classification: improved performance of human readers with a backpropagation neural network computer-aided diagnosis (CAD) system. J Magn Reson Imaging 25:89–95

    Article  PubMed  Google Scholar 

  57. Bhooshan N, Giger M, Lan L et al (2011) Combined use of T2-weighted MRI and T1-weighted dynamic contrast-enhanced MRI in the automated analysis of breast lesions. Magn Reson Med 66:555–564

    Article  PubMed  PubMed Central  Google Scholar 

  58. Ballesio L, Savelli S, Angeletti M et al (2009) Breast MRI: Are T2 IR sequences useful in the evaluation of breast lesions? Eur J Radiol 71:96–101

    Article  PubMed  Google Scholar 

  59. Cai H, Liu L, Peng Y, Wu Y, Li L (2014) Diagnostic assessment by dynamic contrast-enhanced and diffusion-weighted magnetic resonance in differentiation of breast lesions under different imaging protocols. BMC Cancer 14:366

    Article  PubMed  PubMed Central  Google Scholar 

  60. Platel B, Mus R, Welte T, Karssemeijer N, Mann R (2014) Automated characterization of breast lesions imaged with an ultrafast DCE-MR protocol. IEEE Trans Med Imaging 33:225–232

    Article  PubMed  Google Scholar 

  61. Abe H, Mori N, Tsuchiya K et al (2016) Kinetic analysis of benign and malignant breast lesions with ultrafast dynamic contrast-enhanced MRI: comparison with standard kinetic assessment. AJR Am J Roentgenol 207:1159–1166

    Article  PubMed  PubMed Central  Google Scholar 

  62. Greenspan H, van Ginneken B, Summers RM (2016) Guest Editorial Deep Learning in Medical Imaging: Overview and future promise of an exciting new technique. IEEE Trans Med Imaging 35:1153–1159

    Google Scholar 

  63. Kooi T, Litjens G, van Ginneken B et al (2017) Large scale deep learning for computer aided detection of mammographic lesions. Med Image Anal 35:303–312

    PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Medical Biophysics, University of Toronto, Physical Sciences, Sunnybrook Research Institute, Toronto, ON, Canada

    Anne L. Martel

Authors
  1. Anne L. Martel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Anne L. Martel .

Editor information

Editors and Affiliations

  1. Department of Biomedical Sciences for Health, Università degli Studi di Milano, Milan, Italy

    Francesco Sardanelli

  2. Department of Cell Biology and Neurosciences Molecular and Cellular Imaging Unit, Istituto Superiore di Sanità (ISS), Rome, Italy

    Franca Podo

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Martel, A.L. (2020). CAD and Machine Learning for Breast MRI. In: Sardanelli, F., Podo, F. (eds) Breast MRI for High-risk Screening. Springer, Cham. https://doi.org/10.1007/978-3-030-41207-4_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-41207-4_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-41206-7

  • Online ISBN: 978-3-030-41207-4

  • eBook Packages: MedicineMedicine (R0)

Publish with us

Policies and ethics

Search

Navigation