Skip to main content

Advertisement

SpringerLink
Log in

A deep learning framework for efficient analysis of breast volume and fibroglandular tissue using MR data with strong artifacts

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

Abstract

Purpose

The main purpose of this work is to develop, apply, and evaluate an efficient approach for breast density estimation in magnetic resonance imaging data, which contain strong artifacts including intensity inhomogeneities.

Methods

We present a pipeline for breast density estimation, which consists of intensity inhomogeneity correction, breast volume segmentation, nipple extraction, and fibroglandular tissue segmentation. For the segmentation steps, a well-known deep learning architecture is employed.

Results

The average Dice coefficient for the breast parenchyma is \(92.5\%\pm 0.011\), which outperforms the classical state-of-the-art approach by a margin of \(9\%\).

Conclusion

The proposed solution is accurate and highly efficient and has potential to be applied for big epidemiological data with thousands of participants.

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

References

  1. Altman DG, Bland JM (1994) Diagnostic tests. 1: sensitivity and specificity. Br Med J: BMJ 308(6943):1552

    Article  CAS  Google Scholar 

  2. Bland JM, Altman D (1986) Statistical methods for assessing agreement between two methods of clinical measurement. Lancet 327(8476):307–310

    Article  Google Scholar 

  3. Dalmış MU, Litjens G, Holland K, Setio A, Mann R, Karssemeijer N, Gubern-Mérida A (2017) Using deep learning to segment breast and fibroglandular tissue in mri volumes. Med Phys 44(2):533–546

    Article  Google Scholar 

  4. Dice LR (1945) Measures of the amount of ecologic association between species. Ecology 26(3):297–302

    Article  Google Scholar 

  5. Eberl MM, Fox CH, Edge SB, Carter CA, Mahoney MC (2006) Bi-rads classification for management of abnormal mammograms. J Am Board Fam Med 19(2):161–164

    Article  Google Scholar 

  6. Gonzalez RC, Woods RE (2002) Digital image processing. Prentice Hall, Upper Saddle River

    Google Scholar 

  7. 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(5):1153–1159

    Article  Google Scholar 

  8. Gubern-Merida 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 Health Inform 19(1):349–357

    Article  Google Scholar 

  9. Hou Z (2006) A review on MR image intensity inhomogeneity correction. Int J Biomed Imaging 2006:1e11

    Article  Google Scholar 

  10. Ivanovska T, Gloger LWO, Hahn HK, Völzke H, Hegenscheid K (2015) Sliding level set-based boundary: fully automated dense breast segmentation in native MR mammograms. In: Proceedings of MICCAI-BIA p 57

  11. Ivanovska T, Laqua R, Wang L, Liebscher V, Völzke H, Hegenscheid K (2014) A level set based framework for quantitative evaluation of breast tissue density from mri data. PLoS ONE 9(11):1–19

    Article  Google Scholar 

  12. Ivanovska T, Laqua R, Wang L, Schenk A, Yoon JH, Hegenscheid K, Völzke H, Liebscher V (2016) An efficient level set method for simultaneous intensity inhomogeneity correction and segmentation of mr images. Comput Med Imaging Graph 48:9–20

    Article  Google Scholar 

  13. Jentschke TG, Hegenscheid K, Völzke H, Wörgötter F, Ivanovska T (2018) Segmentierung von brustvolumina in magnetresonanztomographiedaten unter der verwendung von deep learning. In: Proceedings of workshop Bildverarbeitung in der Medizin (BVM)

  14. John U, Hensel E, Lüdemann J, Piek M, Sauer S, Adam C, Born G, Alte D, Greiser E, Haertel U, Hense HW, Haerting J, Willich S, Kessler C (2001) Study of health in pomerania (ship): a health examination survey in an east german region: objectives and design. Sozial-und Präventivmedizin 46(3):186–194

    Article  CAS  Google Scholar 

  15. McCormack VA, dos Santos Silva I (2006) Breast density and parenchymal patterns as markers of breast cancer risk: a meta-analysis. Cancer Epidemiol Prev Biomark 15(6):1159–1169

    Article  Google Scholar 

  16. Milletari F, Navab N, Ahmadi SA (2016) V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 fourth international conference on 3D vision (3DV). IEEE, pp 565–571

  17. Razavi M, Wang L, Gubern-Mérida A, Ivanovska T, Laue H, Karssemeijer N, Hahn HK (2015) Towards accurate segmentation of fibroglandular tissue in breast MRI using fuzzy c-means and skin-folds removal. In: International conference on image analysis and processing. Springer, pp 528–536

  18. Rosset A, Spadola L, Ratib O (2004) Osirix: an open-source software for navigating in multidimensional dicom images. J Digit Imaging 17(3):205–216

    Article  Google Scholar 

  19. Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117

    Article  Google Scholar 

  20. Smith TB, Nayak KS (2010) Mri artifacts and correction strategies. Imaging Med 2(4):445–457

    Article  Google Scholar 

  21. Tice JA, Cummings SR, Ziv E, Kerlikowske K (2005) Mammographic breast density and the gail model for breast cancer risk prediction in a screening population. Breast Cancer Res Treat 94(2):115–122

    Article  Google Scholar 

  22. Tustison NJ, Avants BB, Cook PA, Zheng Y, Egan A, Yushkevich PA, Gee JC (2010) N4itk: improved n3 bias correction. IEEE Trans Med Imaging 29(6):1310–1320

    Article  Google Scholar 

  23. Vachon CM, Kuni CC, Anderson K, Anderson VE, Sellers TA (2000) Association of mammographically defined percent breast density with epidemiologic risk factors for breast cancer (united states). Cancer Causes Control 11(7):653–662

    Article  CAS  Google Scholar 

  24. Vincent R (2006) Brainweb: simulated brain database. Available online at http://www.bic.mni.mcgill.ca/brainweb/

  25. Vovk U, Pernus F, Likar B (2007) A review of methods for correction of intensity inhomogeneity in mri. IEEE Trans Med Imaging 26(3):405–421

    Article  Google Scholar 

  26. Zhuo J, Gullapalli RP (2006) Mr artifacts, safety, and quality control. Radiographics 26(1):275–297

    Article  Google Scholar 

Download references

Acknowledgements

This study is developed within the project, which is partially supported by the German Research Foundation, Project No. IV 161/4-1, DA 1810/2-1.

Author information

Author notes

  1. Tatyana Ivanovska and Thomas G. Jentschke have contributed equally to this work.

Authors and Affiliations

  1. Department of Computational Neuroscience, Georg-August-University, Friedrich-Hund Platz, 1, 37077, Göttingen, Germany

    Tatyana Ivanovska, Thomas G. Jentschke & Florentin Wörgötter

  2. Department of Prosthodontics, Gerodontology and Biomaterials, University Medicine Greifswald, Fleischmannstr. 42-44, 17475, Greifswald, Germany

    Amro Daboul

  3. Unfallkrankenhaus Berlin, Warener Str. 7, 12683, Berlin, Germany

    Katrin Hegenscheid

  4. Institute for Community Medicine, University Medicine Greifswald, Walther-Rathenau-Str. 48, 17489, Greifswald, Germany

    Henry Völzke

Authors
  1. Tatyana Ivanovska
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Thomas G. Jentschke
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Amro Daboul
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Katrin Hegenscheid
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Henry Völzke
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Florentin Wörgötter
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tatyana Ivanovska.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Informed consent

Informed consent was obtained from all individuals included in the study. This study was a subproject of the population-based Study of Health in Pomerania (SHIP). SHIP was conducted in the Northeast German federal state of Mecklenburg-Western Pomerania. Written informed consent was obtained separately for study inclusion and MR imaging.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Declaration of Helsinki and its later amendments or comparable ethical standards. The SHIP was conducted as approved by the local Institutional Review Board at Greifswald University Hospital.

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

Ivanovska, T., Jentschke, T.G., Daboul, A. et al. A deep learning framework for efficient analysis of breast volume and fibroglandular tissue using MR data with strong artifacts. Int J CARS 14, 1627–1633 (2019). https://doi.org/10.1007/s11548-019-01928-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-019-01928-y

Keywords

Search

Navigation