Automatic breast tissue segmentation in MRIs with morphology snake and deep denoiser training via extended Stein’s unbiased risk estimator

Abstract

Accurate segmentation of the breast tissue is a significant challenge in the analysis of breast MR images, especially analysis of breast images with low contrast. Most of the existing methods for breast segmentation are semi-automatic and limited in their ability to achieve accurate results. This is because of difficulties in removing landmarks from noisy magnetic resonance images (MRI). Especially, when tumour is imaged for scanning, how to isolate the tumour region from chest will directly affect the accuracy for tumour to be detected. Due to low intensity levels and the close connection between breast and chest portion in MRIs, this study proposes an innovative, fully automatic and fast segmentation approach which combines histogram with inverse Gaussian gradient for morphology snakes, along with extended Stein’s unbiased risk estimator (eSURE) applied for unsupervised learning of deep neural network Gaussian denoisers, aimed at accurate identification of landmarks such as chest and breast.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22

References

  1. 1.

    Fass L, et al. Imaging and cancer: a review. Mol Oncol. 2008;2(2):115–52.

    Article  Google Scholar 

  2. 2.

    Rivera-Franco MM, Leon-Rodriguez E, Delays in breast cancer detection and treatment in developing countries. Breast Cancer (Auckl). 2018; 12: 1178223417752677.

  3. 3.

    Wernli KJ, DeMartini WB, Ichikawa L, Lehman CD, Onega T, Kerlikowske K, Henderson LM, Geller BM, Hofmann M, Yankaskas BC. the breast cancer surveillance consortium, patterns of breast magnetic resonance imaging use in community practice. JAMA Intern Med. 2014;174(1):125–32.

    Article  Google Scholar 

  4. 4.

    Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJWL. Artificial intelligence in radiology. Nat Rev Cancer. 2018;18(8):500–10.

    Article  Google Scholar 

  5. 5.

    Nover AB, Jagtap S, Anjum W, Yegingil H, Shih WY, Shih W-H, Brooks AD, Modern breast cancer detection: a technological review. Int J Biomed Imaging. 2009; Volume 2009, Article ID 902326

  6. 6.

    Berry E, A practical approach to medical image processing, CRC Press, 2019

  7. 7.

    Yin XX, Hadjiloucas S, Chen JH, Zhang Y, Wu JL, Su MY. Tensor based multichannel reconstruction for breast tumours identification from DCE-MRIs. PLoS ONE. 2017;12(4):e0176133.

    Article  Google Scholar 

  8. 8.

    Yin XX, Hadjiloucas S, Zhang Y. Pattern classification of medical images: computer aided diagnosis. Cham: Springer; 2017.

    Book  Google Scholar 

  9. 9.

    Yin XX, Ng BWH, Yang Q, Pitman A, Ramamohanarao K, Abbott D. Anatomical landmark localization in breast dynamic contrast-enhanced MR imaging. Med Biol Eng Comput. 2012;50(1):91–101.

    Article  Google Scholar 

  10. 10.

    Nahid A-A, Kong Y, Involvement of machine learning for breast cancer image classification: a survey, computational and mathematical methods in medicine, Volume 2017, Article ID 3781951, 2017

  11. 11.

    Zilong Hu, Tang J, Wang Z, Zhang K, Zhang L, Sun Q. Deep learning for image-based cancer detection and diagnosis − A survey. Pattern Recogn. 2018;83:134–49.

    Article  Google Scholar 

  12. 12.

    Razzak MI, Naz S, Zaib A, Deep learning for medical image processing: overview, challenges and the future. In: Dey N, Ashour A, Borra S. (eds) Classification in BioApps. Lecture Notes in Computational Vision and Biomechanics, vol 26. Springer, Cham 2018

  13. 13.

    Mann RM, Cho N, Moy L. Breast MRI: state of the art. Radiology. 2019;292(3):520–36.

    Article  Google Scholar 

  14. 14.

    Yin XX, Zhang Y, Cao J, Wu JL, Hadjiloucas S. Exploring the complementarity of THz pulse imaging and DCE-MRIs: toward a unified multi-channel classification and a deep learning framework. Comput Methods Programs Biomed. 2016;137:87–114.

    Article  Google Scholar 

  15. 15.

    Li X, Jiang D, Shi Y, Li W, Segmentation of MR image using local and global region based geodesic model. BioMedical Engineering OnLine 14, Article number:8 2015

  16. 16.

    Guo M, Wang Z, Ma Y, Xie W. Review of parametric active contour models in image processing. J Converg Inform Technol (JCIT). 2013;8(11):248–58.

    Article  Google Scholar 

  17. 17.

    Kass M, Witkin A. D. Terzopoulos, Snake: active contour models. Int J Comput Vis. 1987;1:321–31.

    Article  Google Scholar 

  18. 18.

    Cohen LD, Cohen I. Finite-element methods for active contour models and balloons for 2-D and 3-D images. IEEE Trans Pattern Anal Mach Intell. 1993;15(11):1131–47.

    Article  Google Scholar 

  19. 19.

    Xu Y. Snakes shapes and gradient vector flow. IEEE Trans Image Process. 1998;7(3):359–69.

    MathSciNet  Article  Google Scholar 

  20. 20.

    Li B, Acton ST. Active contour external force using vector field convolution for image segmentation. IEEE Trans Image Process. 2007;16(8):2096–106.

    MathSciNet  Article  Google Scholar 

  21. 21.

    Osher S, Sethian JA. Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations. J Comput Phys. 1988;79(1):12–49.

    MathSciNet  Article  Google Scholar 

  22. 22.

    Whitaker RT. A level-set approach to 3D reconstruction from range data. Int J Comput Vis. 1998;29(3):203–31.

    Article  Google Scholar 

  23. 23.

    Chan TF, Vese LA. Active contours without edges. IEEE Trans Image Process. 2001;10(2):266–77.

    Article  Google Scholar 

  24. 24.

    Dolz J, Kirişli HA, Fechter T, Karnitzki S, Oehlke O, Nestle U et al. Interactive contour delineation of organs at risk in radiotherapy: clinical evaluation on NSCLC patients, Med Phys, 43(5), Art Number 2569, 2016.

  25. 25.

    Liu S, Peng Y. A local region-based Chan-Vese model for image segmentation. Pattern Recogn. 2012;45(7):2769–79.

    Article  Google Scholar 

  26. 26.

    Xu J, Gong L, Wang G, et al. Convolutional neural network initialized active contour model with adaptive ellipse fitting for nuclear segmentation on breast histopathological images. J Med Imaging (Bellingham, Wash). 2019;6(1):017501.

    Google Scholar 

  27. 27.

    Guo X, Schwartz LH, Zhao B. Automatic liver segmentation by integrating fully convolutional networks into active contour models. Med Phys. 2019;46(10):4455–69.

    Article  Google Scholar 

  28. 28.

    Chen X, Williams BM, Vallabhaneni SR, Czanner G, Williams R, Zheng Y, Learning active contour models for medical image segmentation. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019, pp. 11624–11632.

  29. 29.

    Shannon C, Weaver W. The mathematical theory of communication. Champaign: University of Illinois Press; 1998.

    MATH  Google Scholar 

  30. 30.

    Vaishali S, Rao KK, Rao GVS, A review on noise reduction methods for brain MRI images. 2015 International Conference on Signal Processing and Communication Engineering Systems, Guntur, 2015, pp. 363–365.

  31. 31.

    Starck JL, Candes EJ, Donoho DL. The curvelet transform for image denoising. IEEE Trans Image Process. 2002;11(6):670–84.

    MathSciNet  Article  Google Scholar 

  32. 32.

    Singh S, Wadhwani S. Genetic algorithm based medical image denoising through sub band adaptive thresholding. Int J Sci Engineer Technol Res. 2015;4(5):1481–5.

    Google Scholar 

  33. 33.

    Sharif M, Jaffara MA, Mahmood MT. Optimal composite morphological supervised filter for image denoising using genetic programming: application to magnetic resonance images. Eng Appl Artif Intell. 2014;31:78–89.

    Article  Google Scholar 

  34. 34.

    Aharon M, Elad M, Bruckstein AM. K-SVD: an algorithm for designing over complete dictionaries for sparse representation. IEEE Trans Signal Process. 2006;54:4311–22.

    Article  Google Scholar 

  35. 35.

    Binh NT, Khare A. Multilevel threshold based image denoising in curvelet domain. J Comput Sci Technol. 2010;25(3):632–40.

    Article  Google Scholar 

  36. 36.

    Pereira DC, Ramos RP, Nascimento MZ. Segmentation and detection of breast cancer in mammograms combining wavelet analysis and genetic algorithm. Comput Methods Programs Biomed. 2014;114:88–101.

    Article  Google Scholar 

  37. 37.

    Bermudez C, Plassard AJ, Davis LT, Newton AT, Resnick SM, Landman BA. Learning implicit brain MRI manifolds with deep learning. Medical Imaging 2018: Image Processing, 2018; 105741L.

  38. 38.

    Jiang D, Dou W, Vosters L, Xu X, Sun Y, Tan T. Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network. Jpn J Radiol. 2018;36:566–74.

    Article  Google Scholar 

  39. 39.

    Rao GS, Srinivas B. De-noising of MRI Brain Tumor image using Deep Convolutional Neural Network, 2019

  40. 40.

    Balafar MA. New spatial based MRI image de-noising algorithm. Artif Intell Rev. 2013;39(3):225–35.

    Article  Google Scholar 

  41. 41.

    Pantelic RS, et al. The discriminative bilateral filter: an enhanced denoising filter for electron microscopy data. J Struct Biol. 2006;155(3):395–408.

    Article  Google Scholar 

  42. 42.

    Sawant AR, et al. Adaptive median filter algorithm to remove impulse noise in x-ray and CT images and speckle in ultrasound images. Int Soc Opt Photon Med Imaging. 1999;99(1999):1263–74.

    Google Scholar 

  43. 43.

    Zhussip M, Soltanayev S, Chun S. Extending Stein’s unbiased risk estimator to train deep denoisers with correlated pairs of noisy images. Adv Neural Inform Process Syst. 2019;32:1465–75.

    Google Scholar 

  44. 44.

    Li M, Zhang L, Xu X-J, Shi Z, Zhao X-M. CT and MRI features of tumors and tumor-like lesions in the abdominal wall. Quant Imaging Med Surgery. 2019;9(11):41–58.

    Article  Google Scholar 

  45. 45.

    Saini AK, Bhadauria HS, Annapurna S, A survey of noise removal methodologies for lung cancer diagnosis. IEEE Second International Conference on Computational Intelligence & Communication Technology (CICT). 2016; 673–678.

  46. 46.

    Caselles V, Kimmel R, Sapiro G. Geodesic active contours. Int J Comput Vis. 1997;22:61–79.

    Article  Google Scholar 

  47. 47.

    A. Medeiros, M. Guimarães, S. Peixoto, L. Santos, C. Barros, E. Rebouças, V.H.C. Albuquerque, & P.P. Filho. A new fast morphological geodesic active contour method for lung CT image segmentation. measurement. Doi: https://doi.org/10.1016/j.measurement.2019.05.078.

  48. 48.

    Osher S, Sethian JA. Fronts propagating with curvature-dependent speed: algorithms based on hamilton-jacobi formulations. J Comput Phys. 1988;79:12–49.

    MathSciNet  Article  Google Scholar 

  49. 49.

    Alvarez L, Baumela L, Henriquez P, Marquez-Neila P, “Morphological snakes,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010, pp. 2197–2202.

  50. 50.

    Marquez-Neila P, Baumela L, Alvarez L. A morphological approach to curvature-based evolution of curves and surfaces. IEEE Trans Pattern Anal Mach Intell. 2014;36(1):2–17.

    Article  Google Scholar 

  51. 51.

    Gallego-Ortiz C, Martel AL. Automatic atlas-based segmentation of the breast in MRI for 3D breast volume computation. Med Phys. 2012;39:5835–48.

    Article  Google Scholar 

  52. 52.

    Fooladivanda A, Shokouhi SB, Ahmadinejad N. Localized-atlas-based segmentation of breast MRI in a decision making framework. Australas Phys Eng Sci. 2017;40(1):69–84.

    Article  Google Scholar 

  53. 53.

    Doran SJ, Hipwell JH, Denholm R, Eiben B, Busana M, Hawkes DJ, Leach MOD, Silva IDS. Breast MRI segmentation for density estimation: do difffferent methods give the same results and how much do difffferences matter? Med Phys. 2017;44(9):4573–92.

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding authors

Correspondence to Xiao-Xia Yin or Yanchun Zhang.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Yin, XX., Jian, Y., Zhang, Y. et al. Automatic breast tissue segmentation in MRIs with morphology snake and deep denoiser training via extended Stein’s unbiased risk estimator. Health Inf Sci Syst 9, 16 (2021). https://doi.org/10.1007/s13755-021-00143-x

Download citation

Keywords

  • Image segmentation
  • MRI
  • Inverse Gaussian gradient
  • Morphology snakes
  • Breast cancer
  • Adaptive histogram equalization
  • Extended Stein’s unbiased risk estimator