Advertisement

Deep Learning-Based Denoising of Mammographic Images Using Physics-Driven Data Augmentation

  • Dominik EckertEmail author
  • Sulaiman Vesal
  • Ludwig Ritschl
  • Steffen Kappler
  • Andreas Maier
Conference paper
  • 14 Downloads
Part of the Informatik aktuell book series (INFORMAT)

Zusammenfassung

Mammography is using low-energy X-rays to screen the human breast and is utilized by radiologists to detect breast cancer. Typically radiologists require a mammogram with impeccable image quality for an accurate diagnosis. In this study, we propose a deep learning method based on Convolutional Neural Networks (CNNs) for mammogram denoising to improve the image quality. We first enhance the noise level and employ Anscombe Transformation (AT) to transform Poisson noise to white Gaussian noise. With this data augmentation, a deep residual network is trained to learn the noise map of the noisy images. We show, that the proposed method can remove not only simulated but also real noise. Furthermore, we also compare our results with state-of-the-art denoising methods, such as BM3D and DNCNN. In an early investigation, we achieved qualitatively better mammogram denoising results.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literatur

  1. 1. Bray F, Ferlay J, Soerjomataram I, et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians. 2018;68(6):394–424. Available from: https://onlinelibrary.wiley.com/doi/abs/10.3322/caac.21492.
  2. 2. Abdelhafiz D, Yang C, Ammar RA, et al. Deep convolutional neural networks for mammography: advances, challenges and applications. In: BMC Bioinformatics; 2019. .Google Scholar
  3. 3. Joseph AM, John MG, Dhas AS. Mammogram image denoising lters: A comparative study. In: Proc ICEDSS; 2017. p. 184–189.Google Scholar
  4. 4. Singh G, Mittal A, Aggarwal N. Deep convolution neural network based denoiser for mammographic images. In: Singh M, Gupta PK, Tyagi V, et al., editors. Advances in Computing and Data Sciences. Singapore: Springer Singapore; 2019. p. 177–187.Google Scholar
  5. 5. Maier A, Syben C, Stimpel B, et al. Learning with known operators reduces maximum error bounds. Nature Machine Intelligence. 2019;2019(1):373–380.Google Scholar
  6. 6. Zhang K, Zuo W, Chen Y, et al. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. IEEE Transactions on Image Processing. 2017 July;26(7):3142–3155.Google Scholar
  7. 7. Anscombe FJ. The Transformation of Poisson, Binomial and Negative-Binomial Data. Biometrika. 1948 dec;35(3/4):246.Google Scholar
  8. 8. Zhao H, Gallo O, Frosio I, et al. Loss Functions for Image Restoration With Neural Networks. IEEE Transactions on Computational Imaging. 2017 March;3(1).Google Scholar
  9. 9. Dabov K, Foi A, Katkovnik V, et al. Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering. IEEE Transactions on Image Processing. 2007 Aug;16(8):2080–2095.Google Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2020

Authors and Affiliations

  • Dominik Eckert
    • 1
    Email author
  • Sulaiman Vesal
    • 1
  • Ludwig Ritschl
    • 2
  • Steffen Kappler
    • 2
  • Andreas Maier
    • 1
  1. 1.Pattern Recognition LabFriedrich-Alexander-Universität Erlangen-NürnbergErlangenDeutschland
  2. 2.Siemens Healthcare GmbHForchheimDeutschland

Personalised recommendations