Advertisement

Sodium Image Denoising Based on a Convolutional Denoising Autoencoder

  • Simon KoppersEmail author
  • Edouard Coussoux
  • Sandro Romanzetti
  • Kathrin Reetz
  • Dorit Merhof
Conference paper
Part of the Informatik aktuell book series (INFORMAT)

Zusammenfassung

Sodium Magnetic Resonance Imaging (sodium MRI) is an imaging modality that has gained momentum over the past decade, because of its potential ability to become a biomarker for several diseases, ranging from cancer to neurodegenerative pathologies, along with monitoring of tissues metabolism. One of the most important limitation to the exploitation of this imaging modality is its characteristic low resolution and signal-to-noise-ratio as compared to the classical proton MRI, which is due to the notably lower concentration of sodium than water in the human body. Therefore, denoising is a central aspect with respect to the clinical use of sodium MRI. In this work, we introduce a Convolutional Denoising Autoencoder that is trained on a training database of thirteen training subjects with three sodium MRI images each. The results illustrate that the denoised images show a strong improvement after application in comparison to the state-of-the-art Non Local Means denoising algorithm. This effect is demonstrated based on different noise metrics and a qualitative evaluation.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literatur

  1. 1.
    Madelin G, Lee JS, Regatte RR, et al. Sodium MRI: methods and applications. Prog Nucl Magn Reson Spectrosc. 2014;79:14 – 47.CrossRefGoogle Scholar
  2. 2.
    Romanzetti S, Mirkes CC, Fiege DP, et al. Mapping tissue sodium concentration in the human brain: a comparison of MR-sequences at 9.4 tesla. Neuroimage. 2014;96:44 – 53.CrossRefGoogle Scholar
  3. 3.
    LeCun Y, Bengio Y, Hinton G. Deep learning. Nat. 2015;521(7553):436.CrossRefGoogle Scholar
  4. 4.
    Buades A, Coll B, Morel JM. Non-local means denoising. Image Process Line. 2011;1:208–212.Google Scholar
  5. 5.
    Vincent P, Larochelle H, Bengio Y, et al.; ACM. Extracting and composing robust features with denoising autoencoders. Procs 25th Int Conf Mach Learn. 2008; p. 1096–1103.Google Scholar
  6. 6.
    Vincent P, Larochelle H, Lajoie I, et al. Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J Mach Learn Res. 2010;11(Dec):3371–3408.Google Scholar
  7. 7.
    Smith SM. Fast robust automated brain extraction. Hum Brain Mapp. 2002;17(3):143–155.CrossRefGoogle Scholar
  8. 8.
    Wang Z, Bovik AC. Mean squared error: love it or leave it? a new look at signal _delity measures. IEEE Signal Process Mag. 2009;26(1):98–117.Google Scholar
  9. 9.
    Wang Z, Bovik AC, Sheikh HR, et al. Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process. 2004;13(4):600–612.CrossRefGoogle Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2019

Authors and Affiliations

  • Simon Koppers
    • 1
    Email author
  • Edouard Coussoux
    • 1
  • Sandro Romanzetti
    • 2
    • 3
  • Kathrin Reetz
    • 2
    • 3
  • Dorit Merhof
    • 1
  1. 1.Institute of Imaging & Computer VisionRWTH Aachen UniversityAachenDeutschland
  2. 2.Department of NeurologyRWTH Aachen UniversityAachenDeutschland
  3. 3.JARA-BRAIN Institute Molecular Neuroscience and NeuroimagingForschungszentrum Jülich GmbH and RWTH Aachen UniversityAachenDeutschland

Personalised recommendations