• IEEE Trans Med Imaging · Sep 2007

    Feature-preserving MRI denoising: a nonparametric empirical Bayes approach.

    • Suyash P Awate and Ross T Whitaker.
    • Scientific Computing and Imaging (SCI) Institute, Salt Lake City, UT 84112, USA.
    • IEEE Trans Med Imaging. 2007 Sep 1; 26 (9): 1242-55.

    AbstractThis paper presents a novel method for Bayesian denoising of magnetic resonance (MR) images that bootstraps itself by inferring the prior, i.e., the uncorrupted-image statistics, from the corrupted input data and the knowledge of the Rician noise model. The proposed method relies on principles from empirical Bayes (EB) estimation. It models the prior in a nonparametric Markov random field (MRF) framework and estimates this prior by optimizing an information-theoretic metric using the expectation-maximization algorithm. The generality and power of nonparametric modeling, coupled with the EB approach for prior estimation, avoids imposing ill-fitting prior models for denoising. The results demonstrate that, unlike typical denoising methods, the proposed method preserves most of the important features in brain MR images. Furthermore, this paper presents a novel Bayesian-inference algorithm on MRFs, namely iterated conditional entropy reduction (ICER). This paper also extends the application of the proposed method for denoising diffusion-weighted MR images. Validation results and quantitative comparisons with the state of the art in MR-image denoising clearly depict the advantages of the proposed method.

      Pubmed     Full text   Copy Citation     Plaintext  

      Add institutional full text...

    Notes

     
    Knowledge, pearl, summary or comment to share?
    300 characters remaining
    help        

    hide…

What will the 'Medical Journal of You' look like?

Start your free 21 day trial now.

We guarantee your privacy. Your email address will not be shared.