Automatic correction of bias field in magnetic resonance images

Abstract

Two fully automatic restoration-segmentation algorithms are proposed for the processing of biased magnetic resonance images. A first approach is based on an expectation-maximization procedure, where the initial conditions for the class distribution parameters and the number of classes are obtained, without any a priori knowledge, from a mode-based analysis of the biased image. A second approach relies completely on the mode-based analysis to update the number of classes and distribution parameters in every iteration. Both methods give accurate results even for overlapping distributions distorted by a gain factor of up to 40%. The possibility of having automatic initial conditions provides an important enhancement to previously reported methods.

Keywords

A priori and a posterioriExpectation–maximization algorithmComputer scienceMaximizationSegmentationImage segmentationMode (computer interface)Artificial intelligenceAlgorithmImage processingField (mathematics)Image (mathematics)Distribution (mathematics)Pattern recognition (psychology)MathematicsMaximum likelihoodMathematical optimizationStatisticsMathematical analysis

Affiliated Institutions

Related Publications

Statistical approach to X-ray CT imaging and its applications in image analysis. II. A new stochastic model-based image segmentation technique for X-ray CT image

T. Lei , Wilfred Sewchand

For pt.I, see ibid., vol.11, no.1, p.53.61 (1992). Based on the statistical properties of X-ray CT imaging given in pt.I, an unsupervised stochastic model-based image segmentati...

1992 IEEE Transactions on Medical Imaging 91 citations

Automated model-based bias field correction of MR images of the brain

Koen Van Leemput , Frederik Maes , Dirk Vandermeulen +1 more

We propose a model-based method for fully automated bias field correction of MR brain images. The MR signal is modeled as a realization of a random process with a parametric pro...

1999 IEEE Transactions on Medical Imaging 583 citations

Estimating the bias field of MR images

R. Guillemaud , Michael Brady

We propose a modification of Wells et al. technique for bias field estimation and segmentation of magnetic resonance (MR) images. We show that replacing the class other, which i...

1997 IEEE Transactions on Medical Imaging 326 citations

Adaptive segmentation of MRI data

William M. Wells , W. Eric L. Grimson , Ron Kikinis +1 more

Intensity-based classification of MR images has proven problematic, even when advanced techniques are used. Intrascan and interscan intensity inhomogeneities are a common source...

1996 IEEE Transactions on Medical Imaging 1273 citations

The mean field theory in EM procedures for blind Markov random field image restoration

J. Zhang

A Markov random field (MRF) model-based EM (expectation-maximization) procedure for simultaneously estimating the degradation model and restoring the image is described. The MRF...

1993 IEEE Transactions on Image Processing 148 citations

Publication Info

Year: 2003
Type: article
Pages: 752-756
Citations: 1
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Automatic correction of bias field in magnetic resonance images

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

OpenAlex

Cite This

APA Style

                            
                                    M. Garza-Jinich, 
                                
                                    Óscar Yáñez-Suárez, 
                                
                                    V. Medina
                                
                                et al.
                            
                            (2003). 
                            Automatic correction of bias field in magnetic resonance images. 
                            
                            , 752-756.
                            https://doi.org/10.1109/iciap.1999.797685

Identifiers

DOI: 10.1109/iciap.1999.797685