Robust parameter estimation of intensity distributions for brain magnetic resonance images

• Published in: IEEE transactions on medical imaging Vol. 17; no. 2; pp. 172 - 186
• Main Authors: Schroeter, P., Vesin, J.-M., Langenberger, T., Meuli, R.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.04.1998; Institute of Electrical and Electronics Engineers
• Subjects: Adolescent; Adult; Aged; Algorithms; Bias; Biological and medical sciences; Brain; Brain - anatomy & histology; Computational efficiency; Computer Simulation; Female; Gaussian distribution; Genetic algorithms; Histograms; Humans; Image Enhancement - methods; Image Processing, Computer-Assisted - statistics & numerical data; Image segmentation; Investigative techniques, diagnostic techniques (general aspects); Likelihood Functions; Magnetic heads; Magnetic resonance; Magnetic resonance imaging; Magnetic Resonance Imaging - statistics & numerical data; Male; Mathematical models; Medical sciences; Middle Aged; Models, Statistical; Monte Carlo Method; Nervous system; Normal Distribution; Parameter estimation; Radiodiagnosis. Nmr imagery. Nmr spectrometry; Robustness; Statistical distributions; Statistical methods; Stochastic Processes; Human; Parameter estimation; Segmentation; Central nervous system; Medical imagery; Technique; Nuclear magnetic resonance imaging; Brain (vertebrata)
• ISSN: 0278-0062; 1558-254X
• DOI: 10.1109/42.700730

Presents two new methods for robust parameter estimation of mixtures in the context of magnetic resonance (MR) data segmentation. The head is constituted of different types of tissue that can be modeled by a finite mixture of multivariate Gaussian distributions. The authors' goal is to estimate accurately the statistics of desired tissues in presence of other ones of lesser interest. These latter can be considered as outliers and can severly bias the estimates of the former. For this purpose, the authors introduce a first method, which is an extension of the expectation-maximization (EM) algorithm, that estimates parameters of Gaussian mixtures but incorporates an outlier rejection scheme which allows to compute the properties of the desired tissues in presence of atypical data. The second method is based on genetic algorithms and is well suited for estimating the parameters of mixtures of different kind of distributions. The authors use this property by adding a uniform distribution to the Gaussian mixture for modeling the outliers. The proposed genetic algorithm can efficiently estimate the parameters of this extended mixture for various initial settings. Also, by changing the minimization criterion, estimates of the parameters can be obtained by histogram fitting which considerably reduces the computational cost. Experiments on synthetic and real MR data show that accurate estimates of the gray and white matters parameters are computed.