Partial-volume Bayesian classification of material mixtures in MR volume data using voxel histograms

• Published in: IEEE transactions on medical imaging Vol. 17; no. 1; pp. 74 - 86
• Main Authors: Laidlaw, D.H., Fleischer, K.W., Barr, A.H.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01-02-1998; Institute of Electrical and Electronics Engineers
• Subjects: Algorithms; Animation; Bayes Theorem; Bayesian methods; Biological and medical sciences; Brain - anatomy & histology; Computational geometry; Computed tomography; Computer graphics; Computer simulation; Histograms; Humans; Image reconstruction; Image segmentation; Investigative techniques, diagnostic techniques (general aspects); Magnetic materials; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical sciences; Miscellaneous. Technology; Pattern recognition; Probability; Radiodiagnosis. Nmr imagery. Nmr spectrometry; Solid modeling; Tissue; Tomography, X-Ray Computed; Volume measurement; Bayes estimation; Radiodiagnosis; Materials; Anatomy; Nuclear magnetic resonance imaging; Modeling; Geometrical model; Mixture; Volume measurement; Classification; Size effect; Signal processing; Medical imagery; Computerized axial tomography
• ISSN: 0278-0062; 1558-254X
• DOI: 10.1109/42.668696

The authors present a new algorithm for identifying the distribution of different material types in volumetric datasets such as those produced with magnetic resonance imaging (MRI) or computed tomography (CT). Because the authors allow for mixtures of materials and treat voxels as regions, their technique reduces errors that other classification techniques can create along boundaries between materials and is particularly useful for creating accurate geometric models and renderings from volume data. It also has the potential to make volume measurements more accurately and classifies noisy, low-resolution data well. There are two unusual aspects to the authors' approach. First, they assume that, due to partial-volume effects, or blurring, voxels can contain more than one material, e.g., both muscle and fat; the authors compute the relative proportion of each material in the voxels. Second, they incorporate information from neighboring voxels into the classification process by reconstructing a continuous function, /spl rho/(x), from the samples and then looking at the distribution of values that /spl rho/(x) takes on within the region of a voxel. This distribution of values is represented by a histogram taken over the region of the voxel; the mixture of materials that those values measure is identified within the voxel using a probabilistic Bayesian approach that matches the histogram by finding the mixture of materials within each voxel most likely to have created the histogram. The size of regions that the authors classify is chosen to match the sparing of the samples because the spacing is intrinsically related to the minimum feature size that the reconstructed continuous function can represent.