Unsupervised partial volume estimation in single-channel image data
- 7 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Partial volume effects are present in nearly all medical imaging data. These artifacts blur the boundaries between different regions, making accurate delineation of anatomical structures difficult. Here, the authors propose a method for unsupervised estimation of partial volume effects in single-channel image data. Based on a statistical image model, an algorithm is derived for estimating both partial volumes and the means of the different tissue classes in the image. To compensate for the ill-posed nature of the estimation problem, the authors employ a Bayesian approach that places a prior probability model on the parameters. They demonstrate on simulated and real images that the new algorithm is superior in several respects to the fuzzy and Gaussian clustering algorithms that have previously been used for modeling partial volume effects.Keywords
This publication has 9 references indexed in Scilit:
- Optimal transformation for correcting partial volume averaging effects in magnetic resonance imagingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Partial volume estimation and the fuzzy C-means algorithm [brain MRI application]Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Adaptive fuzzy segmentation of magnetic resonance imagesIEEE Transactions on Medical Imaging, 1999
- Design and construction of a realistic digital brain phantomIEEE Transactions on Medical Imaging, 1998
- Partial-volume Bayesian classification of material mixtures in MR volume data using voxel histogramsIEEE Transactions on Medical Imaging, 1998
- Estimation of CSF, white and gray matter volumes in hydrocephalic children using fuzzy clustering of Mr ImagesComputerized Medical Imaging and Graphics, 1994
- Quantification of MR brain images by mixture density and partial volume modelingIEEE Transactions on Medical Imaging, 1993
- Partial volume tissue classification of multichannel magnetic resonance images-a mixel modelIEEE Transactions on Medical Imaging, 1991
- Fuzzy setsInformation and Control, 1965