Estimating gain fields in multispectral MRI

An unsupervised, completely automatic method for gain field estimation and segmentation of multispectral magnetic resonance (MR) images is presented. This new adaptive algorithm is based on statistical modeling of MR images using finite mixtures. Variability of gain field artifact with imaging parameters (i.e. TE, TR, and TI) is considered in the estimation process. Beside gain field, partial volume artifact is also considered in the labeling phase. Quantitative analysis on experimental results shows an efficient and robust performance of the adaptive algorithm and that it outperforms even advanced nonadaptive intensity-based approaches.