Unsupervised Partial Volume Estimation in Single-Channel Image Data
MMBIA '00 Proceedings of the IEEE Workshop on Mathematical Methods in Biomedical Image Analysis
Efficient Partial Volume Tissue Classification in MRI Scans
MICCAI '02 Proceedings of the 5th International Conference on Medical Image Computing and Computer-Assisted Intervention-Part I
| Hi-index | 0.00 |
Accurate brain tissue segmentation by intensity-based voxel classification of MR images is complicated by partial volume (PV) voxels that contain a mixture of two or more tissue types. In this paper, we present a statistical framework for PV segmentation that combines and extends existing techniques. We think of a partial volumed image as a downsampled version of a fictive higher-resolution image that does not contain partial voluming, and we estimate the model parameters of this underlying image using an Expectation-Maximization algorithm. This leads to an iterative approach that interleaves a statistical classification of the image voxels using spatial information and an according update of the model parameters. We illustrate the performance of the method on simulated data and on 2-D slices of real MR images. We demonstrate that the use of appropriate spatial models not only improves the classification, but is often indispensable for robust parameter estimation as well.