Simultaneous Boundary and Partial Volume Estimation in Medical Images

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. In this paper, we propose a method for unsupervised estimation of partial volume fractions in single-channel image data. Unlike previous methods, the proposed algorithm simultaneously estimates partial volume fractions, the means of the different tissue classes, as well as the the locations of tissue boundaries within the image. The latter allows the partial volume fractions to be constrained to represent pure or nearly pure tissue except along tissue boundaries. We demonstrate the application of the algorithm on simulated and real magnetic resonance images.