Multi-Spectral Probabilistic Diffusion Using Bayesian Classification

This paper proposes a diiusion scheme for multi-spectral images which incorporates both spatial derivatives and feature-space clas-siication. A variety of conductance terms are suggested that use the posterior probability maps and their spatial derivatives to create resis-tive boundaries that reeect objectness rather than intensity diierences alone. A theoretical test case is discussed as well as simulated and real magnetic resonance dual echo images. We compare the method for both supervised and unsupervised classiication.