A New Image Registration Technique with Free Boundary Constraints: Application to Mammography

In this paper, a new image-matching mathematical model is presented with its application to mammogram registration. In a variational framework, an energy minimization problem is formulated and a multigrid resolution algorithm is designed. The model focuses on the matching of regions of interest. It also combines several constraints which are both intensity and segmentation based. A new feature of our model is combining region matching and segmentation by formulation of the energy minimization problem with free boundary conditions. Moreover, the energy has a new registration constraint. The performances of the new model and an equivalent model with fixed boundary conditions are compared on simulated mammogram pairs. It is shown that the model with free boundary is more robust to initialization inaccuracies than the one with fixed boundary conditions. Both models are applied to several real bilateral mammogram pairs. The model ability to compensate significantly for some normal differences between mammograms is illustrated. Results suggest that the new model could enable some improvements of mammogram comparisons and tumor detection system performances.