Graph-based methods have become popular in recent years and have successfully addressed tasks like segmentation and deformable registration. Their main strength is optimality of the obtained solution while their main limitation is the lack of precision due to the grid-like representations and the discrete nature of the quantized search space. In this paper we introduce a novel approach for combined segmentation/registration of brain tumors that adapts graph and sampling resolution according to the image content. To this end we estimate the segmentation and registration marginals towards adaptive graph resolution and intelligent definition of the search space. This information is considered in a hierarchical framework where uncertainties are propagated in a natural manner. State of the art results in the joint segmentation/registration of brain images with low-grade gliomas demonstrate the potential of our approach.

In this paper we propose a novel approach for detection, segmentation and characterization of brain tumors. Our method exploits prior knowledge in the form of a sparse graph representing the expected spatial positions of tumor classes. Such information is coupled with image-based classification techniques along with spatial smoothness constraints towards producing a reliable detection map within a unified graphical model formulation. Towards optimal use of prior knowledge, a two layer interconnected graph is considered with one layer corresponding to the low-grade glioma type (characterization) and the second layer to voxel-based decisions of tumor presence. Efficient linear programming both in terms of performance as well as in terms of computational load is considered to recover the lowest potential of the objective function. The outcome of the method refers to both tumor segmentation as well as their characterization. Promising results on substantial data sets demonstrate the extreme potentials of our method.