Recognizing deviations from normalcy for brain tumor segmentation

Abstract

A framework is proposed for the segmentation of brain tumors from MRI. Instead of training on pathology, the proposed method trains exclusively on healthy tissue. The algorithm attempts to recognize deviations from normalcy in order to compute a fitness map over the image associated with the presence of pathology. The resulting fitness map may then be used by conventional image segmentation techniques for honing in on boundary delineation. Such an approach is applicable to structures that are too irregular, in both shape and texture, to permit construction of comprehensive training sets. We develop the method of diagonalized nearest neighbor pattern recognition, and we use it to demonstrate that recognizing deviations from normalcy requires a rich understanding of context. Therefore, we propose a framework for a Contextual Dependency Network (CDN) that incorporates context at multiple levels: voxel intensities, neighborhood coherence, intra-structure properties, inter-structure relationships, and user input. Information flows bi-directionally between the layers via multi-level Markov random fields or iterated Bayesian classification. A simple instantiation of the framework has been implemented to perform preliminary experiments on synthetic and MRI data.