Jason J. Corso; EECS @ U of Michigan

Automatic segmentation is a difficult problem: it is under-constrained, precise physical models are generally not yet known, and the data presents high intra-class variance. In this research, we study methods for automatic segmentation of image data that strive to leverage the efficiency of bottom-up algorithms with the power of top-down models. The work takes one step toward unifying two state-of-the-art image segmentation approaches: graph affinity-based and generative model-based segmentation. Specifically, the main contribution of the work is a mathematical formulation for incorporating soft model assignments into the calculation of affinities, which are traditionally model free. This Bayesian model-aware affinity measurement has been integrated into the multilevel Segmentation by Weighted Aggregation algorithm. As a byproduct of the integrated Bayesian model classification, each node in the graph hierarchy is assigned a most likely model class according to a set of learned model classes. The technique has been applied to the task of detecting and segmenting brain tumor and edema, subcortical brain structures and multiple sclerosis lesions in multichannel magnetic resonance image volumes (see the application page for more details on the use of the ideas).

This is an example result on a synthetic image.

This is an example result on 3D structural MRI for brain subcortical structure segmentation.

Code: is available. Please email me.