Hierarchical max-flow segmentation framework for multi-atlas segmentation with Kohonen self-organizing map based Gaussian mixture modeling

• Novel probabilistic multi-atlas segmentation framework.
• Large scale Gaussian mixture models achieved through Kohonen self-organizing maps.
• Deformable registration and label fusion generate spatial priors from the multi-atlas.
• Max-flow solver incorporates these priors with hierarchical label information.
• Framework validated on 2 open neuro-imaging databases.

The incorporation of intensity, spatial, and topological information into large-scale multi-region segmentation has been a topic of ongoing research in medical image analysis. Multi-region segmentation problems, such as segmentation of brain structures, pose unique challenges in image segmentation in which regions may not have a defined intensity, spatial, or topological distinction, but rely on a combination of the three. We propose a novel framework within the Advanced segmentation tools (ASETS)2, which combines large-scale Gaussian mixture models trained via Kohonen self-organizing maps, with deformable registration, and a convex max-flow optimization algorithm incorporating region topology as a hierarchy or tree. Our framework is validated on two publicly available neuroimaging datasets, the OASIS and MRBrainS13 databases, against the more conventional Potts model, achieving more accurate segmentations. Each component is accelerated using general-purpose programming on graphics processing Units to ensure computational feasibility.

Figure optionsDownload high-quality image (331 K)Download as PowerPoint slide