GPU-accelerated, gradient-free MI deformable registration for atlas-based MR brain image segmentation

Xiao Han, L.S. Hibbard, V. Willcut
2009 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
Brain structure segmentation is an important task in many neuroscience and clinical applications. In this paper, we introduce a novel MI-based dense deformable registration method and apply it to the automatic segmentation of detailed brain structures. Together with a multiple atlas fusion strategy, very accurate segmentation results were obtained, as compared with other reported methods in the literature. To make multi-atlas segmentation computationally feasible, we also propose to take
more » ... ge of the recent advancements in GPU technology and introduce a GPUbased implementation of the proposed registration method. With GPU acceleration it takes less than 8 minutes to compile a multi-atlas segmentation for each subject even with as many as 17 atlases, which demonstrates that the use of GPUs can greatly facilitate the application of such atlasbased segmentation methods in practice.
doi:10.1109/cvpr.2009.5204043 fatcat:i2js5sbklzftxcj32mhvxoxawm