Publications
Journals
Our Segmentation |
Improved Segmentation of White Matter Tracts with Adaptive Riemannian Metrics
X. Hao, Kristen Zygmunt, Ross T. Whitakter, and P.T. Fletcher. Medical Image Analysis, 2014 We present a novel geodesic approach to segment white matter tracts from diffusion tensor imaging (DTI). Compared to deterministic and stochastic tractography, geodesic approaches treat the geometry of the brain white matter as a manifold. The white matter pathways are then inferred from the resulting geodesics. Previous methods have tried to threshold the cost of the geodesics to segment white matter tracts, but the segmentation is senstitive to the threshold value. In this chapter, we develop a way to automatically segment the white matter tracts based on the computed geodesics. Paper: 
|
Conferences
Problematic Binary Segmentation
Fractional Segmentation |
Joint Fractional Segmentation and Multi-Tensor Estimation in Diffusion MRI
X. Hao and P.T. Fletcher. Information Processing in Medical Imaging (IPMI), 2013 In this paper we present a novel Bayesian approach for fractional segmentation of white matter tracts and simultaneous estimation of a multi-tensor diffusion model. We demonstrate that the proposed method can recover the correct volume fractions and tensor compartments, results in improved segmentation and diffusion measurement statistics on real data in the presence of crossing tracts and partial voluming. Paper:
Demo: 
|
Geodesics Before Correction
Geodesics After Correction |
Adaptive Riemannian Metrics for Improved Geodesic Tracking of White
Matter
X. Hao, R.T. Whitaker, and P.T. Fletcher. Information Processing in Medical Imaging (IPMI), 2011 We present a new geodesic approach for studying white matter connectivity from diffusion tensor imaging (DTI). In this paper we formulate a modification of the Riemannian metric that results in geodesics adapted to follow the principal eigendirection of the tensor even in high-curvature regions. We demonstrate that the proposed method results in improved geodesics using both synthetic and real DTI data. Paper:
IPMI Presentation (Updated):
|
