Name
Abstract | ||
|---|---|---|
Susceptibility-weighted imaging (SWI) venography can produce detailed venous contrast and complement arterial dominated MR angiography (MRA) techniques. However, these dense reversed-contrast SWI venograms pose new segmentation challenges. We present an automatic method for whole-brain venous blood segmentation in SWI using Conditional Random Fields (CRF). The CRF model combines different first and second order potentials. First-order association potentials are modeled as the composite of an appearance potential, a Hessianbased shape potential and a non-linear location potential. Second-order interaction potentials are modeled using an autologistic (smoothing) potential and a data-dependent (edge) potential. Minimal post-processing is used for excluding voxels outside the brain parenchyma and visualizing the surface vessels. The CRF model is trained and validated using 30 SWI venograms acquired within a population of deep brain stimulation (DBS) patients (age range = 43-73 years). Results demonstrate robust and consistent segmentation in deep and subcortical regions (median kappa = 0.84 and 0.82), as well as in challenging mid-sagittal and surface regions (median kappa = 0.81 and 0.83) regions. Overall, this CRF model produces highquality segmentation of SWI venous vasculature that finds applications in DBS for minimizing hemorrhagic risks and other surgical and non-surgical applications. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/TMI.2015.2442236 | Medical Imaging, IEEE Transactions |
Keywords | Field | DocType |
conditional random fields,deep brain stimulation,image-guided neurosurgery,mr venography,susceptibility-weighted imaging,shape,image segmentation,imaging | Voxel,Conditional random field,Population,Computer vision,Segmentation,Computer science,Image segmentation,Smoothing,Artificial intelligence,Venography,Susceptibility weighted imaging | Journal |
Volume | Issue | ISSN |
PP | 99 | 0278-0062 |
Citations | PageRank | References |
5 | 0.44 | 24 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Silvain Bériault | 1 | 5 | 0.44 |
| Yiming Xiao | 2 | 5 | 0.44 |
| D Louis Collins | 3 | 115 | 7.41 |
| G Bruce Pike | 4 | 399 | 22.73 |