Combining a patch-based approach with a non-rigid registration-based label fusion method for the hippocampal segmentation
We propose a patch-based labeling method, which cooperates
with a label fusion using non-rigid registrations. We present
a novel patch-based label fusion method, whose selected patches and their weights are calculated from a combination of similarity measures between patches using intensity-based distances and labeling-based distances, where a previous labeling of the target image is inferred by a label fusion method using non-rigid registrations. We compare several label fusion methods on publicly available MR images of human brains for segmenting the hippocampus.
with a label fusion using non-rigid registrations. We present
a novel patch-based label fusion method, whose selected patches and their weights are calculated from a combination of similarity measures between patches using intensity-based distances and labeling-based distances, where a previous labeling of the target image is inferred by a label fusion method using non-rigid registrations. We compare several label fusion methods on publicly available MR images of human brains for segmenting the hippocampus.
Execution Options
Download Now:
Execute Now:
Specifications
Domain:
Recent Activity - Files
lf_patches: demo_CRF_patch_v.0.2 release
demo_CRF_patchv.0.2.zip posted by Carlos Platero on Feb 7, 2018
lf_patches: demo_CRF_patch_v.0.1 release
demo_CRF_patchv.0.1.zip posted by Carlos Platero on Mar 18, 2016
lf_patches: CRF_PATCHES_matlab_mexw64 release
LF_PATCHES_v0.0.0.zip posted by Carlos Platero on Jun 6, 2015