2015
DOI: 10.1016/j.cviu.2014.09.004
|View full text |Cite
|
Sign up to set email alerts
|

Improving label fusion in multi-atlas based segmentation by locally combining atlas selection and performance estimation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
4
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
4
1

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(4 citation statements)
references
References 26 publications
0
4
0
Order By: Relevance
“…When multiple raters provide segmentations from an identical dataset, it is of interest to produce a gold standard. For a voxel representation, a probability map can be constructed, where each voxel value represents the number of raters that counted the voxel as part of their segmentation (Frisoni et al, 2015;Iglesias & Sabuncu, 2015;Langerak, van der Heide, Kotte, Berendsen, & Pluim, 2015; Pipitone et al, 2014). This can be normalized and then thresholded to obtain a binary mask representing whether or not the voxel was segmented by enough rater.…”
Section: Gold Standardmentioning
confidence: 99%
“…When multiple raters provide segmentations from an identical dataset, it is of interest to produce a gold standard. For a voxel representation, a probability map can be constructed, where each voxel value represents the number of raters that counted the voxel as part of their segmentation (Frisoni et al, 2015;Iglesias & Sabuncu, 2015;Langerak, van der Heide, Kotte, Berendsen, & Pluim, 2015; Pipitone et al, 2014). This can be normalized and then thresholded to obtain a binary mask representing whether or not the voxel was segmented by enough rater.…”
Section: Gold Standardmentioning
confidence: 99%
“…Offline selection aims to select the atlas(es) that outperform other candidate atlases on average in an offline training [38], [40], [45]. Specifically, the process selects atlases that represent the mode of the segmentation performance distribution from the database, and can be estimated empirically offline since the reference contours of all atlases are available.…”
Section: E Offline Atlas Selectionmentioning
confidence: 99%
“…FMRIB's Linear Image Registration Tool (FLIRT) 6,7 in the FMRIB Software Library (FSL) a 8 is an affine registration method, which provides a standard framework for MR images registration based on the image intensity. FLIRT can handle multi-modality medical image (e.g., functional MRI, structure MRI and PET).…”
Section: Fmrib's Linear Image Registration Toolmentioning
confidence: 99%
“…Also, the term σ=mi x i n‖P(y)-P(x i )‖+ε. PBM uses the calculated pairwise similarity between the target patch and the selected candidate patch within the certain region as the voting weight to calculate the soft label of to-be-segmented by the weight sum,(7) where δ(l(x i,k )=c) is a Dirac function, which equals to 1 when l(x i,k )=c and 0 otherwise. Also, PBM obtain the final label of to-be-segmented voxel by Eq.…”
mentioning
confidence: 99%