rdf:type |
|
lifeskim:mentions |
|
pubmed:issue |
Pt 1
|
pubmed:dateCreated |
2007-12-4
|
pubmed:abstractText |
In this paper, we propose a unified framework for computing atlases from manually labeled data at various degrees of "sharpness" and the joint registration-segmentation of a new brain with these atlases. In non-rigid registration, the tradeoff between warp regularization and image fidelity is typically set empirically. In segmentation, this leads to a probabilistic atlas of arbitrary "sharpness": weak regularization results in well-aligned training images and a "sharp" atlas; strong regularization yields a "blurry" atlas. We study the effects of this tradeoff in the context of cortical surface parcellation by comparing three special cases of our framework, namely: progressive registration-segmentation of a new brain to increasingly "sharp" atlases with increasingly flexible warps; secondly, progressive registration to a single atlas with increasingly flexible warps; and thirdly, registration to a single atlas with fixed constrained warps. The optimal parcellation in all three cases corresponds to a unique balance of atlas "sharpness" and warp regularization that yield statistically significant improvements over the previously demonstrated parcellation results.
|
pubmed:grant |
|
pubmed:commentsCorrections |
http://linkedlifedata.com/resource/pubmed/commentcorrection/18051118-11145307,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18051118-11798269,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18051118-12044997,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18051118-14654453,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18051118-15627570,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18051118-15955494,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18051118-16466677,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18051118-16530430,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18051118-17354951,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18051118-17354952,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18051118-9931269
|
pubmed:language |
eng
|
pubmed:journal |
|
pubmed:citationSubset |
IM
|
pubmed:status |
MEDLINE
|
pubmed:author |
|
pubmed:volume |
10
|
pubmed:owner |
NLM
|
pubmed:authorsComplete |
Y
|
pubmed:pagination |
683-91
|
pubmed:dateRevised |
2010-9-15
|
pubmed:meshHeading |
pubmed-meshheading:18051118-Algorithms,
pubmed-meshheading:18051118-Cerebrum,
pubmed-meshheading:18051118-Computer Simulation,
pubmed-meshheading:18051118-Humans,
pubmed-meshheading:18051118-Image Enhancement,
pubmed-meshheading:18051118-Image Interpretation, Computer-Assisted,
pubmed-meshheading:18051118-Imaging, Three-Dimensional,
pubmed-meshheading:18051118-Magnetic Resonance Imaging,
pubmed-meshheading:18051118-Models, Biological,
pubmed-meshheading:18051118-Models, Statistical,
pubmed-meshheading:18051118-Reproducibility of Results,
pubmed-meshheading:18051118-Sensitivity and Specificity,
pubmed-meshheading:18051118-Subtraction Technique
|
pubmed:year |
2007
|
pubmed:articleTitle |
Effects of registration regularization and atlas sharpness on segmentation accuracy.
|
pubmed:affiliation |
Computer Science and Artificial Intelligence Lab, MIT, USA.
|
pubmed:publicationType |
Journal Article,
Research Support, U.S. Gov't, Non-P.H.S.,
Research Support, Non-U.S. Gov't,
Research Support, N.I.H., Extramural
|