|
rdf:type |
|
|
lifeskim:mentions |
|
|
pubmed:issue |
5
|
|
pubmed:dateCreated |
2008-8-12
|
|
pubmed:abstractText |
In non-rigid registration, the tradeoff between warp regularization and image fidelity is typically determined empirically. In atlas-based 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. In this paper, we employ a generative model for the joint registration and segmentation of images. The atlas construction process arises naturally as estimation of the model parameters. This framework allows the computation of unbiased atlases from manually labeled data at various degrees of "sharpness", as well as the joint registration and segmentation of a novel brain in a consistent manner. We study the effects of the tradeoff of atlas sharpness and warp smoothness in the context of cortical surface parcellation. This is an important question because of the increasingly availability of atlases in public databases, and the development of registration algorithms separate from the atlas construction process. We find that the optimal segmentation (parcellation) corresponds to a unique balance of atlas sharpness and warp regularization, yielding statistically significant improvements over the FreeSurfer parcellation algorithm. Furthermore, we conclude that one can simply use a single atlas computed at an optimal sharpness for the registration-segmentation of a new subject with a pre-determined, fixed, optimal warp constraint. The optimal atlas sharpness and warp smoothness can be determined by probing the segmentation performance on available training data. Our experiments also suggest that segmentation accuracy is tolerant up to a small mismatch between atlas sharpness and warp smoothness.
|
|
pubmed:grant |
http://linkedlifedata.com/resource/pubmed/grant/P41 RR006009-150400,
http://linkedlifedata.com/resource/pubmed/grant/P41 RR013218-06,
http://linkedlifedata.com/resource/pubmed/grant/P41-RR13218,
http://linkedlifedata.com/resource/pubmed/grant/P41-RR14075,
http://linkedlifedata.com/resource/pubmed/grant/R01 EB001550,
http://linkedlifedata.com/resource/pubmed/grant/R01 EB006758-02,
http://linkedlifedata.com/resource/pubmed/grant/R01 NS051826-03,
http://linkedlifedata.com/resource/pubmed/grant/R01 NS052585-01,
http://linkedlifedata.com/resource/pubmed/grant/R01 NS052585-03,
http://linkedlifedata.com/resource/pubmed/grant/R01 RR016594-01A1,
http://linkedlifedata.com/resource/pubmed/grant/R01 RR16594-01A1,
http://linkedlifedata.com/resource/pubmed/grant/R01-NS051826,
http://linkedlifedata.com/resource/pubmed/grant/R01EB006758,
http://linkedlifedata.com/resource/pubmed/grant/U24 RR021382,
http://linkedlifedata.com/resource/pubmed/grant/U24 RR021382-04,
http://linkedlifedata.com/resource/pubmed/grant/U24-RR021382,
http://linkedlifedata.com/resource/pubmed/grant/U54 EB005149-01,
http://linkedlifedata.com/resource/pubmed/grant/U54-EB005149
|
|
pubmed:commentsCorrections |
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-10334905,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-10619420,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-10628949,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-11145307,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-11293693,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-11798269,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-11832223,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-12044997,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-12868620,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-14561557,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-14654453,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-15627570,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-15919231,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-15955494,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-16466677,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-16530430,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-16860573,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-17354680,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-17354690,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-17427739,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-17427741,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-17427745,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-8670651,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-9343592,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-9931268,
http://linkedlifedata.com/resource/pubmed/commentcorrection/18667352-9931269
|
|
pubmed:language |
eng
|
|
pubmed:journal |
|
|
pubmed:citationSubset |
IM
|
|
pubmed:status |
MEDLINE
|
|
pubmed:month |
Oct
|
|
pubmed:issn |
1361-8423
|
|
pubmed:author |
|
|
pubmed:issnType |
Electronic
|
|
pubmed:volume |
12
|
|
pubmed:owner |
NLM
|
|
pubmed:authorsComplete |
Y
|
|
pubmed:pagination |
603-15
|
|
pubmed:dateRevised |
2011-9-26
|
|
pubmed:meshHeading |
pubmed-meshheading:18667352-Algorithms,
pubmed-meshheading:18667352-Artifacts,
pubmed-meshheading:18667352-Artificial Intelligence,
pubmed-meshheading:18667352-Brain,
pubmed-meshheading:18667352-Humans,
pubmed-meshheading:18667352-Image Enhancement,
pubmed-meshheading:18667352-Image Interpretation, Computer-Assisted,
pubmed-meshheading:18667352-Imaging, Three-Dimensional,
pubmed-meshheading:18667352-Magnetic Resonance Imaging,
pubmed-meshheading:18667352-Pattern Recognition, Automated,
pubmed-meshheading:18667352-Reproducibility of Results,
pubmed-meshheading:18667352-Sensitivity and Specificity,
pubmed-meshheading:18667352-Subtraction Technique
|
|
pubmed:year |
2008
|
|
pubmed:articleTitle |
Effects of registration regularization and atlas sharpness on segmentation accuracy.
|
|
pubmed:affiliation |
Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA. ythomas@csail.mit.edu
|
|
pubmed:publicationType |
Journal Article,
Research Support, U.S. Gov't, Non-P.H.S.,
Research Support, Non-U.S. Gov't,
Evaluation Studies,
Research Support, N.I.H., Extramural
|
