Prior knowledge regularization in statistical medical image tasks
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Prior knowledge regularization in statistical medical image tasks. / Crimi, Alessandro; Sporring, Jon; de Bruijne, Marleen; Lillholm, Martin; Nielsen, Mads.
Proceedings of the MICCAI Workshop on Probabilistic Models for Medical Image Analysis. 2009.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Prior knowledge regularization in statistical medical image tasks
AU - Crimi, Alessandro
AU - Sporring, Jon
AU - de Bruijne, Marleen
AU - Lillholm, Martin
AU - Nielsen, Mads
N1 - Conference code: 12
PY - 2009
Y1 - 2009
N2 - The estimation of the covariance matrix is a pivotal step inseveral statistical tasks. In particular, the estimation becomes challeng-ing for high dimensional representations of data when few samples areavailable. Using the standard Maximum Likelihood estimation (MLE)when the number of samples are lower than the dimension of the datacan lead to incorrect estimation e.g. of the covariance matrix and subse-quent unreliable results of statistical tasks. This limitation is normallysolved by the well-known Tikhonov regularization adding partially anidentity matrix; here we discuss a Bayesian approach for regularizing thecovariance matrix using prior knowledge. Our method is evaluated forreconstructing and modeling vertebra and cartilage shapes from a lowerdimensional representation and a conditional model. For these centralproblems, the proposed methodology outperforms the traditional MLEmethod and the Tikhonov regularization.
AB - The estimation of the covariance matrix is a pivotal step inseveral statistical tasks. In particular, the estimation becomes challeng-ing for high dimensional representations of data when few samples areavailable. Using the standard Maximum Likelihood estimation (MLE)when the number of samples are lower than the dimension of the datacan lead to incorrect estimation e.g. of the covariance matrix and subse-quent unreliable results of statistical tasks. This limitation is normallysolved by the well-known Tikhonov regularization adding partially anidentity matrix; here we discuss a Bayesian approach for regularizing thecovariance matrix using prior knowledge. Our method is evaluated forreconstructing and modeling vertebra and cartilage shapes from a lowerdimensional representation and a conditional model. For these centralproblems, the proposed methodology outperforms the traditional MLEmethod and the Tikhonov regularization.
M3 - Article in proceedings
BT - Proceedings of the MICCAI Workshop on Probabilistic Models for Medical Image Analysis
Y2 - 20 September 2009 through 24 September 2009
ER -
ID: 21235760