Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950902996> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2950902996 abstract "Difficult image segmentation problems, for instance left atrium MRI, can be addressed by incorporating shape priors to find solutions that are consistent with known objects. Nonetheless, a single multivariate Gaussian is not an adequate model in cases with significant nonlinear shape variation or where the prior distribution is multimodal. Nonparametric density estimation is more general, but has a ravenous appetite for training samples and poses serious challenges in optimization, especially in high dimensional spaces. Here, we propose a maximum-a-posteriori formulation that relies on a generative image model by incorporating both local intensity and global shape priors. We use deep autoencoders to capture the complex intensity distribution while avoiding the careful selection of hand-crafted features. We formulate the shape prior as a mixture of Gaussians and learn the corresponding parameters in a high-dimensional shape space rather than pre-projecting onto a low-dimensional subspace. In segmentation, we treat the identity of the mixture component as a latent variable and marginalize it within a generalized expectation-maximization framework. We present a conditional maximization-based scheme that alternates between a closed-form solution for component-specific shape parameters that provides a global update-based optimization strategy, and an intensity-based energy minimization that translates the global notion of a nonlinear shape prior into a set of local penalties. We demonstrate our approach on the left atrial segmentation from gadolinium-enhanced MRI, which is useful in quantifying the atrial geometry in patients with atrial fibrillation." @default.
- W2950902996 created "2019-06-27" @default.
- W2950902996 creator A5000258401 @default.
- W2950902996 creator A5015074091 @default.
- W2950902996 creator A5040162472 @default.
- W2950902996 creator A5050076136 @default.
- W2950902996 creator A5068780431 @default.
- W2950902996 creator A5085364817 @default.
- W2950902996 date "2019-03-06" @default.
- W2950902996 modified "2023-09-27" @default.
- W2950902996 title "Mixture Modeling of Global Shape Priors and Autoencoding Local Intensity Priors for Left Atrium Segmentation" @default.
- W2950902996 hasPublicationYear "2019" @default.
- W2950902996 type Work @default.
- W2950902996 sameAs 2950902996 @default.
- W2950902996 citedByCount "0" @default.
- W2950902996 crossrefType "posted-content" @default.
- W2950902996 hasAuthorship W2950902996A5000258401 @default.
- W2950902996 hasAuthorship W2950902996A5015074091 @default.
- W2950902996 hasAuthorship W2950902996A5040162472 @default.
- W2950902996 hasAuthorship W2950902996A5050076136 @default.
- W2950902996 hasAuthorship W2950902996A5068780431 @default.
- W2950902996 hasAuthorship W2950902996A5085364817 @default.
- W2950902996 hasConcept C105795698 @default.
- W2950902996 hasConcept C107673813 @default.
- W2950902996 hasConcept C126255220 @default.
- W2950902996 hasConcept C153180895 @default.
- W2950902996 hasConcept C154945302 @default.
- W2950902996 hasConcept C177769412 @default.
- W2950902996 hasConcept C182081679 @default.
- W2950902996 hasConcept C2776330181 @default.
- W2950902996 hasConcept C32834561 @default.
- W2950902996 hasConcept C33923547 @default.
- W2950902996 hasConcept C41008148 @default.
- W2950902996 hasConcept C49781872 @default.
- W2950902996 hasConcept C61224824 @default.
- W2950902996 hasConcept C89600930 @default.
- W2950902996 hasConceptScore W2950902996C105795698 @default.
- W2950902996 hasConceptScore W2950902996C107673813 @default.
- W2950902996 hasConceptScore W2950902996C126255220 @default.
- W2950902996 hasConceptScore W2950902996C153180895 @default.
- W2950902996 hasConceptScore W2950902996C154945302 @default.
- W2950902996 hasConceptScore W2950902996C177769412 @default.
- W2950902996 hasConceptScore W2950902996C182081679 @default.
- W2950902996 hasConceptScore W2950902996C2776330181 @default.
- W2950902996 hasConceptScore W2950902996C32834561 @default.
- W2950902996 hasConceptScore W2950902996C33923547 @default.
- W2950902996 hasConceptScore W2950902996C41008148 @default.
- W2950902996 hasConceptScore W2950902996C49781872 @default.
- W2950902996 hasConceptScore W2950902996C61224824 @default.
- W2950902996 hasConceptScore W2950902996C89600930 @default.
- W2950902996 hasLocation W29509029961 @default.
- W2950902996 hasOpenAccess W2950902996 @default.
- W2950902996 hasPrimaryLocation W29509029961 @default.
- W2950902996 hasRelatedWork W1491051173 @default.
- W2950902996 hasRelatedWork W1501769036 @default.
- W2950902996 hasRelatedWork W1511424638 @default.
- W2950902996 hasRelatedWork W1514038321 @default.
- W2950902996 hasRelatedWork W1559619288 @default.
- W2950902996 hasRelatedWork W1644388879 @default.
- W2950902996 hasRelatedWork W1980243515 @default.
- W2950902996 hasRelatedWork W1992192543 @default.
- W2950902996 hasRelatedWork W2011365573 @default.
- W2950902996 hasRelatedWork W2081425135 @default.
- W2950902996 hasRelatedWork W2110872054 @default.
- W2950902996 hasRelatedWork W2113472920 @default.
- W2950902996 hasRelatedWork W2129212445 @default.
- W2950902996 hasRelatedWork W2139998199 @default.
- W2950902996 hasRelatedWork W2165902556 @default.
- W2950902996 hasRelatedWork W2250899144 @default.
- W2950902996 hasRelatedWork W2607545421 @default.
- W2950902996 hasRelatedWork W2759706418 @default.
- W2950902996 hasRelatedWork W2951977119 @default.
- W2950902996 hasRelatedWork W2963434812 @default.
- W2950902996 isParatext "false" @default.
- W2950902996 isRetracted "false" @default.
- W2950902996 magId "2950902996" @default.
- W2950902996 workType "article" @default.