Matches in SemOpenAlex for { <https://semopenalex.org/work/W3093430047> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3093430047 abstract "Ambiguity is inevitable in medical images, which often results in different image interpretations (e.g. object boundaries or segmentation maps) from different human experts. Thus, a model that learns the ambiguity and outputs a probability distribution of the target, would be valuable for medical applications to assess the uncertainty of diagnosis. In this paper, we propose a powerful generative model to learn a representation of ambiguity and to generate probabilistic outputs. Our model, named Coordinate Quantization Variational Autoencoder (CQ-VAE) employs a discrete latent space with an internal discrete probability distribution by quantizing the coordinates of a continuous latent space. As a result, the output distribution from CQ-VAE is discrete. During training, Gumbel-Softmax sampling is used to enable backpropagation through the discrete latent space. A matching algorithm is used to establish the correspondence between model-generated samples and ground-truth samples, which makes a trade-off between the ability to generate new samples and the ability to represent training samples. Besides these probabilistic components to generate possible outputs, our model has a deterministic path to output the best estimation. We demonstrated our method on a lumbar disk image dataset, and the results show that our CQ-VAE can learn lumbar disk shape variation and uncertainty." @default.
- W3093430047 created "2020-10-22" @default.
- W3093430047 creator A5004156323 @default.
- W3093430047 creator A5015975510 @default.
- W3093430047 creator A5040829949 @default.
- W3093430047 creator A5046293249 @default.
- W3093430047 creator A5067242485 @default.
- W3093430047 date "2020-10-17" @default.
- W3093430047 modified "2023-09-23" @default.
- W3093430047 title "CQ-VAE: Coordinate Quantized VAE for Uncertainty Estimation with Application to Disk Shape Analysis from Lumbar Spine MRI Images" @default.
- W3093430047 cites W2000814501 @default.
- W3093430047 cites W2519430864 @default.
- W3093430047 cites W2547875792 @default.
- W3093430047 cites W2604944342 @default.
- W3093430047 cites W2770937706 @default.
- W3093430047 cites W2807414627 @default.
- W3093430047 cites W2891116995 @default.
- W3093430047 cites W2945559256 @default.
- W3093430047 cites W2951004968 @default.
- W3093430047 cites W2963632741 @default.
- W3093430047 cites W2963799213 @default.
- W3093430047 cites W2968131493 @default.
- W3093430047 hasPublicationYear "2020" @default.
- W3093430047 type Work @default.
- W3093430047 sameAs 3093430047 @default.
- W3093430047 citedByCount "0" @default.
- W3093430047 crossrefType "posted-content" @default.
- W3093430047 hasAuthorship W3093430047A5004156323 @default.
- W3093430047 hasAuthorship W3093430047A5015975510 @default.
- W3093430047 hasAuthorship W3093430047A5040829949 @default.
- W3093430047 hasAuthorship W3093430047A5046293249 @default.
- W3093430047 hasAuthorship W3093430047A5067242485 @default.
- W3093430047 hasConcept C105795698 @default.
- W3093430047 hasConcept C108583219 @default.
- W3093430047 hasConcept C149441793 @default.
- W3093430047 hasConcept C153180895 @default.
- W3093430047 hasConcept C154945302 @default.
- W3093430047 hasConcept C167966045 @default.
- W3093430047 hasConcept C188441871 @default.
- W3093430047 hasConcept C199360897 @default.
- W3093430047 hasConcept C2780522230 @default.
- W3093430047 hasConcept C31972630 @default.
- W3093430047 hasConcept C33923547 @default.
- W3093430047 hasConcept C39890363 @default.
- W3093430047 hasConcept C41008148 @default.
- W3093430047 hasConcept C49937458 @default.
- W3093430047 hasConcept C51167844 @default.
- W3093430047 hasConcept C89600930 @default.
- W3093430047 hasConceptScore W3093430047C105795698 @default.
- W3093430047 hasConceptScore W3093430047C108583219 @default.
- W3093430047 hasConceptScore W3093430047C149441793 @default.
- W3093430047 hasConceptScore W3093430047C153180895 @default.
- W3093430047 hasConceptScore W3093430047C154945302 @default.
- W3093430047 hasConceptScore W3093430047C167966045 @default.
- W3093430047 hasConceptScore W3093430047C188441871 @default.
- W3093430047 hasConceptScore W3093430047C199360897 @default.
- W3093430047 hasConceptScore W3093430047C2780522230 @default.
- W3093430047 hasConceptScore W3093430047C31972630 @default.
- W3093430047 hasConceptScore W3093430047C33923547 @default.
- W3093430047 hasConceptScore W3093430047C39890363 @default.
- W3093430047 hasConceptScore W3093430047C41008148 @default.
- W3093430047 hasConceptScore W3093430047C49937458 @default.
- W3093430047 hasConceptScore W3093430047C51167844 @default.
- W3093430047 hasConceptScore W3093430047C89600930 @default.
- W3093430047 hasOpenAccess W3093430047 @default.
- W3093430047 hasRelatedWork W180112536 @default.
- W3093430047 hasRelatedWork W1971281902 @default.
- W3093430047 hasRelatedWork W1996561948 @default.
- W3093430047 hasRelatedWork W2010277206 @default.
- W3093430047 hasRelatedWork W2115823281 @default.
- W3093430047 hasRelatedWork W2152374763 @default.
- W3093430047 hasRelatedWork W2186610865 @default.
- W3093430047 hasRelatedWork W2271070614 @default.
- W3093430047 hasRelatedWork W2531529435 @default.
- W3093430047 hasRelatedWork W2611832709 @default.
- W3093430047 hasRelatedWork W2767633599 @default.
- W3093430047 hasRelatedWork W2968518909 @default.
- W3093430047 hasRelatedWork W2999550516 @default.
- W3093430047 hasRelatedWork W3018086778 @default.
- W3093430047 hasRelatedWork W3083387921 @default.
- W3093430047 hasRelatedWork W3090285375 @default.
- W3093430047 hasRelatedWork W3093392184 @default.
- W3093430047 hasRelatedWork W3112593495 @default.
- W3093430047 hasRelatedWork W3120704692 @default.
- W3093430047 hasRelatedWork W3132744937 @default.
- W3093430047 isParatext "false" @default.
- W3093430047 isRetracted "false" @default.
- W3093430047 magId "3093430047" @default.
- W3093430047 workType "article" @default.