FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048238399> ?p ?o ?g. }

• W3048238399 abstract "Unsupervised deep-learning (DL) models were recently proposed for deformable image registration tasks. In such models, a neural-network is trained to predict the best deformation field by minimizing some dissimilarity function between the moving and the target images. After training on a dataset without reference deformation fields available, such a model can be used to rapidly predict the deformation field between newly seen moving and target images. Currently, the training process effectively provides a point-estimate of the network weights rather than characterizing their entire posterior distribution. This may result in a potential over-fitting which may yield sub-optimal results at inference phase, especially for small-size datasets, frequently present in the medical imaging domain. We introduce a fully Bayesian framework for unsupervised DL-based deformable image registration. Our method provides a principled way to characterize the true posterior distribution, thus, avoiding potential over-fitting. We used stochastic gradient Langevin dynamics (SGLD) to conduct the posterior sampling, which is both theoretically well-founded and computationally efficient. We demonstrated the added-value of our Basyesian unsupervised DL-based registration framework on the MNIST and brain MRI (MGH10) datasets in comparison to the VoxelMorph unsupervised DL-based image registration framework. Our experiments show that our approach provided better estimates of the deformation field by means of improved mean-squared-error ($0.0063$ vs. $0.0065$) and Dice coefficient ($0.73$ vs. $0.71$) for the MNIST and the MGH10 datasets respectively. Further, our approach provides an estimate of the uncertainty in the deformation-field by characterizing the true posterior distribution." @default.
• W3048238399 created "2020-08-13" @default.
• W3048238399 creator A5051033690 @default.
• W3048238399 creator A5089641146 @default.
• W3048238399 date "2020-08-10" @default.
• W3048238399 modified "2023-09-27" @default.
• W3048238399 title "Unsupervised Deep-Learning Based Deformable Image Registration: A Bayesian Framework" @default.
• W3048238399 cites W1522301498 @default.
• W3048238399 cites W18423312 @default.
• W3048238399 cites W1901129140 @default.
• W3048238399 cites W1970928383 @default.
• W3048238399 cites W1987869189 @default.
• W3048238399 cites W2007153649 @default.
• W3048238399 cites W2102099319 @default.
• W3048238399 cites W2111051539 @default.
• W3048238399 cites W2115167851 @default.
• W3048238399 cites W2140139548 @default.
• W3048238399 cites W2147555557 @default.
• W3048238399 cites W2155298532 @default.
• W3048238399 cites W2167433878 @default.
• W3048238399 cites W2170167891 @default.
• W3048238399 cites W2263490141 @default.
• W3048238399 cites W2271840356 @default.
• W3048238399 cites W2604920239 @default.
• W3048238399 cites W2891590469 @default.
• W3048238399 cites W2904555209 @default.
• W3048238399 cites W2922479016 @default.
• W3048238399 cites W2950561442 @default.
• W3048238399 cites W2963153890 @default.
• W3048238399 cites W2963383962 @default.
• W3048238399 cites W2964013315 @default.
• W3048238399 cites W2970493254 @default.
• W3048238399 cites W3098269293 @default.
• W3048238399 cites W3099561884 @default.
• W3048238399 hasPublicationYear "2020" @default.
• W3048238399 type Work @default.
• W3048238399 sameAs 3048238399 @default.
• W3048238399 citedByCount "1" @default.
• W3048238399 countsByYear W30482383992021 @default.
• W3048238399 crossrefType "posted-content" @default.
• W3048238399 hasAuthorship W3048238399A5051033690 @default.
• W3048238399 hasAuthorship W3048238399A5089641146 @default.
• W3048238399 hasConcept C107673813 @default.
• W3048238399 hasConcept C115961682 @default.
• W3048238399 hasConcept C119857082 @default.
• W3048238399 hasConcept C153180895 @default.
• W3048238399 hasConcept C154945302 @default.
• W3048238399 hasConcept C160234255 @default.
• W3048238399 hasConcept C166704113 @default.
• W3048238399 hasConcept C190502265 @default.
• W3048238399 hasConcept C202444582 @default.
• W3048238399 hasConcept C2776214188 @default.
• W3048238399 hasConcept C33923547 @default.
• W3048238399 hasConcept C41008148 @default.
• W3048238399 hasConcept C50644808 @default.
• W3048238399 hasConcept C57830394 @default.
• W3048238399 hasConcept C8038995 @default.
• W3048238399 hasConcept C9652623 @default.
• W3048238399 hasConceptScore W3048238399C107673813 @default.
• W3048238399 hasConceptScore W3048238399C115961682 @default.
• W3048238399 hasConceptScore W3048238399C119857082 @default.
• W3048238399 hasConceptScore W3048238399C153180895 @default.
• W3048238399 hasConceptScore W3048238399C154945302 @default.
• W3048238399 hasConceptScore W3048238399C160234255 @default.
• W3048238399 hasConceptScore W3048238399C166704113 @default.
• W3048238399 hasConceptScore W3048238399C190502265 @default.
• W3048238399 hasConceptScore W3048238399C202444582 @default.
• W3048238399 hasConceptScore W3048238399C2776214188 @default.
• W3048238399 hasConceptScore W3048238399C33923547 @default.
• W3048238399 hasConceptScore W3048238399C41008148 @default.
• W3048238399 hasConceptScore W3048238399C50644808 @default.
• W3048238399 hasConceptScore W3048238399C57830394 @default.
• W3048238399 hasConceptScore W3048238399C8038995 @default.
• W3048238399 hasConceptScore W3048238399C9652623 @default.
• W3048238399 hasLocation W30482383991 @default.
• W3048238399 hasOpenAccess W3048238399 @default.
• W3048238399 hasPrimaryLocation W30482383991 @default.
• W3048238399 hasRelatedWork W1479893190 @default.
• W3048238399 hasRelatedWork W1597642293 @default.
• W3048238399 hasRelatedWork W1688338525 @default.
• W3048238399 hasRelatedWork W1988942170 @default.
• W3048238399 hasRelatedWork W2169061716 @default.
• W3048238399 hasRelatedWork W2212870497 @default.
• W3048238399 hasRelatedWork W2503351305 @default.
• W3048238399 hasRelatedWork W2611832709 @default.
• W3048238399 hasRelatedWork W2898917755 @default.
• W3048238399 hasRelatedWork W2950500943 @default.
• W3048238399 hasRelatedWork W2953456263 @default.
• W3048238399 hasRelatedWork W2968518909 @default.
• W3048238399 hasRelatedWork W2988134392 @default.
• W3048238399 hasRelatedWork W2998809599 @default.
• W3048238399 hasRelatedWork W3013830789 @default.
• W3048238399 hasRelatedWork W3018086778 @default.
• W3048238399 hasRelatedWork W3120704692 @default.
• W3048238399 hasRelatedWork W3194042225 @default.
• W3048238399 hasRelatedWork W3206699992 @default.
• W3048238399 hasRelatedWork W834848241 @default.
• W3048238399 isParatext "false" @default.
• W3048238399 isRetracted "false" @default.
• W3048238399 magId "3048238399" @default.

• next