Matches in SemOpenAlex for { <https://semopenalex.org/work/W2803086176> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2803086176 endingPage "1463" @default.
- W2803086176 startingPage "1454" @default.
- W2803086176 abstract "In this paper, we present a new deep learning framework for 3-D tomographic reconstruction. To this end, we map filtered back-projection-type algorithms to neural networks. However, the back-projection cannot be implemented as a fully connected layer due to its memory requirements. To overcome this problem, we propose a new type of cone-beam back-projection layer, efficiently calculating the forward pass. We derive this layer's backward pass as a projection operation. Unlike most deep learning approaches for reconstruction, our new layer permits joint optimization of correction steps in volume and projection domain. Evaluation is performed numerically on a public data set in a limited angle setting showing a consistent improvement over analytical algorithms while keeping the same computational test-time complexity by design. In the region of interest, the peak signal-to-noise ratio has increased by 23%. In addition, we show that the learned algorithm can be interpreted using known concepts from cone beam reconstruction: the network is able to automatically learn strategies such as compensation weights and apodization windows." @default.
- W2803086176 created "2018-05-17" @default.
- W2803086176 creator A5020211325 @default.
- W2803086176 creator A5025681380 @default.
- W2803086176 creator A5030367033 @default.
- W2803086176 creator A5046060326 @default.
- W2803086176 creator A5073209088 @default.
- W2803086176 creator A5087093169 @default.
- W2803086176 creator A5087095414 @default.
- W2803086176 date "2018-06-01" @default.
- W2803086176 modified "2023-10-04" @default.
- W2803086176 title "Deep Learning Computed Tomography: Learning Projection-Domain Weights From Image Domain in Limited Angle Problems" @default.
- W2803086176 cites W1868831826 @default.
- W2803086176 cites W1970163214 @default.
- W2803086176 cites W2023749508 @default.
- W2803086176 cites W2031572482 @default.
- W2803086176 cites W2035895659 @default.
- W2803086176 cites W2080924368 @default.
- W2803086176 cites W2098239148 @default.
- W2803086176 cites W2119300750 @default.
- W2803086176 cites W2133665775 @default.
- W2803086176 cites W2134999791 @default.
- W2803086176 cites W2171141876 @default.
- W2803086176 cites W2318872361 @default.
- W2803086176 cites W2520016695 @default.
- W2803086176 cites W2581082771 @default.
- W2803086176 cites W2593035862 @default.
- W2803086176 cites W2963653931 @default.
- W2803086176 cites W3101765447 @default.
- W2803086176 cites W3104324122 @default.
- W2803086176 doi "https://doi.org/10.1109/tmi.2018.2833499" @default.
- W2803086176 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29870373" @default.
- W2803086176 hasPublicationYear "2018" @default.
- W2803086176 type Work @default.
- W2803086176 sameAs 2803086176 @default.
- W2803086176 citedByCount "164" @default.
- W2803086176 countsByYear W28030861762018 @default.
- W2803086176 countsByYear W28030861762019 @default.
- W2803086176 countsByYear W28030861762020 @default.
- W2803086176 countsByYear W28030861762021 @default.
- W2803086176 countsByYear W28030861762022 @default.
- W2803086176 countsByYear W28030861762023 @default.
- W2803086176 crossrefType "journal-article" @default.
- W2803086176 hasAuthorship W2803086176A5020211325 @default.
- W2803086176 hasAuthorship W2803086176A5025681380 @default.
- W2803086176 hasAuthorship W2803086176A5030367033 @default.
- W2803086176 hasAuthorship W2803086176A5046060326 @default.
- W2803086176 hasAuthorship W2803086176A5073209088 @default.
- W2803086176 hasAuthorship W2803086176A5087093169 @default.
- W2803086176 hasAuthorship W2803086176A5087095414 @default.
- W2803086176 hasConcept C108583219 @default.
- W2803086176 hasConcept C11413529 @default.
- W2803086176 hasConcept C134306372 @default.
- W2803086176 hasConcept C141379421 @default.
- W2803086176 hasConcept C154945302 @default.
- W2803086176 hasConcept C197231052 @default.
- W2803086176 hasConcept C31972630 @default.
- W2803086176 hasConcept C33923547 @default.
- W2803086176 hasConcept C36503486 @default.
- W2803086176 hasConcept C41008148 @default.
- W2803086176 hasConcept C50644808 @default.
- W2803086176 hasConcept C57493831 @default.
- W2803086176 hasConcept C97742081 @default.
- W2803086176 hasConceptScore W2803086176C108583219 @default.
- W2803086176 hasConceptScore W2803086176C11413529 @default.
- W2803086176 hasConceptScore W2803086176C134306372 @default.
- W2803086176 hasConceptScore W2803086176C141379421 @default.
- W2803086176 hasConceptScore W2803086176C154945302 @default.
- W2803086176 hasConceptScore W2803086176C197231052 @default.
- W2803086176 hasConceptScore W2803086176C31972630 @default.
- W2803086176 hasConceptScore W2803086176C33923547 @default.
- W2803086176 hasConceptScore W2803086176C36503486 @default.
- W2803086176 hasConceptScore W2803086176C41008148 @default.
- W2803086176 hasConceptScore W2803086176C50644808 @default.
- W2803086176 hasConceptScore W2803086176C57493831 @default.
- W2803086176 hasConceptScore W2803086176C97742081 @default.
- W2803086176 hasFunder F4320337363 @default.
- W2803086176 hasIssue "6" @default.
- W2803086176 hasLocation W28030861761 @default.
- W2803086176 hasLocation W28030861762 @default.
- W2803086176 hasOpenAccess W2803086176 @default.
- W2803086176 hasPrimaryLocation W28030861761 @default.
- W2803086176 hasRelatedWork W1484307171 @default.
- W2803086176 hasRelatedWork W2031711888 @default.
- W2803086176 hasRelatedWork W2085090764 @default.
- W2803086176 hasRelatedWork W2345851064 @default.
- W2803086176 hasRelatedWork W2473840714 @default.
- W2803086176 hasRelatedWork W2969336654 @default.
- W2803086176 hasRelatedWork W3140649175 @default.
- W2803086176 hasRelatedWork W4200181155 @default.
- W2803086176 hasRelatedWork W4296061934 @default.
- W2803086176 hasRelatedWork W628413776 @default.
- W2803086176 hasVolume "37" @default.
- W2803086176 isParatext "false" @default.
- W2803086176 isRetracted "false" @default.
- W2803086176 magId "2803086176" @default.
- W2803086176 workType "article" @default.