Matches in SemOpenAlex for { <https://semopenalex.org/work/W2809550384> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2809550384 abstract "Convolutional networks have become state-of-the-art techniques for automatic medical image analysis, with the U-net architecture being the most popular at this moment. In this article we report the application of a 3D version of U-net to the automatic segmentation of prostate peripheral and transition zones in 3D MRI images. Our results are slightly better than recent studies that used 2D U-net and handcrafted feature approaches. In addition, we test ideas for improving the 3D U-net setup, by 1) letting the network segment surrounding tissues, making use of the fixed anatomy, and 2) adjusting the network architecture to reflect the anisotropy in the dimensions of the MRI image volumes. While the latter adjustment gave a marginal improvement, the former adjustment showed a significant deterioration of the network performance. We were able to explain this deterioration by inspecting feature map activations in all layers of the network. We show that to segment more tissues the network replaces feature maps that were dedicated to detecting prostate peripheral zones, by feature maps detecting the surrounding tissues." @default.
- W2809550384 created "2018-06-29" @default.
- W2809550384 creator A5049622369 @default.
- W2809550384 creator A5054345200 @default.
- W2809550384 creator A5090469916 @default.
- W2809550384 date "2018-06-19" @default.
- W2809550384 modified "2023-09-26" @default.
- W2809550384 title "Automatic segmentation of prostate zones" @default.
- W2809550384 cites W1901129140 @default.
- W2809550384 cites W2106033751 @default.
- W2809550384 cites W2132241724 @default.
- W2809550384 cites W2432481613 @default.
- W2809550384 cites W2464708700 @default.
- W2809550384 hasPublicationYear "2018" @default.
- W2809550384 type Work @default.
- W2809550384 sameAs 2809550384 @default.
- W2809550384 citedByCount "3" @default.
- W2809550384 countsByYear W28095503842019 @default.
- W2809550384 countsByYear W28095503842021 @default.
- W2809550384 crossrefType "posted-content" @default.
- W2809550384 hasAuthorship W2809550384A5049622369 @default.
- W2809550384 hasAuthorship W2809550384A5054345200 @default.
- W2809550384 hasAuthorship W2809550384A5090469916 @default.
- W2809550384 hasConcept C108583219 @default.
- W2809550384 hasConcept C115961682 @default.
- W2809550384 hasConcept C121608353 @default.
- W2809550384 hasConcept C126322002 @default.
- W2809550384 hasConcept C138885662 @default.
- W2809550384 hasConcept C14166107 @default.
- W2809550384 hasConcept C153180895 @default.
- W2809550384 hasConcept C154945302 @default.
- W2809550384 hasConcept C193415008 @default.
- W2809550384 hasConcept C2524010 @default.
- W2809550384 hasConcept C2776235491 @default.
- W2809550384 hasConcept C2776401178 @default.
- W2809550384 hasConcept C31972630 @default.
- W2809550384 hasConcept C33923547 @default.
- W2809550384 hasConcept C38652104 @default.
- W2809550384 hasConcept C41008148 @default.
- W2809550384 hasConcept C41895202 @default.
- W2809550384 hasConcept C71924100 @default.
- W2809550384 hasConcept C89600930 @default.
- W2809550384 hasConceptScore W2809550384C108583219 @default.
- W2809550384 hasConceptScore W2809550384C115961682 @default.
- W2809550384 hasConceptScore W2809550384C121608353 @default.
- W2809550384 hasConceptScore W2809550384C126322002 @default.
- W2809550384 hasConceptScore W2809550384C138885662 @default.
- W2809550384 hasConceptScore W2809550384C14166107 @default.
- W2809550384 hasConceptScore W2809550384C153180895 @default.
- W2809550384 hasConceptScore W2809550384C154945302 @default.
- W2809550384 hasConceptScore W2809550384C193415008 @default.
- W2809550384 hasConceptScore W2809550384C2524010 @default.
- W2809550384 hasConceptScore W2809550384C2776235491 @default.
- W2809550384 hasConceptScore W2809550384C2776401178 @default.
- W2809550384 hasConceptScore W2809550384C31972630 @default.
- W2809550384 hasConceptScore W2809550384C33923547 @default.
- W2809550384 hasConceptScore W2809550384C38652104 @default.
- W2809550384 hasConceptScore W2809550384C41008148 @default.
- W2809550384 hasConceptScore W2809550384C41895202 @default.
- W2809550384 hasConceptScore W2809550384C71924100 @default.
- W2809550384 hasConceptScore W2809550384C89600930 @default.
- W2809550384 hasLocation W28095503841 @default.
- W2809550384 hasOpenAccess W2809550384 @default.
- W2809550384 hasPrimaryLocation W28095503841 @default.
- W2809550384 hasRelatedWork W1661454636 @default.
- W2809550384 hasRelatedWork W1827911007 @default.
- W2809550384 hasRelatedWork W1901129140 @default.
- W2809550384 hasRelatedWork W2568526264 @default.
- W2809550384 hasRelatedWork W2766076071 @default.
- W2809550384 hasRelatedWork W2890732316 @default.
- W2809550384 hasRelatedWork W2897778443 @default.
- W2809550384 hasRelatedWork W2913844953 @default.
- W2809550384 hasRelatedWork W2993184403 @default.
- W2809550384 hasRelatedWork W2998718901 @default.
- W2809550384 hasRelatedWork W3081623163 @default.
- W2809550384 hasRelatedWork W3097329159 @default.
- W2809550384 hasRelatedWork W3100369519 @default.
- W2809550384 hasRelatedWork W3100708836 @default.
- W2809550384 hasRelatedWork W3119260780 @default.
- W2809550384 hasRelatedWork W3168601957 @default.
- W2809550384 hasRelatedWork W3170231947 @default.
- W2809550384 hasRelatedWork W3173589586 @default.
- W2809550384 hasRelatedWork W3176384940 @default.
- W2809550384 hasRelatedWork W3208128414 @default.
- W2809550384 isParatext "false" @default.
- W2809550384 isRetracted "false" @default.
- W2809550384 magId "2809550384" @default.
- W2809550384 workType "article" @default.