Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890130458> ?p ?o ?g. }
- W2890130458 abstract "Convolutional neural networks have advanced the state of the art in medical image segmentation. However, there are two challenges in 3D deep learning segmentation networks. First, the segmentation masks from deep learning networks lack shape constraints, often resulting in the need for post-processing. Second, the training and deployment of 3D networks require substantial memory resources. The memory requirement becomes an issue especially when the target organs cover a large footprint. Commonly down-sampling and up-sampling operations are needed before and after the network. To address the post-processing requirement, we present a new loss function that incorporates the level set based smoothing loss together with multi Dice loss to avoid an additional post processing step. The formulation is general and can accommodate other deformable shape models. Further, we propose a way to integrate the down- and up-sampling in the network such that the input of the deep learning network can work directly on the original image without a significant increase in the memory usage. The 3D segmentation network with the proposed loss and sampling approach shows promising results on a dataset of 48 chest CT angiography images with 16 target anatomies. We obtained average Dice of 79.5% in 4 fold cross validation." @default.
- W2890130458 created "2018-09-27" @default.
- W2890130458 creator A5010388971 @default.
- W2890130458 creator A5024350063 @default.
- W2890130458 creator A5049301997 @default.
- W2890130458 creator A5057284370 @default.
- W2890130458 creator A5066182705 @default.
- W2890130458 creator A5082167522 @default.
- W2890130458 date "2018-01-01" @default.
- W2890130458 modified "2023-09-24" @default.
- W2890130458 title "Integrating Deformable Modeling with 3D Deep Neural Network Segmentation" @default.
- W2890130458 cites W1991113069 @default.
- W2890130458 cites W2160956336 @default.
- W2890130458 cites W2301358467 @default.
- W2890130458 cites W2357815549 @default.
- W2890130458 cites W2464708700 @default.
- W2890130458 cites W2555096873 @default.
- W2890130458 cites W2616240092 @default.
- W2890130458 cites W2674447025 @default.
- W2890130458 cites W2740652190 @default.
- W2890130458 cites W2791680898 @default.
- W2890130458 cites W2806692427 @default.
- W2890130458 cites W2962914239 @default.
- W2890130458 doi "https://doi.org/10.1007/978-3-030-00889-5_43" @default.
- W2890130458 hasPublicationYear "2018" @default.
- W2890130458 type Work @default.
- W2890130458 sameAs 2890130458 @default.
- W2890130458 citedByCount "3" @default.
- W2890130458 countsByYear W28901304582018 @default.
- W2890130458 countsByYear W28901304582019 @default.
- W2890130458 countsByYear W28901304582020 @default.
- W2890130458 crossrefType "book-chapter" @default.
- W2890130458 hasAuthorship W2890130458A5010388971 @default.
- W2890130458 hasAuthorship W2890130458A5024350063 @default.
- W2890130458 hasAuthorship W2890130458A5049301997 @default.
- W2890130458 hasAuthorship W2890130458A5057284370 @default.
- W2890130458 hasAuthorship W2890130458A5066182705 @default.
- W2890130458 hasAuthorship W2890130458A5082167522 @default.
- W2890130458 hasConcept C106131492 @default.
- W2890130458 hasConcept C108583219 @default.
- W2890130458 hasConcept C111919701 @default.
- W2890130458 hasConcept C119857082 @default.
- W2890130458 hasConcept C124504099 @default.
- W2890130458 hasConcept C140779682 @default.
- W2890130458 hasConcept C153180895 @default.
- W2890130458 hasConcept C154945302 @default.
- W2890130458 hasConcept C22029948 @default.
- W2890130458 hasConcept C2524010 @default.
- W2890130458 hasConcept C31972630 @default.
- W2890130458 hasConcept C33923547 @default.
- W2890130458 hasConcept C3770464 @default.
- W2890130458 hasConcept C41008148 @default.
- W2890130458 hasConcept C50644808 @default.
- W2890130458 hasConcept C74912251 @default.
- W2890130458 hasConcept C81363708 @default.
- W2890130458 hasConcept C89600930 @default.
- W2890130458 hasConceptScore W2890130458C106131492 @default.
- W2890130458 hasConceptScore W2890130458C108583219 @default.
- W2890130458 hasConceptScore W2890130458C111919701 @default.
- W2890130458 hasConceptScore W2890130458C119857082 @default.
- W2890130458 hasConceptScore W2890130458C124504099 @default.
- W2890130458 hasConceptScore W2890130458C140779682 @default.
- W2890130458 hasConceptScore W2890130458C153180895 @default.
- W2890130458 hasConceptScore W2890130458C154945302 @default.
- W2890130458 hasConceptScore W2890130458C22029948 @default.
- W2890130458 hasConceptScore W2890130458C2524010 @default.
- W2890130458 hasConceptScore W2890130458C31972630 @default.
- W2890130458 hasConceptScore W2890130458C33923547 @default.
- W2890130458 hasConceptScore W2890130458C3770464 @default.
- W2890130458 hasConceptScore W2890130458C41008148 @default.
- W2890130458 hasConceptScore W2890130458C50644808 @default.
- W2890130458 hasConceptScore W2890130458C74912251 @default.
- W2890130458 hasConceptScore W2890130458C81363708 @default.
- W2890130458 hasConceptScore W2890130458C89600930 @default.
- W2890130458 hasLocation W28901304581 @default.
- W2890130458 hasOpenAccess W2890130458 @default.
- W2890130458 hasPrimaryLocation W28901304581 @default.
- W2890130458 hasRelatedWork W2515791897 @default.
- W2890130458 hasRelatedWork W2751436279 @default.
- W2890130458 hasRelatedWork W2806818134 @default.
- W2890130458 hasRelatedWork W2810644003 @default.
- W2890130458 hasRelatedWork W2893045060 @default.
- W2890130458 hasRelatedWork W2903013553 @default.
- W2890130458 hasRelatedWork W2912546698 @default.
- W2890130458 hasRelatedWork W2922462327 @default.
- W2890130458 hasRelatedWork W2965682404 @default.
- W2890130458 hasRelatedWork W2966249696 @default.
- W2890130458 hasRelatedWork W2979600871 @default.
- W2890130458 hasRelatedWork W3003425036 @default.
- W2890130458 hasRelatedWork W3006169930 @default.
- W2890130458 hasRelatedWork W3023772698 @default.
- W2890130458 hasRelatedWork W3041083211 @default.
- W2890130458 hasRelatedWork W3042127584 @default.
- W2890130458 hasRelatedWork W3044038196 @default.
- W2890130458 hasRelatedWork W3097615406 @default.
- W2890130458 hasRelatedWork W3175554448 @default.
- W2890130458 hasRelatedWork W3112976032 @default.
- W2890130458 isParatext "false" @default.
- W2890130458 isRetracted "false" @default.
- W2890130458 magId "2890130458" @default.