Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307038408> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4307038408 endingPage "101111" @default.
- W4307038408 startingPage "101111" @default.
- W4307038408 abstract "Deep Learning is providing new solutions for medical image segmentation problems and becomes a key point for future clinical application. The study of vascular structures is a challenging task due to the extremely small size of the vessel structure, low SNR, and varying contrast in medical image data. In this study, we present an end-to-end deep learning segmentation method relying on the integration of vessel enhancement filters inside a 3-D U-Net based architecture. In particular, the raw data used in the learning process -or used as input- is preprocessed using these filters. The use of vesselness filters can significantly improve the contrast in raw images; this step can also help to improve segmentation decision especially on bifurcations. 3-D U-Net, Dense U-Net and MultiRes U-Net are pitted against each other in the vessel segmentation task with the public IRCAD dataset. Considering the integration of vesselness filters, the model parameters were optimized in order to identify the optimal configuration for fully automatic segmentation of hepatic vessels. In addition the three architectures were tested on full 3-D images and slabs (stacks of 2-D slices). The results showed that the most accurate setup is the full 3-D process, which provides the highest Dice for most of the considered models. The 3-D Dense U-Net also gives the best results compared to other models with or without vessel enhancement filters." @default.
- W4307038408 created "2022-10-23" @default.
- W4307038408 creator A5004052727 @default.
- W4307038408 creator A5032782542 @default.
- W4307038408 creator A5070742303 @default.
- W4307038408 creator A5079861120 @default.
- W4307038408 date "2022-01-01" @default.
- W4307038408 modified "2023-10-08" @default.
- W4307038408 title "Robust deep 3-D architectures based on vascular patterns for liver vessel segmentation" @default.
- W4307038408 cites W2345194886 @default.
- W4307038408 cites W2488305974 @default.
- W4307038408 cites W2590120901 @default.
- W4307038408 cites W2763233973 @default.
- W4307038408 cites W2888011474 @default.
- W4307038408 cites W2899097654 @default.
- W4307038408 cites W2928133111 @default.
- W4307038408 cites W2943580940 @default.
- W4307038408 cites W2947448622 @default.
- W4307038408 cites W2978457402 @default.
- W4307038408 cites W2996290406 @default.
- W4307038408 cites W4213029887 @default.
- W4307038408 doi "https://doi.org/10.1016/j.imu.2022.101111" @default.
- W4307038408 hasPublicationYear "2022" @default.
- W4307038408 type Work @default.
- W4307038408 citedByCount "2" @default.
- W4307038408 countsByYear W43070384082023 @default.
- W4307038408 crossrefType "journal-article" @default.
- W4307038408 hasAuthorship W4307038408A5004052727 @default.
- W4307038408 hasAuthorship W4307038408A5032782542 @default.
- W4307038408 hasAuthorship W4307038408A5070742303 @default.
- W4307038408 hasAuthorship W4307038408A5079861120 @default.
- W4307038408 hasBestOaLocation W43070384081 @default.
- W4307038408 hasConcept C106131492 @default.
- W4307038408 hasConcept C108583219 @default.
- W4307038408 hasConcept C111919701 @default.
- W4307038408 hasConcept C124504099 @default.
- W4307038408 hasConcept C127413603 @default.
- W4307038408 hasConcept C153180895 @default.
- W4307038408 hasConcept C154945302 @default.
- W4307038408 hasConcept C201995342 @default.
- W4307038408 hasConcept C22029948 @default.
- W4307038408 hasConcept C2524010 @default.
- W4307038408 hasConcept C2780451532 @default.
- W4307038408 hasConcept C31972630 @default.
- W4307038408 hasConcept C33923547 @default.
- W4307038408 hasConcept C41008148 @default.
- W4307038408 hasConcept C89600930 @default.
- W4307038408 hasConcept C98045186 @default.
- W4307038408 hasConceptScore W4307038408C106131492 @default.
- W4307038408 hasConceptScore W4307038408C108583219 @default.
- W4307038408 hasConceptScore W4307038408C111919701 @default.
- W4307038408 hasConceptScore W4307038408C124504099 @default.
- W4307038408 hasConceptScore W4307038408C127413603 @default.
- W4307038408 hasConceptScore W4307038408C153180895 @default.
- W4307038408 hasConceptScore W4307038408C154945302 @default.
- W4307038408 hasConceptScore W4307038408C201995342 @default.
- W4307038408 hasConceptScore W4307038408C22029948 @default.
- W4307038408 hasConceptScore W4307038408C2524010 @default.
- W4307038408 hasConceptScore W4307038408C2780451532 @default.
- W4307038408 hasConceptScore W4307038408C31972630 @default.
- W4307038408 hasConceptScore W4307038408C33923547 @default.
- W4307038408 hasConceptScore W4307038408C41008148 @default.
- W4307038408 hasConceptScore W4307038408C89600930 @default.
- W4307038408 hasConceptScore W4307038408C98045186 @default.
- W4307038408 hasFunder F4320320883 @default.
- W4307038408 hasLocation W43070384081 @default.
- W4307038408 hasOpenAccess W4307038408 @default.
- W4307038408 hasPrimaryLocation W43070384081 @default.
- W4307038408 hasRelatedWork W1669643531 @default.
- W4307038408 hasRelatedWork W2005437358 @default.
- W4307038408 hasRelatedWork W2008656436 @default.
- W4307038408 hasRelatedWork W2023558673 @default.
- W4307038408 hasRelatedWork W2110230079 @default.
- W4307038408 hasRelatedWork W2134924024 @default.
- W4307038408 hasRelatedWork W2517104666 @default.
- W4307038408 hasRelatedWork W2790662084 @default.
- W4307038408 hasRelatedWork W2960184797 @default.
- W4307038408 hasRelatedWork W4285827401 @default.
- W4307038408 hasVolume "34" @default.
- W4307038408 isParatext "false" @default.
- W4307038408 isRetracted "false" @default.
- W4307038408 workType "article" @default.