Matches in SemOpenAlex for { <https://semopenalex.org/work/W2901926849> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2901926849 abstract "Accurate localization and segmentation of intervertebral disc (IVD) is crucial for the assessment of spine disease diagnosis. Despite the technological advances in medical imaging, IVD localization and segmentation are still manually performed, which is time-consuming and prone to errors. If, in addition, multi-modal imaging is considered, the burden imposed on disease assessments increases substantially. In this paper, we propose an architecture for IVD localization and segmentation in multi-modal MRI, which extends the well-known UNet. Compared to single images, multi-modal data brings complementary information, contributing to better data representation and discriminative power. Our contributions are three-fold. First, how to effectively integrate and fully leverage multi-modal data remains almost unexplored. In this work, each MRI modality is processed in a different path to better exploit their unique information. Second, inspired by HyperDenseNet, the network is densely-connected both within each path and across different paths, granting the model the freedom to learn where and how the different modalities should be processed and combined. Third, we improved standard U-Net modules by extending inception modules with two dilated convolutions blocks of different scale, which helps handling multi-scale context. We report experiments over the data set of the public MICCAI 2018 Challenge on Automatic Intervertebral Disc Localization and Segmentation, with 13 multi-modal MRI images used for training and 3 for validation. We trained IVD-Net on an NVidia TITAN XP GPU with 16 GBs RAM, using ADAM as optimizer and a learning rate of 10e-5 during 200 epochs. Training took about 5 hours, and segmentation of a whole volume about 2-3 seconds, on average. Several baselines, with different multi-modal fusion strategies, were used to demonstrate the effectiveness of the proposed architecture." @default.
- W2901926849 created "2018-11-29" @default.
- W2901926849 creator A5004770604 @default.
- W2901926849 creator A5017608284 @default.
- W2901926849 creator A5053292735 @default.
- W2901926849 date "2018-11-19" @default.
- W2901926849 modified "2023-09-25" @default.
- W2901926849 title "IVD-Net: Intervertebral disc localization and segmentation in MRI with a multi-modal UNet." @default.
- W2901926849 cites W133787854 @default.
- W2901926849 cites W154472438 @default.
- W2901926849 cites W1901129140 @default.
- W2901926849 cites W2082526668 @default.
- W2901926849 cites W2099321744 @default.
- W2901926849 cites W2183341477 @default.
- W2901926849 cites W2441649867 @default.
- W2901926849 cites W2518297742 @default.
- W2901926849 cites W2592412568 @default.
- W2901926849 cites W2766785165 @default.
- W2901926849 cites W2775394473 @default.
- W2901926849 cites W2778955544 @default.
- W2901926849 cites W2791533555 @default.
- W2901926849 cites W2792023360 @default.
- W2901926849 cites W2889625240 @default.
- W2901926849 cites W2890419922 @default.
- W2901926849 cites W2950863783 @default.
- W2901926849 cites W2963120588 @default.
- W2901926849 cites W2963125010 @default.
- W2901926849 cites W2963446712 @default.
- W2901926849 cites W2963840672 @default.
- W2901926849 hasPublicationYear "2018" @default.
- W2901926849 type Work @default.
- W2901926849 sameAs 2901926849 @default.
- W2901926849 citedByCount "0" @default.
- W2901926849 crossrefType "posted-content" @default.
- W2901926849 hasAuthorship W2901926849A5004770604 @default.
- W2901926849 hasAuthorship W2901926849A5017608284 @default.
- W2901926849 hasAuthorship W2901926849A5053292735 @default.
- W2901926849 hasConcept C126838900 @default.
- W2901926849 hasConcept C151730666 @default.
- W2901926849 hasConcept C153083717 @default.
- W2901926849 hasConcept C153180895 @default.
- W2901926849 hasConcept C154945302 @default.
- W2901926849 hasConcept C185592680 @default.
- W2901926849 hasConcept C188027245 @default.
- W2901926849 hasConcept C2777755357 @default.
- W2901926849 hasConcept C2779343474 @default.
- W2901926849 hasConcept C31601959 @default.
- W2901926849 hasConcept C31972630 @default.
- W2901926849 hasConcept C41008148 @default.
- W2901926849 hasConcept C71139939 @default.
- W2901926849 hasConcept C71924100 @default.
- W2901926849 hasConcept C86803240 @default.
- W2901926849 hasConcept C89600930 @default.
- W2901926849 hasConcept C97931131 @default.
- W2901926849 hasConceptScore W2901926849C126838900 @default.
- W2901926849 hasConceptScore W2901926849C151730666 @default.
- W2901926849 hasConceptScore W2901926849C153083717 @default.
- W2901926849 hasConceptScore W2901926849C153180895 @default.
- W2901926849 hasConceptScore W2901926849C154945302 @default.
- W2901926849 hasConceptScore W2901926849C185592680 @default.
- W2901926849 hasConceptScore W2901926849C188027245 @default.
- W2901926849 hasConceptScore W2901926849C2777755357 @default.
- W2901926849 hasConceptScore W2901926849C2779343474 @default.
- W2901926849 hasConceptScore W2901926849C31601959 @default.
- W2901926849 hasConceptScore W2901926849C31972630 @default.
- W2901926849 hasConceptScore W2901926849C41008148 @default.
- W2901926849 hasConceptScore W2901926849C71139939 @default.
- W2901926849 hasConceptScore W2901926849C71924100 @default.
- W2901926849 hasConceptScore W2901926849C86803240 @default.
- W2901926849 hasConceptScore W2901926849C89600930 @default.
- W2901926849 hasConceptScore W2901926849C97931131 @default.
- W2901926849 hasLocation W29019268491 @default.
- W2901926849 hasOpenAccess W2901926849 @default.
- W2901926849 hasPrimaryLocation W29019268491 @default.
- W2901926849 hasRelatedWork W2594097440 @default.
- W2901926849 hasRelatedWork W2784280518 @default.
- W2901926849 hasRelatedWork W2791543691 @default.
- W2901926849 hasRelatedWork W2921650695 @default.
- W2901926849 hasRelatedWork W2922059535 @default.
- W2901926849 hasRelatedWork W2958862109 @default.
- W2901926849 hasRelatedWork W2963931909 @default.
- W2901926849 hasRelatedWork W2964702684 @default.
- W2901926849 hasRelatedWork W3001164942 @default.
- W2901926849 hasRelatedWork W3080830962 @default.
- W2901926849 hasRelatedWork W3083561211 @default.
- W2901926849 hasRelatedWork W3094156580 @default.
- W2901926849 hasRelatedWork W3140422664 @default.
- W2901926849 hasRelatedWork W3150559585 @default.
- W2901926849 hasRelatedWork W3176440633 @default.
- W2901926849 hasRelatedWork W3189766340 @default.
- W2901926849 hasRelatedWork W3192535210 @default.
- W2901926849 hasRelatedWork W3201951169 @default.
- W2901926849 hasRelatedWork W3211488937 @default.
- W2901926849 hasRelatedWork W4225887539 @default.
- W2901926849 isParatext "false" @default.
- W2901926849 isRetracted "false" @default.
- W2901926849 magId "2901926849" @default.
- W2901926849 workType "article" @default.