FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200558263> ?p ?o ?g. }

• W4200558263 endingPage "103442" @default.
• W4200558263 startingPage "103442" @default.
• W4200558263 abstract "• The MetricUNet method can effectively model inter-voxel relationships for learning of more context information of tumors. • The scale-adaptive metric loss is proposed for the brain tumor image whose target areas are with large variations in scale. • The super voxel-level feature is proposed to represent a group of voxel-level features (of the same label) in non-edge regions. It can reduce the computation to about 1/11 of the original MetricUNet and focus more attention on the edge regions that are difficult to segment. Accurate segmentation of brain tumors is very essential for brain tumor diagnosis and treatment plans. In general, brain tumor includes WT (whole tumor), TC (tumor core) and ET (enhance tumor), and TC and ET are much more important than WT clinically. However, TC and ET usually contain blurred boundaries, and occupy much fewer pixels than WT. Recently, MetricUNet based on voxel-metric learning is proposed, which considers voxel-level feature relationship in the image to obtain finer segmentation results. However, it may not be applicable in brain tumor segmentation. That is because the scales/sizes of brain tumor greatly vary between images and causing ineffective model training in MetricUNet. Moreover, it has heavy computation for considering voxel-level feature relationship in brain tumor segmentation. In this work, a Scale-adaptive Super-feature based MetricUNet (S2MetricUNet) is proposed and provides two advantages: i) higher accuracy on TC and ET since a novel scale-adaptive metric loss is proposed for learning of more context information about TC and ET while addressing the scale variation between images; ii) significant reduction on computation since a super voxel-level feature is proposed to represent a group of voxel-level features (of the same label) in non-edge regions. The experimental results on public dataset BraTS2019 have demonstrated that the improvement of our method is up to 3.38% on TC and 3.82% on ET in terms Dice. Moreover, the computation of our S2MetricUNet is reduced to about 1/11 of MetricUNet." @default.
• W4200558263 created "2021-12-31" @default.
• W4200558263 creator A5001212991 @default.
• W4200558263 creator A5020044312 @default.
• W4200558263 creator A5030883042 @default.
• W4200558263 creator A5046543349 @default.
• W4200558263 creator A5048331196 @default.
• W4200558263 creator A5069516330 @default.
• W4200558263 creator A5076922237 @default.
• W4200558263 creator A5086910766 @default.
• W4200558263 date "2022-03-01" @default.
• W4200558263 modified "2023-09-26" @default.
• W4200558263 title "Scale-adaptive super-feature based MetricUNet for brain tumor segmentation" @default.
• W4200558263 cites W1641498739 @default.
• W4200558263 cites W1884191083 @default.
• W4200558263 cites W1987869189 @default.
• W4200558263 cites W2301358467 @default.
• W4200558263 cites W2386703324 @default.
• W4200558263 cites W2412782625 @default.
• W4200558263 cites W2550409828 @default.
• W4200558263 cites W2744130673 @default.
• W4200558263 cites W2751069891 @default.
• W4200558263 cites W2774320778 @default.
• W4200558263 cites W2783946051 @default.
• W4200558263 cites W2888044560 @default.
• W4200558263 cites W2889147523 @default.
• W4200558263 cites W2950793747 @default.
• W4200558263 cites W2954704152 @default.
• W4200558263 cites W2971667786 @default.
• W4200558263 cites W2972200333 @default.
• W4200558263 cites W2988141759 @default.
• W4200558263 cites W2999945314 @default.
• W4200558263 cites W3009632017 @default.
• W4200558263 cites W3011995047 @default.
• W4200558263 cites W3017314222 @default.
• W4200558263 cites W3031224726 @default.
• W4200558263 cites W3037611653 @default.
• W4200558263 cites W3044256341 @default.
• W4200558263 cites W3046342815 @default.
• W4200558263 cites W3047597044 @default.
• W4200558263 cites W3086505308 @default.
• W4200558263 cites W3099206234 @default.
• W4200558263 cites W3112701542 @default.
• W4200558263 cites W3117765623 @default.
• W4200558263 cites W3129135322 @default.
• W4200558263 cites W3136619793 @default.
• W4200558263 cites W3137775167 @default.
• W4200558263 cites W3178929172 @default.
• W4200558263 cites W4211220688 @default.
• W4200558263 doi "https://doi.org/10.1016/j.bspc.2021.103442" @default.
• W4200558263 hasPublicationYear "2022" @default.
• W4200558263 type Work @default.
• W4200558263 citedByCount "15" @default.
• W4200558263 countsByYear W42005582632022 @default.
• W4200558263 countsByYear W42005582632023 @default.
• W4200558263 crossrefType "journal-article" @default.
• W4200558263 hasAuthorship W4200558263A5001212991 @default.
• W4200558263 hasAuthorship W4200558263A5020044312 @default.
• W4200558263 hasAuthorship W4200558263A5030883042 @default.
• W4200558263 hasAuthorship W4200558263A5046543349 @default.
• W4200558263 hasAuthorship W4200558263A5048331196 @default.
• W4200558263 hasAuthorship W4200558263A5069516330 @default.
• W4200558263 hasAuthorship W4200558263A5076922237 @default.
• W4200558263 hasAuthorship W4200558263A5086910766 @default.
• W4200558263 hasConcept C11413529 @default.
• W4200558263 hasConcept C124504099 @default.
• W4200558263 hasConcept C138885662 @default.
• W4200558263 hasConcept C142724271 @default.
• W4200558263 hasConcept C151730666 @default.
• W4200558263 hasConcept C153180895 @default.
• W4200558263 hasConcept C154945302 @default.
• W4200558263 hasConcept C160633673 @default.
• W4200558263 hasConcept C162324750 @default.
• W4200558263 hasConcept C176217482 @default.
• W4200558263 hasConcept C205649164 @default.
• W4200558263 hasConcept C21547014 @default.
• W4200558263 hasConcept C2776401178 @default.
• W4200558263 hasConcept C2778755073 @default.
• W4200558263 hasConcept C2779130545 @default.
• W4200558263 hasConcept C2779343474 @default.
• W4200558263 hasConcept C31972630 @default.
• W4200558263 hasConcept C41008148 @default.
• W4200558263 hasConcept C41895202 @default.
• W4200558263 hasConcept C45374587 @default.
• W4200558263 hasConcept C54170458 @default.
• W4200558263 hasConcept C58640448 @default.
• W4200558263 hasConcept C71924100 @default.
• W4200558263 hasConcept C86803240 @default.
• W4200558263 hasConcept C89600930 @default.
• W4200558263 hasConceptScore W4200558263C11413529 @default.
• W4200558263 hasConceptScore W4200558263C124504099 @default.
• W4200558263 hasConceptScore W4200558263C138885662 @default.
• W4200558263 hasConceptScore W4200558263C142724271 @default.
• W4200558263 hasConceptScore W4200558263C151730666 @default.
• W4200558263 hasConceptScore W4200558263C153180895 @default.
• W4200558263 hasConceptScore W4200558263C154945302 @default.
• W4200558263 hasConceptScore W4200558263C160633673 @default.
• W4200558263 hasConceptScore W4200558263C162324750 @default.

• next