FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3137748815> ?p ?o ?g. }

• W3137748815 endingPage "2959" @default.
• W3137748815 startingPage "2951" @default.
• W3137748815 abstract "To investigate a deep learning approach that enables three-dimensional (3D) segmentation of an arbitrary structure of interest given a user provided two-dimensional (2D) contour for context. Such an approach could decrease delineation times and improve contouring consistency, particularly for anatomical structures for which no automatic segmentation tools exist.A series of deep learning segmentation models using a Recurrent Residual U-Net with attention gates was trained with a successively expanding training set. Contextual information was provided to the models, using a previously contoured slice as an input, in addition to the slice to be contoured. In total, 6 models were developed, and 19 different anatomical structures were used for training and testing. Each of the models was evaluated for all 19 structures, even if they were excluded from the training set, in order to assess the model's ability to segment unseen structures of interest. Each model's performance was evaluated using the Dice similarity coefficient (DSC), Hausdorff distance, and relative added path length (APL).The segmentation performance for seen and unseen structures improved when the training set was expanded by addition of structures previously excluded from the training set. A model trained exclusively on heart structures achieved a DSC of 0.33, HD of 44 mm, and relative APL of 0.85 when segmenting the spleen, whereas a model trained on a diverse set of structures, but still excluding the spleen, achieved a DSC of 0.80, HD of 13 mm, and relative APL of 0.35. Iterative prediction performed better compared to direct prediction when considering unseen structures.Training a contextual deep learning model on a diverse set of structures increases the segmentation performance for the structures in the training set, but importantly enables the model to generalize and make predictions even for unseen structures that were not represented in the training set. This shows that user-provided context can be incorporated into deep learning contouring to facilitate semi-automatic segmentation of CT images for any given structure. Such an approach can enable faster de-novo contouring in clinical practice." @default.
• W3137748815 created "2021-03-29" @default.
• W3137748815 creator A5047320633 @default.
• W3137748815 creator A5050327045 @default.
• W3137748815 creator A5074404084 @default.
• W3137748815 creator A5083853243 @default.
• W3137748815 creator A5084133212 @default.
• W3137748815 date "2021-05-03" @default.
• W3137748815 modified "2023-10-09" @default.
• W3137748815 title "Interactive contouring through contextual deep learning" @default.
• W3137748815 cites W1987869189 @default.
• W3137748815 cites W2104460869 @default.
• W3137748815 cites W2160754664 @default.
• W3137748815 cites W2165614176 @default.
• W3137748815 cites W2732931556 @default.
• W3137748815 cites W2763160469 @default.
• W3137748815 cites W2773960327 @default.
• W3137748815 cites W2808772741 @default.
• W3137748815 cites W2888358068 @default.
• W3137748815 cites W2893275934 @default.
• W3137748815 cites W2905338897 @default.
• W3137748815 cites W2909847169 @default.
• W3137748815 cites W2912989244 @default.
• W3137748815 cites W2920206089 @default.
• W3137748815 cites W2936495845 @default.
• W3137748815 cites W2944958482 @default.
• W3137748815 cites W2964212292 @default.
• W3137748815 cites W2994739006 @default.
• W3137748815 cites W3101756320 @default.
• W3137748815 cites W3105282616 @default.
• W3137748815 doi "https://doi.org/10.1002/mp.14852" @default.
• W3137748815 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33742454" @default.
• W3137748815 hasPublicationYear "2021" @default.
• W3137748815 type Work @default.
• W3137748815 sameAs 3137748815 @default.
• W3137748815 citedByCount "7" @default.
• W3137748815 countsByYear W31377488152021 @default.
• W3137748815 countsByYear W31377488152022 @default.
• W3137748815 countsByYear W31377488152023 @default.
• W3137748815 crossrefType "journal-article" @default.
• W3137748815 hasAuthorship W3137748815A5047320633 @default.
• W3137748815 hasAuthorship W3137748815A5050327045 @default.
• W3137748815 hasAuthorship W3137748815A5074404084 @default.
• W3137748815 hasAuthorship W3137748815A5083853243 @default.
• W3137748815 hasAuthorship W3137748815A5084133212 @default.
• W3137748815 hasBestOaLocation W31377488152 @default.
• W3137748815 hasConcept C103278499 @default.
• W3137748815 hasConcept C105795698 @default.
• W3137748815 hasConcept C108583219 @default.
• W3137748815 hasConcept C11413529 @default.
• W3137748815 hasConcept C115961682 @default.
• W3137748815 hasConcept C121684516 @default.
• W3137748815 hasConcept C125308379 @default.
• W3137748815 hasConcept C141898687 @default.
• W3137748815 hasConcept C144133560 @default.
• W3137748815 hasConcept C151730666 @default.
• W3137748815 hasConcept C153008295 @default.
• W3137748815 hasConcept C153180895 @default.
• W3137748815 hasConcept C154945302 @default.
• W3137748815 hasConcept C155512373 @default.
• W3137748815 hasConcept C162853370 @default.
• W3137748815 hasConcept C177264268 @default.
• W3137748815 hasConcept C199360897 @default.
• W3137748815 hasConcept C22029948 @default.
• W3137748815 hasConcept C2776436953 @default.
• W3137748815 hasConcept C2779104521 @default.
• W3137748815 hasConcept C2779343474 @default.
• W3137748815 hasConcept C31972630 @default.
• W3137748815 hasConcept C33923547 @default.
• W3137748815 hasConcept C41008148 @default.
• W3137748815 hasConcept C86803240 @default.
• W3137748815 hasConcept C89600930 @default.
• W3137748815 hasConceptScore W3137748815C103278499 @default.
• W3137748815 hasConceptScore W3137748815C105795698 @default.
• W3137748815 hasConceptScore W3137748815C108583219 @default.
• W3137748815 hasConceptScore W3137748815C11413529 @default.
• W3137748815 hasConceptScore W3137748815C115961682 @default.
• W3137748815 hasConceptScore W3137748815C121684516 @default.
• W3137748815 hasConceptScore W3137748815C125308379 @default.
• W3137748815 hasConceptScore W3137748815C141898687 @default.
• W3137748815 hasConceptScore W3137748815C144133560 @default.
• W3137748815 hasConceptScore W3137748815C151730666 @default.
• W3137748815 hasConceptScore W3137748815C153008295 @default.
• W3137748815 hasConceptScore W3137748815C153180895 @default.
• W3137748815 hasConceptScore W3137748815C154945302 @default.
• W3137748815 hasConceptScore W3137748815C155512373 @default.
• W3137748815 hasConceptScore W3137748815C162853370 @default.
• W3137748815 hasConceptScore W3137748815C177264268 @default.
• W3137748815 hasConceptScore W3137748815C199360897 @default.
• W3137748815 hasConceptScore W3137748815C22029948 @default.
• W3137748815 hasConceptScore W3137748815C2776436953 @default.
• W3137748815 hasConceptScore W3137748815C2779104521 @default.
• W3137748815 hasConceptScore W3137748815C2779343474 @default.
• W3137748815 hasConceptScore W3137748815C31972630 @default.
• W3137748815 hasConceptScore W3137748815C33923547 @default.
• W3137748815 hasConceptScore W3137748815C41008148 @default.
• W3137748815 hasConceptScore W3137748815C86803240 @default.
• W3137748815 hasConceptScore W3137748815C89600930 @default.

• next