Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297795705> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4297795705 abstract "Segmentation tasks in medical imaging are inherently ambiguous: the boundary of a target structure is oftentimes unclear due to image quality and biological factors. As such, predicted segmentations from deep learning algorithms are inherently ambiguous. Additionally, ground truth segmentations performed by human annotators are in fact weak labels that further increase the uncertainty of outputs of supervised models developed on these manual labels. To date, most deep learning segmentation studies utilize predicted segmentations without uncertainty quantification. In contrast, we explore the use of Monte Carlo dropout U-Nets for the segmentation with additional quantification of segmentation uncertainty. We assess the utility of three measures of uncertainty (Coefficient of Variation, Mean Pairwise Dice, and Mean Voxelwise Uncertainty) for the segmentation of a less ambiguous target structure (liver) and a more ambiguous one (liver tumors). Furthermore, we assess how the utility of these measures changes with different patch sizes and cost functions. Our results suggest that models trained using larger patches and the weighted categorical cross-entropy as cost function allow the extraction of more meaningful uncertainty measures compared to smaller patches and soft dice loss. Among the three uncertainty measures Mean Pairwise Dice shows the strongest correlation with segmentation quality. Our study serves as a proof-of-concept of how uncertainty measures can be used to assess the quality of a predicted segmentation, potentially serving to flag low quality segmentations from a given model for further human review." @default.
- W4297795705 created "2022-10-01" @default.
- W4297795705 creator A5001020883 @default.
- W4297795705 creator A5007189721 @default.
- W4297795705 creator A5039622318 @default.
- W4297795705 creator A5060793983 @default.
- W4297795705 creator A5065482711 @default.
- W4297795705 date "2019-11-14" @default.
- W4297795705 modified "2023-09-24" @default.
- W4297795705 title "Give me (un)certainty -- An exploration of parameters that affect segmentation uncertainty" @default.
- W4297795705 doi "https://doi.org/10.48550/arxiv.1911.06357" @default.
- W4297795705 hasPublicationYear "2019" @default.
- W4297795705 type Work @default.
- W4297795705 citedByCount "0" @default.
- W4297795705 crossrefType "posted-content" @default.
- W4297795705 hasAuthorship W4297795705A5001020883 @default.
- W4297795705 hasAuthorship W4297795705A5007189721 @default.
- W4297795705 hasAuthorship W4297795705A5039622318 @default.
- W4297795705 hasAuthorship W4297795705A5060793983 @default.
- W4297795705 hasAuthorship W4297795705A5065482711 @default.
- W4297795705 hasBestOaLocation W42977957051 @default.
- W4297795705 hasConcept C105795698 @default.
- W4297795705 hasConcept C119857082 @default.
- W4297795705 hasConcept C124504099 @default.
- W4297795705 hasConcept C146849305 @default.
- W4297795705 hasConcept C153180895 @default.
- W4297795705 hasConcept C154945302 @default.
- W4297795705 hasConcept C163892561 @default.
- W4297795705 hasConcept C167981619 @default.
- W4297795705 hasConcept C184898388 @default.
- W4297795705 hasConcept C22029948 @default.
- W4297795705 hasConcept C33923547 @default.
- W4297795705 hasConcept C41008148 @default.
- W4297795705 hasConcept C5274069 @default.
- W4297795705 hasConcept C89600930 @default.
- W4297795705 hasConceptScore W4297795705C105795698 @default.
- W4297795705 hasConceptScore W4297795705C119857082 @default.
- W4297795705 hasConceptScore W4297795705C124504099 @default.
- W4297795705 hasConceptScore W4297795705C146849305 @default.
- W4297795705 hasConceptScore W4297795705C153180895 @default.
- W4297795705 hasConceptScore W4297795705C154945302 @default.
- W4297795705 hasConceptScore W4297795705C163892561 @default.
- W4297795705 hasConceptScore W4297795705C167981619 @default.
- W4297795705 hasConceptScore W4297795705C184898388 @default.
- W4297795705 hasConceptScore W4297795705C22029948 @default.
- W4297795705 hasConceptScore W4297795705C33923547 @default.
- W4297795705 hasConceptScore W4297795705C41008148 @default.
- W4297795705 hasConceptScore W4297795705C5274069 @default.
- W4297795705 hasConceptScore W4297795705C89600930 @default.
- W4297795705 hasLocation W42977957051 @default.
- W4297795705 hasOpenAccess W4297795705 @default.
- W4297795705 hasPrimaryLocation W42977957051 @default.
- W4297795705 hasRelatedWork W2630229246 @default.
- W4297795705 hasRelatedWork W2942988769 @default.
- W4297795705 hasRelatedWork W2971461860 @default.
- W4297795705 hasRelatedWork W2973136608 @default.
- W4297795705 hasRelatedWork W2982780470 @default.
- W4297795705 hasRelatedWork W3105697449 @default.
- W4297795705 hasRelatedWork W3128451644 @default.
- W4297795705 hasRelatedWork W3152950745 @default.
- W4297795705 hasRelatedWork W4297795705 @default.
- W4297795705 hasRelatedWork W3127600691 @default.
- W4297795705 isParatext "false" @default.
- W4297795705 isRetracted "false" @default.
- W4297795705 workType "article" @default.