Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366352148> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4366352148 endingPage "e0284508" @default.
- W4366352148 startingPage "e0284508" @default.
- W4366352148 abstract "Qualitative visual assessment of MRI scans is a key mechanism by which inflammation is assessed in clinical practice. For example, in axial spondyloarthritis (axSpA), visual assessment focuses on the identification of regions with increased signal in the bone marrow, known as bone marrow oedema (BMO), on water-sensitive images. The identification of BMO has an important role in the diagnosis, quantification and monitoring of disease in axSpA. However, BMO evaluation depends heavily on the experience and expertise of the image reader, creating substantial imprecision. Deep learning-based segmentation is a natural approach to addressing this imprecision, but purely automated solutions require large training sets that are not currently available, and deep learning solutions with limited data may not be sufficiently trustworthy for use in clinical practice. To address this, we propose a workflow for inflammation segmentation incorporating both deep learning and human input. With this ‘human-machine cooperation’ workflow, a preliminary segmentation is generated automatically by deep learning; a human reader then ‘cleans’ the segmentation by removing extraneous segmented voxels. The final cleaned segmentation defines the volume of hyperintense inflammation (V HI ), which is proposed as a quantitative imaging biomarker (QIB) of inflammation load in axSpA. We implemented and evaluated the proposed human-machine workflow in a cohort of 29 patients with axSpA who had undergone prospective MRI scans before and after starting biologic therapy. The performance of the workflow was compared against purely visual assessment in terms of inter-observer/inter-method segmentation overlap, inter-observer agreement and assessment of response to biologic therapy. The human-machine workflow showed superior inter-observer segmentation overlap than purely manual segmentation (Dice score 0.84 versus 0.56). V HI measurements produced by the workflow showed similar or better inter-observer agreement than visual scoring, with similar response assessments. We conclude that the proposed human-machine workflow offers a mechanism to improve the consistency of inflammation assessment, and that V HI could be a valuable QIB of inflammation load in axSpA, as well as offering an exemplar of human-machine cooperation more broadly." @default.
- W4366352148 created "2023-04-21" @default.
- W4366352148 creator A5003759585 @default.
- W4366352148 creator A5032841378 @default.
- W4366352148 creator A5054888342 @default.
- W4366352148 creator A5074194702 @default.
- W4366352148 creator A5083838326 @default.
- W4366352148 creator A5087206127 @default.
- W4366352148 creator A5089354085 @default.
- W4366352148 creator A5090667792 @default.
- W4366352148 date "2023-04-19" @default.
- W4366352148 modified "2023-09-26" @default.
- W4366352148 title "Volume of hyperintense inflammation (VHI): A quantitative imaging biomarker of inflammation load in spondyloarthritis, enabled by human-machine cooperation" @default.
- W4366352148 cites W1980064060 @default.
- W4366352148 cites W2079392881 @default.
- W4366352148 cites W2118596556 @default.
- W4366352148 cites W2127890285 @default.
- W4366352148 cites W2133038766 @default.
- W4366352148 cites W2153785016 @default.
- W4366352148 cites W2335579102 @default.
- W4366352148 cites W2340907062 @default.
- W4366352148 cites W2529077007 @default.
- W4366352148 cites W2603295433 @default.
- W4366352148 cites W2607436252 @default.
- W4366352148 cites W2737270755 @default.
- W4366352148 cites W2768755701 @default.
- W4366352148 cites W2998744841 @default.
- W4366352148 cites W3021060361 @default.
- W4366352148 cites W3080123676 @default.
- W4366352148 cites W3112701542 @default.
- W4366352148 cites W3169750593 @default.
- W4366352148 cites W4281701276 @default.
- W4366352148 cites W2922440290 @default.
- W4366352148 doi "https://doi.org/10.1371/journal.pone.0284508" @default.
- W4366352148 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37075028" @default.
- W4366352148 hasPublicationYear "2023" @default.
- W4366352148 type Work @default.
- W4366352148 citedByCount "0" @default.
- W4366352148 crossrefType "journal-article" @default.
- W4366352148 hasAuthorship W4366352148A5003759585 @default.
- W4366352148 hasAuthorship W4366352148A5032841378 @default.
- W4366352148 hasAuthorship W4366352148A5054888342 @default.
- W4366352148 hasAuthorship W4366352148A5074194702 @default.
- W4366352148 hasAuthorship W4366352148A5083838326 @default.
- W4366352148 hasAuthorship W4366352148A5087206127 @default.
- W4366352148 hasAuthorship W4366352148A5089354085 @default.
- W4366352148 hasAuthorship W4366352148A5090667792 @default.
- W4366352148 hasBestOaLocation W43663521481 @default.
- W4366352148 hasConcept C108583219 @default.
- W4366352148 hasConcept C119857082 @default.
- W4366352148 hasConcept C154945302 @default.
- W4366352148 hasConcept C177212765 @default.
- W4366352148 hasConcept C2781197716 @default.
- W4366352148 hasConcept C41008148 @default.
- W4366352148 hasConcept C55493867 @default.
- W4366352148 hasConcept C71924100 @default.
- W4366352148 hasConcept C77088390 @default.
- W4366352148 hasConcept C86803240 @default.
- W4366352148 hasConcept C89600930 @default.
- W4366352148 hasConceptScore W4366352148C108583219 @default.
- W4366352148 hasConceptScore W4366352148C119857082 @default.
- W4366352148 hasConceptScore W4366352148C154945302 @default.
- W4366352148 hasConceptScore W4366352148C177212765 @default.
- W4366352148 hasConceptScore W4366352148C2781197716 @default.
- W4366352148 hasConceptScore W4366352148C41008148 @default.
- W4366352148 hasConceptScore W4366352148C55493867 @default.
- W4366352148 hasConceptScore W4366352148C71924100 @default.
- W4366352148 hasConceptScore W4366352148C77088390 @default.
- W4366352148 hasConceptScore W4366352148C86803240 @default.
- W4366352148 hasConceptScore W4366352148C89600930 @default.
- W4366352148 hasFunder F4320319669 @default.
- W4366352148 hasFunder F4320334659 @default.
- W4366352148 hasFunder F4320335936 @default.
- W4366352148 hasIssue "4" @default.
- W4366352148 hasLocation W43663521481 @default.
- W4366352148 hasLocation W43663521482 @default.
- W4366352148 hasLocation W43663521483 @default.
- W4366352148 hasOpenAccess W4366352148 @default.
- W4366352148 hasPrimaryLocation W43663521481 @default.
- W4366352148 hasRelatedWork W2790662084 @default.
- W4366352148 hasRelatedWork W3014300295 @default.
- W4366352148 hasRelatedWork W3164822677 @default.
- W4366352148 hasRelatedWork W4223943233 @default.
- W4366352148 hasRelatedWork W4225161397 @default.
- W4366352148 hasRelatedWork W4312200629 @default.
- W4366352148 hasRelatedWork W4360585206 @default.
- W4366352148 hasRelatedWork W4364306694 @default.
- W4366352148 hasRelatedWork W4380075502 @default.
- W4366352148 hasRelatedWork W4380086463 @default.
- W4366352148 hasVolume "18" @default.
- W4366352148 isParatext "false" @default.
- W4366352148 isRetracted "false" @default.
- W4366352148 workType "article" @default.