FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306248002> ?p ?o ?g. }

• W4306248002 endingPage "673" @default.
• W4306248002 startingPage "661" @default.
• W4306248002 abstract "While supervised learning techniques have demonstrated state-of-the-art performance in many medical image analysis tasks, the role of sample selection is important. Selecting the most informative samples contributes to the system attaining optimum performance with minimum labeled samples, which translates to fewer expert interventions and cost. Active Learning (AL) methods for informative sample selection are effective in boosting performance of computer aided diagnosis systems when limited labels are available. Conventional approaches to AL have mostly focused on the single label setting where a sample has only one disease label from the set of possible labels. These approaches do not perform optimally in the multi-label setting where a sample can have multiple disease labels (e.g. in chest X-ray images). In this paper we propose a novel sample selection approach based on graph analysis to identify informative samples in a multi-label setting. For every analyzed sample, each class label is denoted as a separate node of a graph. Building on findings from interpretability of deep learning models, edge interactions in this graph characterize similarity between corresponding interpretability saliency map model encodings. We explore different types of graph aggregation to identify informative samples for active learning. We apply our method to public chest X-ray and medical image datasets, and report improved results over state-of-the-art AL techniques in terms of model performance, learning rates, and robustness." @default.
• W4306248002 created "2022-10-15" @default.
• W4306248002 creator A5051830200 @default.
• W4306248002 creator A5060822066 @default.
• W4306248002 creator A5078933997 @default.
• W4306248002 date "2023-03-01" @default.
• W4306248002 modified "2023-10-01" @default.
• W4306248002 title "Graph Node Based Interpretability Guided Sample Selection for Active Learning" @default.
• W4306248002 cites W1964017540 @default.
• W4306248002 cites W2008989859 @default.
• W4306248002 cites W2097501027 @default.
• W4306248002 cites W2194775991 @default.
• W4306248002 cites W2195388612 @default.
• W4306248002 cites W2197357114 @default.
• W4306248002 cites W2279894747 @default.
• W4306248002 cites W2295107390 @default.
• W4306248002 cites W2471138382 @default.
• W4306248002 cites W2568998735 @default.
• W4306248002 cites W2625559849 @default.
• W4306248002 cites W2748525783 @default.
• W4306248002 cites W2798820905 @default.
• W4306248002 cites W2904204744 @default.
• W4306248002 cites W2926307165 @default.
• W4306248002 cites W2941567073 @default.
• W4306248002 cites W2962858109 @default.
• W4306248002 cites W2963015987 @default.
• W4306248002 cites W2963466845 @default.
• W4306248002 cites W2977942577 @default.
• W4306248002 cites W2980246484 @default.
• W4306248002 cites W2991372685 @default.
• W4306248002 cites W3014249243 @default.
• W4306248002 cites W3029137193 @default.
• W4306248002 cites W3035131250 @default.
• W4306248002 cites W3095948197 @default.
• W4306248002 cites W3098712157 @default.
• W4306248002 cites W3101156210 @default.
• W4306248002 cites W3102100346 @default.
• W4306248002 cites W3129604848 @default.
• W4306248002 cites W3176196997 @default.
• W4306248002 cites W4225344339 @default.
• W4306248002 cites W4286436505 @default.
• W4306248002 cites W4312677475 @default.
• W4306248002 cites W55768394 @default.
• W4306248002 doi "https://doi.org/10.1109/tmi.2022.3215017" @default.
• W4306248002 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36240033" @default.
• W4306248002 hasPublicationYear "2023" @default.
• W4306248002 type Work @default.
• W4306248002 citedByCount "4" @default.
• W4306248002 countsByYear W43062480022023 @default.
• W4306248002 crossrefType "journal-article" @default.
• W4306248002 hasAuthorship W4306248002A5051830200 @default.
• W4306248002 hasAuthorship W4306248002A5060822066 @default.
• W4306248002 hasAuthorship W4306248002A5078933997 @default.
• W4306248002 hasConcept C104317684 @default.
• W4306248002 hasConcept C119857082 @default.
• W4306248002 hasConcept C124101348 @default.
• W4306248002 hasConcept C132525143 @default.
• W4306248002 hasConcept C153180895 @default.
• W4306248002 hasConcept C154945302 @default.
• W4306248002 hasConcept C185592680 @default.
• W4306248002 hasConcept C198531522 @default.
• W4306248002 hasConcept C2781067378 @default.
• W4306248002 hasConcept C41008148 @default.
• W4306248002 hasConcept C43617362 @default.
• W4306248002 hasConcept C46686674 @default.
• W4306248002 hasConcept C55493867 @default.
• W4306248002 hasConcept C63479239 @default.
• W4306248002 hasConcept C80444323 @default.
• W4306248002 hasConceptScore W4306248002C104317684 @default.
• W4306248002 hasConceptScore W4306248002C119857082 @default.
• W4306248002 hasConceptScore W4306248002C124101348 @default.
• W4306248002 hasConceptScore W4306248002C132525143 @default.
• W4306248002 hasConceptScore W4306248002C153180895 @default.
• W4306248002 hasConceptScore W4306248002C154945302 @default.
• W4306248002 hasConceptScore W4306248002C185592680 @default.
• W4306248002 hasConceptScore W4306248002C198531522 @default.
• W4306248002 hasConceptScore W4306248002C2781067378 @default.
• W4306248002 hasConceptScore W4306248002C41008148 @default.
• W4306248002 hasConceptScore W4306248002C43617362 @default.
• W4306248002 hasConceptScore W4306248002C46686674 @default.
• W4306248002 hasConceptScore W4306248002C55493867 @default.
• W4306248002 hasConceptScore W4306248002C63479239 @default.
• W4306248002 hasConceptScore W4306248002C80444323 @default.
• W4306248002 hasFunder F4320327931 @default.
• W4306248002 hasIssue "3" @default.
• W4306248002 hasLocation W43062480021 @default.
• W4306248002 hasLocation W43062480022 @default.
• W4306248002 hasOpenAccess W4306248002 @default.
• W4306248002 hasPrimaryLocation W43062480021 @default.
• W4306248002 hasRelatedWork W3006943036 @default.
• W4306248002 hasRelatedWork W3012234327 @default.
• W4306248002 hasRelatedWork W3101544650 @default.
• W4306248002 hasRelatedWork W3103064266 @default.
• W4306248002 hasRelatedWork W3203961807 @default.
• W4306248002 hasRelatedWork W4200027074 @default.
• W4306248002 hasRelatedWork W4205364923 @default.
• W4306248002 hasRelatedWork W4206534706 @default.
• W4306248002 hasRelatedWork W4229079080 @default.

• next