Matches in SemOpenAlex for { <https://semopenalex.org/work/W3019824890> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3019824890 abstract "Chest radiographs are primarily employed for the screening of cardio, thoracic and pulmonary conditions. Machine learning based automated solutions are being developed to reduce the burden of routine screening on Radiologists, allowing them to focus on critical cases. While recent efforts demonstrate the use of ensemble of deep convolutional neural networks(CNN), they do not take disease comorbidity into consideration, thus lowering their screening performance. To address this issue, we propose a Graph Neural Network (GNN) based solution to obtain ensemble predictions which models the dependencies between different diseases. A comprehensive evaluation of the proposed method demonstrated its potential by improving the performance over standard ensembling technique across a wide range of ensemble constructions. The best performance was achieved using the GNN ensemble of DenseNet121 with an average AUC of 0.821 across thirteen disease comorbidities." @default.
- W3019824890 created "2020-05-01" @default.
- W3019824890 creator A5005047202 @default.
- W3019824890 creator A5010986022 @default.
- W3019824890 creator A5023217610 @default.
- W3019824890 creator A5054681196 @default.
- W3019824890 creator A5064240264 @default.
- W3019824890 date "2020-04-24" @default.
- W3019824890 modified "2023-10-17" @default.
- W3019824890 title "Learning Decision Ensemble using a Graph Neural Network for Comorbidity Aware Chest Radiograph Screening" @default.
- W3019824890 cites W1966976587 @default.
- W3019824890 cites W2117539524 @default.
- W3019824890 cites W2194775991 @default.
- W3019824890 cites W2531409750 @default.
- W3019824890 cites W2606202972 @default.
- W3019824890 cites W2624431344 @default.
- W3019824890 cites W2761100306 @default.
- W3019824890 cites W2765312638 @default.
- W3019824890 cites W2786052267 @default.
- W3019824890 cites W2904183610 @default.
- W3019824890 cites W2948093896 @default.
- W3019824890 cites W2950772592 @default.
- W3019824890 cites W2951696358 @default.
- W3019824890 cites W2962767366 @default.
- W3019824890 cites W2962838801 @default.
- W3019824890 cites W2963446712 @default.
- W3019824890 cites W2964121744 @default.
- W3019824890 cites W3101156210 @default.
- W3019824890 hasPublicationYear "2020" @default.
- W3019824890 type Work @default.
- W3019824890 sameAs 3019824890 @default.
- W3019824890 citedByCount "0" @default.
- W3019824890 crossrefType "posted-content" @default.
- W3019824890 hasAuthorship W3019824890A5005047202 @default.
- W3019824890 hasAuthorship W3019824890A5010986022 @default.
- W3019824890 hasAuthorship W3019824890A5023217610 @default.
- W3019824890 hasAuthorship W3019824890A5054681196 @default.
- W3019824890 hasAuthorship W3019824890A5064240264 @default.
- W3019824890 hasConcept C108583219 @default.
- W3019824890 hasConcept C119857082 @default.
- W3019824890 hasConcept C126838900 @default.
- W3019824890 hasConcept C132525143 @default.
- W3019824890 hasConcept C142724271 @default.
- W3019824890 hasConcept C153180895 @default.
- W3019824890 hasConcept C154945302 @default.
- W3019824890 hasConcept C2779159551 @default.
- W3019824890 hasConcept C2781137159 @default.
- W3019824890 hasConcept C36454342 @default.
- W3019824890 hasConcept C41008148 @default.
- W3019824890 hasConcept C45942800 @default.
- W3019824890 hasConcept C50644808 @default.
- W3019824890 hasConcept C71924100 @default.
- W3019824890 hasConcept C80444323 @default.
- W3019824890 hasConcept C81363708 @default.
- W3019824890 hasConceptScore W3019824890C108583219 @default.
- W3019824890 hasConceptScore W3019824890C119857082 @default.
- W3019824890 hasConceptScore W3019824890C126838900 @default.
- W3019824890 hasConceptScore W3019824890C132525143 @default.
- W3019824890 hasConceptScore W3019824890C142724271 @default.
- W3019824890 hasConceptScore W3019824890C153180895 @default.
- W3019824890 hasConceptScore W3019824890C154945302 @default.
- W3019824890 hasConceptScore W3019824890C2779159551 @default.
- W3019824890 hasConceptScore W3019824890C2781137159 @default.
- W3019824890 hasConceptScore W3019824890C36454342 @default.
- W3019824890 hasConceptScore W3019824890C41008148 @default.
- W3019824890 hasConceptScore W3019824890C45942800 @default.
- W3019824890 hasConceptScore W3019824890C50644808 @default.
- W3019824890 hasConceptScore W3019824890C71924100 @default.
- W3019824890 hasConceptScore W3019824890C80444323 @default.
- W3019824890 hasConceptScore W3019824890C81363708 @default.
- W3019824890 hasOpenAccess W3019824890 @default.
- W3019824890 hasRelatedWork W2125400135 @default.
- W3019824890 hasRelatedWork W2130316382 @default.
- W3019824890 hasRelatedWork W2493683088 @default.
- W3019824890 hasRelatedWork W2738627448 @default.
- W3019824890 hasRelatedWork W2964043069 @default.
- W3019824890 hasRelatedWork W2979322170 @default.
- W3019824890 hasRelatedWork W3018202420 @default.
- W3019824890 hasRelatedWork W3081688429 @default.
- W3019824890 hasRelatedWork W3081902266 @default.
- W3019824890 hasRelatedWork W3098873896 @default.
- W3019824890 hasRelatedWork W3119196374 @default.
- W3019824890 hasRelatedWork W3120374612 @default.
- W3019824890 hasRelatedWork W3142870706 @default.
- W3019824890 hasRelatedWork W3154624119 @default.
- W3019824890 hasRelatedWork W3163306278 @default.
- W3019824890 hasRelatedWork W3168986074 @default.
- W3019824890 hasRelatedWork W3174735939 @default.
- W3019824890 hasRelatedWork W3184377958 @default.
- W3019824890 hasRelatedWork W3189903454 @default.
- W3019824890 hasRelatedWork W3202792552 @default.
- W3019824890 isParatext "false" @default.
- W3019824890 isRetracted "false" @default.
- W3019824890 magId "3019824890" @default.
- W3019824890 workType "article" @default.