Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220852230> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4220852230 endingPage "106739" @default.
- W4220852230 startingPage "106739" @default.
- W4220852230 abstract "Early fundus screening and timely treatment of ophthalmology diseases can effectively prevent blindness. Previous studies just focus on fundus images of single eye without utilizing the useful relevant information of the left and right eyes. While clinical ophthalmologists usually use binocular fundus images to help ocular disease diagnosis. Besides, previous works usually target only one ocular diseases at a time. Considering the importance of patient-level bilateral eye diagnosis and multi-label ophthalmic diseases classification, we propose a bilateral feature enhancement network (BFENet) to address the above two problems.We propose a two-stream interactive CNN architecture for multi-label ophthalmic diseases classification with bilateral fundus images. Firstly, we design a feature enhancement module, which makes use of the interaction between bilateral fundus images to strengthen the extracted feature information. Specifically, attention mechanism is used to learn the interdependence between local and global information in the designed interactive architecture for two-stream, which leads to the reweighting of these features, and recover more details. In order to capture more disease characteristics, we further design a novel multiscale module, which enriches the feature maps by superimposing feature information of different resolutions images extracted through dilated convolution.In the off-site set, the Kappa, F1, AUC and Final score are 0.535, 0.892, 0.912 and 0.780, respectively. In the on-site set, the Kappa, F1, AUC and Final score are 0.513, 0.886, 0.903 and 0.767 respectively. Comparing with existing methods, BFENet achieves the best classification performance.Comprehensive experiments are conducted to demonstrate the effectiveness of this proposed model. Besides, our method can be extended to similar tasks where the correlation between different images is important." @default.
- W4220852230 created "2022-04-03" @default.
- W4220852230 creator A5000432967 @default.
- W4220852230 creator A5018331991 @default.
- W4220852230 creator A5047570667 @default.
- W4220852230 creator A5050852420 @default.
- W4220852230 creator A5070816171 @default.
- W4220852230 creator A5082071336 @default.
- W4220852230 date "2022-06-01" @default.
- W4220852230 modified "2023-10-15" @default.
- W4220852230 title "BFENet: A two-stream interaction CNN method for multi-label ophthalmic diseases classification with bilateral fundus images" @default.
- W4220852230 cites W180947891 @default.
- W4220852230 cites W2000099545 @default.
- W4220852230 cites W2116273337 @default.
- W4220852230 cites W2193621263 @default.
- W4220852230 cites W2557738935 @default.
- W4220852230 cites W2570893893 @default.
- W4220852230 cites W2592929672 @default.
- W4220852230 cites W2761604622 @default.
- W4220852230 cites W2772246530 @default.
- W4220852230 cites W2792026451 @default.
- W4220852230 cites W2793119512 @default.
- W4220852230 cites W2806796234 @default.
- W4220852230 cites W2894585861 @default.
- W4220852230 cites W2964137095 @default.
- W4220852230 cites W2966096374 @default.
- W4220852230 cites W2985431718 @default.
- W4220852230 cites W3080421470 @default.
- W4220852230 cites W3085574514 @default.
- W4220852230 cites W3101507774 @default.
- W4220852230 cites W3110220146 @default.
- W4220852230 cites W3112251966 @default.
- W4220852230 cites W3123686843 @default.
- W4220852230 cites W3211772703 @default.
- W4220852230 doi "https://doi.org/10.1016/j.cmpb.2022.106739" @default.
- W4220852230 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35344766" @default.
- W4220852230 hasPublicationYear "2022" @default.
- W4220852230 type Work @default.
- W4220852230 citedByCount "10" @default.
- W4220852230 countsByYear W42208522302022 @default.
- W4220852230 countsByYear W42208522302023 @default.
- W4220852230 crossrefType "journal-article" @default.
- W4220852230 hasAuthorship W4220852230A5000432967 @default.
- W4220852230 hasAuthorship W4220852230A5018331991 @default.
- W4220852230 hasAuthorship W4220852230A5047570667 @default.
- W4220852230 hasAuthorship W4220852230A5050852420 @default.
- W4220852230 hasAuthorship W4220852230A5070816171 @default.
- W4220852230 hasAuthorship W4220852230A5082071336 @default.
- W4220852230 hasConcept C118487528 @default.
- W4220852230 hasConcept C138885662 @default.
- W4220852230 hasConcept C153180895 @default.
- W4220852230 hasConcept C154945302 @default.
- W4220852230 hasConcept C177264268 @default.
- W4220852230 hasConcept C199360897 @default.
- W4220852230 hasConcept C2776391266 @default.
- W4220852230 hasConcept C2776401178 @default.
- W4220852230 hasConcept C31972630 @default.
- W4220852230 hasConcept C41008148 @default.
- W4220852230 hasConcept C41895202 @default.
- W4220852230 hasConcept C71924100 @default.
- W4220852230 hasConcept C81363708 @default.
- W4220852230 hasConceptScore W4220852230C118487528 @default.
- W4220852230 hasConceptScore W4220852230C138885662 @default.
- W4220852230 hasConceptScore W4220852230C153180895 @default.
- W4220852230 hasConceptScore W4220852230C154945302 @default.
- W4220852230 hasConceptScore W4220852230C177264268 @default.
- W4220852230 hasConceptScore W4220852230C199360897 @default.
- W4220852230 hasConceptScore W4220852230C2776391266 @default.
- W4220852230 hasConceptScore W4220852230C2776401178 @default.
- W4220852230 hasConceptScore W4220852230C31972630 @default.
- W4220852230 hasConceptScore W4220852230C41008148 @default.
- W4220852230 hasConceptScore W4220852230C41895202 @default.
- W4220852230 hasConceptScore W4220852230C71924100 @default.
- W4220852230 hasConceptScore W4220852230C81363708 @default.
- W4220852230 hasFunder F4320321001 @default.
- W4220852230 hasLocation W42208522301 @default.
- W4220852230 hasLocation W42208522302 @default.
- W4220852230 hasOpenAccess W4220852230 @default.
- W4220852230 hasPrimaryLocation W42208522301 @default.
- W4220852230 hasRelatedWork W2364945429 @default.
- W4220852230 hasRelatedWork W2374520121 @default.
- W4220852230 hasRelatedWork W2394034517 @default.
- W4220852230 hasRelatedWork W2811106690 @default.
- W4220852230 hasRelatedWork W2936819511 @default.
- W4220852230 hasRelatedWork W2967742050 @default.
- W4220852230 hasRelatedWork W4293226380 @default.
- W4220852230 hasRelatedWork W4313906399 @default.
- W4220852230 hasRelatedWork W4321444604 @default.
- W4220852230 hasRelatedWork W4321487865 @default.
- W4220852230 hasVolume "219" @default.
- W4220852230 isParatext "false" @default.
- W4220852230 isRetracted "false" @default.
- W4220852230 workType "article" @default.