Matches in SemOpenAlex for { <https://semopenalex.org/work/W4206901058> ?p ?o ?g. }
- W4206901058 abstract "Abstract In this work, we propose an attention-based deep convolutional neural network (CNN) model as an assistive computer-aided tool to classify common types of macular diseases: age-related macular degeneration, diabetic macular edema, diabetic retinopathy, choroidal neovascularization, macular hole, and central serous retinopathy from normal macular conditions with the help of scans from optical coherence tomography (OCT) imaging. Our proposed architecture unifies refined deep pre-trained models using transfer learning with limited training data and a deformation-aware attention mechanism encoding crucial morphological variations appearing in the deformation of retinal layers, detachments from the subsequent layers, presence of fluid-filled regions, geographic atrophy, scars, cysts, drusen, to achieve superior macular imaging classification performance. The proposed attention module facilitates the base network to automatically focus on the salient features arising due to the macular structural abnormalities while suppressing the irrelevant (or no cues) regions. The superiority of our proposed method lies in the fact that it does not require any pre-processing steps such as retinal flattening, denoising, and selection of a region of interest making it fully automatic and end-to-end trainable. Additionally, it requires a reduced number of network model parameters while achieving higher diagnostic performance. Extensive experimental results, analysis on four datasets along with the ablation studies show that the proposed architecture achieves state-of-the-art performance." @default.
- W4206901058 created "2022-01-26" @default.
- W4206901058 creator A5048131385 @default.
- W4206901058 creator A5067464832 @default.
- W4206901058 creator A5086045014 @default.
- W4206901058 date "2022-01-22" @default.
- W4206901058 modified "2023-10-18" @default.
- W4206901058 title "MacularNet: Towards Fully Automated Attention-Based Deep CNN for Macular Disease Classification" @default.
- W4206901058 cites W1978478291 @default.
- W4206901058 cites W2013754472 @default.
- W4206901058 cites W2071110690 @default.
- W4206901058 cites W2107826392 @default.
- W4206901058 cites W2116064496 @default.
- W4206901058 cites W2194775991 @default.
- W4206901058 cites W2325939864 @default.
- W4206901058 cites W2346062110 @default.
- W4206901058 cites W2418802570 @default.
- W4206901058 cites W2546844354 @default.
- W4206901058 cites W2570893893 @default.
- W4206901058 cites W2574964908 @default.
- W4206901058 cites W2613478786 @default.
- W4206901058 cites W2617085002 @default.
- W4206901058 cites W2773475231 @default.
- W4206901058 cites W2788633781 @default.
- W4206901058 cites W2790301353 @default.
- W4206901058 cites W2798413309 @default.
- W4206901058 cites W2808730081 @default.
- W4206901058 cites W2886281300 @default.
- W4206901058 cites W2888358068 @default.
- W4206901058 cites W2902947916 @default.
- W4206901058 cites W2910179937 @default.
- W4206901058 cites W2914016683 @default.
- W4206901058 cites W2953040471 @default.
- W4206901058 cites W2963967185 @default.
- W4206901058 cites W2966909379 @default.
- W4206901058 cites W2981458349 @default.
- W4206901058 cites W2985431718 @default.
- W4206901058 cites W2996651271 @default.
- W4206901058 cites W2997662364 @default.
- W4206901058 cites W3035267940 @default.
- W4206901058 cites W3035576197 @default.
- W4206901058 cites W3110529192 @default.
- W4206901058 cites W3131308308 @default.
- W4206901058 cites W3142292783 @default.
- W4206901058 cites W3157034296 @default.
- W4206901058 cites W3159895986 @default.
- W4206901058 cites W3172516001 @default.
- W4206901058 cites W4237713631 @default.
- W4206901058 doi "https://doi.org/10.1007/s42979-022-01024-0" @default.
- W4206901058 hasPublicationYear "2022" @default.
- W4206901058 type Work @default.
- W4206901058 citedByCount "5" @default.
- W4206901058 countsByYear W42069010582022 @default.
- W4206901058 countsByYear W42069010582023 @default.
- W4206901058 crossrefType "journal-article" @default.
- W4206901058 hasAuthorship W4206901058A5048131385 @default.
- W4206901058 hasAuthorship W4206901058A5067464832 @default.
- W4206901058 hasAuthorship W4206901058A5086045014 @default.
- W4206901058 hasBestOaLocation W42069010581 @default.
- W4206901058 hasConcept C108583219 @default.
- W4206901058 hasConcept C118487528 @default.
- W4206901058 hasConcept C134018914 @default.
- W4206901058 hasConcept C153180895 @default.
- W4206901058 hasConcept C154945302 @default.
- W4206901058 hasConcept C2776403814 @default.
- W4206901058 hasConcept C2778818243 @default.
- W4206901058 hasConcept C2779093074 @default.
- W4206901058 hasConcept C2779829184 @default.
- W4206901058 hasConcept C31972630 @default.
- W4206901058 hasConcept C41008148 @default.
- W4206901058 hasConcept C555293320 @default.
- W4206901058 hasConcept C71924100 @default.
- W4206901058 hasConcept C81363708 @default.
- W4206901058 hasConceptScore W4206901058C108583219 @default.
- W4206901058 hasConceptScore W4206901058C118487528 @default.
- W4206901058 hasConceptScore W4206901058C134018914 @default.
- W4206901058 hasConceptScore W4206901058C153180895 @default.
- W4206901058 hasConceptScore W4206901058C154945302 @default.
- W4206901058 hasConceptScore W4206901058C2776403814 @default.
- W4206901058 hasConceptScore W4206901058C2778818243 @default.
- W4206901058 hasConceptScore W4206901058C2779093074 @default.
- W4206901058 hasConceptScore W4206901058C2779829184 @default.
- W4206901058 hasConceptScore W4206901058C31972630 @default.
- W4206901058 hasConceptScore W4206901058C41008148 @default.
- W4206901058 hasConceptScore W4206901058C555293320 @default.
- W4206901058 hasConceptScore W4206901058C71924100 @default.
- W4206901058 hasConceptScore W4206901058C81363708 @default.
- W4206901058 hasIssue "2" @default.
- W4206901058 hasLocation W42069010581 @default.
- W4206901058 hasLocation W42069010582 @default.
- W4206901058 hasOpenAccess W4206901058 @default.
- W4206901058 hasPrimaryLocation W42069010581 @default.
- W4206901058 hasRelatedWork W2001080026 @default.
- W4206901058 hasRelatedWork W2017975899 @default.
- W4206901058 hasRelatedWork W2067597951 @default.
- W4206901058 hasRelatedWork W2161462781 @default.
- W4206901058 hasRelatedWork W2731899572 @default.
- W4206901058 hasRelatedWork W3133861977 @default.
- W4206901058 hasRelatedWork W4200173597 @default.
- W4206901058 hasRelatedWork W4312417841 @default.