FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3028990794> ?p ?o ?g. }

• W3028990794 endingPage "909" @default.
• W3028990794 startingPage "909" @default.
• W3028990794 abstract "Cup-to-disc ratio (CDR) is of great importance during assessing structural changes at the optic nerve head (ONH) and diagnosis of glaucoma. While most efforts have been put on acquiring the CDR number through CNN-based segmentation algorithms followed by the calculation of CDR, these methods usually only focus on the features in the convolution kernel, which is, after all, the operation of the local region, ignoring the contribution of rich global features (such as distant pixels) to the current features. In this paper, a new end-to-end channel and spatial attention regression deep learning network is proposed to deduces CDR number from the regression perspective and combine the self-attention mechanism with the regression network. Our network consists of four modules: the feature extraction module to extract deep features expressing the complicated pattern of optic disc (OD) and optic cup (OC), the attention module including the channel attention block (CAB) and the spatial attention block (SAB) to improve feature representation by aggregating long-range contextual information, the regression module to deduce CDR number directly, and the segmentation-auxiliary module to focus the model’s attention on the relevant features instead of the background region. Especially, the CAB selects relatively important feature maps in channel dimension, shifting the emphasis on the OD and OC region; meanwhile, the SAB learns the discriminative ability of feature representation at pixel level by capturing the relationship of intra-feature map. The experimental results of ORIGA dataset show that our method obtains absolute CDR error of 0.067 and the Pearson’s correlation coefficient of 0.694 in estimating CDR and our method has a great potential in predicting the CDR number." @default.
• W3028990794 created "2020-06-05" @default.
• W3028990794 creator A5007211501 @default.
• W3028990794 creator A5037057824 @default.
• W3028990794 creator A5043296622 @default.
• W3028990794 creator A5068363339 @default.
• W3028990794 creator A5078580228 @default.
• W3028990794 date "2020-05-29" @default.
• W3028990794 modified "2023-09-26" @default.
• W3028990794 title "Channel and Spatial Attention Regression Network for Cup-to-Disc Ratio Estimation" @default.
• W3028990794 cites W2056871061 @default.
• W3028990794 cites W2081178133 @default.
• W3028990794 cites W2106376259 @default.
• W3028990794 cites W2108824200 @default.
• W3028990794 cites W2149865252 @default.
• W3028990794 cites W2170203892 @default.
• W3028990794 cites W2177654152 @default.
• W3028990794 cites W2263081120 @default.
• W3028990794 cites W2512450393 @default.
• W3028990794 cites W2555816429 @default.
• W3028990794 cites W2575285771 @default.
• W3028990794 cites W2607394097 @default.
• W3028990794 cites W2613836512 @default.
• W3028990794 cites W2724534590 @default.
• W3028990794 cites W2727810912 @default.
• W3028990794 cites W2759518055 @default.
• W3028990794 cites W2783157867 @default.
• W3028990794 cites W2792289763 @default.
• W3028990794 cites W2793402133 @default.
• W3028990794 cites W2799341967 @default.
• W3028990794 cites W2804081635 @default.
• W3028990794 cites W2884120031 @default.
• W3028990794 cites W2907733702 @default.
• W3028990794 cites W2915496375 @default.
• W3028990794 cites W2938047312 @default.
• W3028990794 cites W2941075605 @default.
• W3028990794 cites W2946133851 @default.
• W3028990794 cites W2968097744 @default.
• W3028990794 cites W3101507774 @default.
• W3028990794 doi "https://doi.org/10.3390/electronics9060909" @default.
• W3028990794 hasPublicationYear "2020" @default.
• W3028990794 type Work @default.
• W3028990794 sameAs 3028990794 @default.
• W3028990794 citedByCount "2" @default.
• W3028990794 countsByYear W30289907942021 @default.
• W3028990794 countsByYear W30289907942022 @default.
• W3028990794 crossrefType "journal-article" @default.
• W3028990794 hasAuthorship W3028990794A5007211501 @default.
• W3028990794 hasAuthorship W3028990794A5037057824 @default.
• W3028990794 hasAuthorship W3028990794A5043296622 @default.
• W3028990794 hasAuthorship W3028990794A5068363339 @default.
• W3028990794 hasAuthorship W3028990794A5078580228 @default.
• W3028990794 hasBestOaLocation W30289907941 @default.
• W3028990794 hasConcept C104317684 @default.
• W3028990794 hasConcept C105795698 @default.
• W3028990794 hasConcept C114696181 @default.
• W3028990794 hasConcept C120665830 @default.
• W3028990794 hasConcept C121332964 @default.
• W3028990794 hasConcept C127162648 @default.
• W3028990794 hasConcept C127716648 @default.
• W3028990794 hasConcept C138885662 @default.
• W3028990794 hasConcept C153180895 @default.
• W3028990794 hasConcept C154945302 @default.
• W3028990794 hasConcept C160633673 @default.
• W3028990794 hasConcept C185592680 @default.
• W3028990794 hasConcept C192209626 @default.
• W3028990794 hasConcept C2524010 @default.
• W3028990794 hasConcept C2776401178 @default.
• W3028990794 hasConcept C2777210771 @default.
• W3028990794 hasConcept C33923547 @default.
• W3028990794 hasConcept C41008148 @default.
• W3028990794 hasConcept C41895202 @default.
• W3028990794 hasConcept C52622490 @default.
• W3028990794 hasConcept C55493867 @default.
• W3028990794 hasConcept C76155785 @default.
• W3028990794 hasConcept C81363708 @default.
• W3028990794 hasConcept C83546350 @default.
• W3028990794 hasConcept C89600930 @default.
• W3028990794 hasConcept C96021297 @default.
• W3028990794 hasConcept C97931131 @default.
• W3028990794 hasConceptScore W3028990794C104317684 @default.
• W3028990794 hasConceptScore W3028990794C105795698 @default.
• W3028990794 hasConceptScore W3028990794C114696181 @default.
• W3028990794 hasConceptScore W3028990794C120665830 @default.
• W3028990794 hasConceptScore W3028990794C121332964 @default.
• W3028990794 hasConceptScore W3028990794C127162648 @default.
• W3028990794 hasConceptScore W3028990794C127716648 @default.
• W3028990794 hasConceptScore W3028990794C138885662 @default.
• W3028990794 hasConceptScore W3028990794C153180895 @default.
• W3028990794 hasConceptScore W3028990794C154945302 @default.
• W3028990794 hasConceptScore W3028990794C160633673 @default.
• W3028990794 hasConceptScore W3028990794C185592680 @default.
• W3028990794 hasConceptScore W3028990794C192209626 @default.
• W3028990794 hasConceptScore W3028990794C2524010 @default.
• W3028990794 hasConceptScore W3028990794C2776401178 @default.
• W3028990794 hasConceptScore W3028990794C2777210771 @default.
• W3028990794 hasConceptScore W3028990794C33923547 @default.
• W3028990794 hasConceptScore W3028990794C41008148 @default.

• next