Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206556234> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3206556234 abstract "Segmentation plays a crucial role in diagnosis. Studying the retinal vasculatures from fundus images help identify early signs of many crucial illnesses such as diabetic retinopathy. Due to the varying shape, size, and patterns of retinal vessels, along with artefacts and noises in fundus images, no one-stage method can accurately segment retinal vessels. In this work, we propose a multi-scale, multi-level attention embedded CNN architecture ((M)SLAe-Net) to address the issue of multistage processing for robust and precise segmentation of retinal vessels. We do this by extracting features at multiple scales and multiple levels of the network, enabling our model to holistically extracts the local and global features. Multi-scale features are extracted using our novel dynamic dilated pyramid pooling (D - DPP) module. We also aggregate the features from all the network levels. These effectively resolved the issues of varying shape and artefacts and hence the need for multiple stages. To assist in better pixel level classification, we use the Squeeze and Attention (SA) module, a smartly adapted version of the Squeeze and Excitation (SE) module for segmentation tasks in our network to facilitate pixel-group attention. Our unique network design and novel D-DPP module with efficient task specific loss function for thin vessels enabled our model for better cross data performance. Exhaustive experimental results on DRIVE, STARE, HRF, and CHASE-DB1 show the superiority of our method." @default.
- W3206556234 created "2021-10-25" @default.
- W3206556234 creator A5023120109 @default.
- W3206556234 creator A5055059667 @default.
- W3206556234 date "2021-08-01" @default.
- W3206556234 modified "2023-10-16" @default.
- W3206556234 title "(M)SLAe-Net: Multi-Scale Multi-Level Attention embedded Network for Retinal Vessel Segmentation" @default.
- W3206556234 cites W1901129140 @default.
- W3206556234 cites W2045227075 @default.
- W3206556234 cites W2072130234 @default.
- W3206556234 cites W2093545979 @default.
- W3206556234 cites W2592848770 @default.
- W3206556234 cites W2893691907 @default.
- W3206556234 cites W2898910301 @default.
- W3206556234 cites W2923997689 @default.
- W3206556234 cites W2966523470 @default.
- W3206556234 cites W2982364173 @default.
- W3206556234 cites W3015701499 @default.
- W3206556234 cites W3023519466 @default.
- W3206556234 cites W3027519656 @default.
- W3206556234 cites W3034681889 @default.
- W3206556234 cites W3096125778 @default.
- W3206556234 cites W3107816570 @default.
- W3206556234 cites W3169743628 @default.
- W3206556234 doi "https://doi.org/10.1109/ichi52183.2021.00042" @default.
- W3206556234 hasPublicationYear "2021" @default.
- W3206556234 type Work @default.
- W3206556234 sameAs 3206556234 @default.
- W3206556234 citedByCount "2" @default.
- W3206556234 countsByYear W32065562342022 @default.
- W3206556234 countsByYear W32065562342023 @default.
- W3206556234 crossrefType "proceedings-article" @default.
- W3206556234 hasAuthorship W3206556234A5023120109 @default.
- W3206556234 hasAuthorship W3206556234A5055059667 @default.
- W3206556234 hasBestOaLocation W32065562342 @default.
- W3206556234 hasConcept C118487528 @default.
- W3206556234 hasConcept C120665830 @default.
- W3206556234 hasConcept C121332964 @default.
- W3206556234 hasConcept C124504099 @default.
- W3206556234 hasConcept C142575187 @default.
- W3206556234 hasConcept C153180895 @default.
- W3206556234 hasConcept C154945302 @default.
- W3206556234 hasConcept C160633673 @default.
- W3206556234 hasConcept C2776391266 @default.
- W3206556234 hasConcept C2778755073 @default.
- W3206556234 hasConcept C2993807640 @default.
- W3206556234 hasConcept C31972630 @default.
- W3206556234 hasConcept C41008148 @default.
- W3206556234 hasConcept C62520636 @default.
- W3206556234 hasConcept C70437156 @default.
- W3206556234 hasConcept C71924100 @default.
- W3206556234 hasConcept C89600930 @default.
- W3206556234 hasConceptScore W3206556234C118487528 @default.
- W3206556234 hasConceptScore W3206556234C120665830 @default.
- W3206556234 hasConceptScore W3206556234C121332964 @default.
- W3206556234 hasConceptScore W3206556234C124504099 @default.
- W3206556234 hasConceptScore W3206556234C142575187 @default.
- W3206556234 hasConceptScore W3206556234C153180895 @default.
- W3206556234 hasConceptScore W3206556234C154945302 @default.
- W3206556234 hasConceptScore W3206556234C160633673 @default.
- W3206556234 hasConceptScore W3206556234C2776391266 @default.
- W3206556234 hasConceptScore W3206556234C2778755073 @default.
- W3206556234 hasConceptScore W3206556234C2993807640 @default.
- W3206556234 hasConceptScore W3206556234C31972630 @default.
- W3206556234 hasConceptScore W3206556234C41008148 @default.
- W3206556234 hasConceptScore W3206556234C62520636 @default.
- W3206556234 hasConceptScore W3206556234C70437156 @default.
- W3206556234 hasConceptScore W3206556234C71924100 @default.
- W3206556234 hasConceptScore W3206556234C89600930 @default.
- W3206556234 hasLocation W32065562341 @default.
- W3206556234 hasLocation W32065562342 @default.
- W3206556234 hasOpenAccess W3206556234 @default.
- W3206556234 hasPrimaryLocation W32065562341 @default.
- W3206556234 hasRelatedWork W1631910785 @default.
- W3206556234 hasRelatedWork W1669643531 @default.
- W3206556234 hasRelatedWork W2110230079 @default.
- W3206556234 hasRelatedWork W2122581818 @default.
- W3206556234 hasRelatedWork W2159066190 @default.
- W3206556234 hasRelatedWork W2739874619 @default.
- W3206556234 hasRelatedWork W2943038984 @default.
- W3206556234 hasRelatedWork W3198183219 @default.
- W3206556234 hasRelatedWork W3206556234 @default.
- W3206556234 hasRelatedWork W4286986085 @default.
- W3206556234 isParatext "false" @default.
- W3206556234 isRetracted "false" @default.
- W3206556234 magId "3206556234" @default.
- W3206556234 workType "article" @default.