Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308233814> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4308233814 abstract "We propose an adversarial training framework to simultaneously address the vessel segmentation and dirt/reflection removal problems in fundus photographs used for diabetic retinopathy diagnosis. This framework contains two primary subnetworks, each triggered by a set of loss terms, i.e., one for segmentation and the other for reconstruction. These two subnetworks act as inverse functions of each other so that they form an autoencoder framework with a 2-dimensional latent code, which can be a vessel segmentation mask after binarization. To further improve the segmentation and reconstruction performance, we devise a loss function based on gradient vector flow (GVF) and reorganize the generator network. Experimental results show that the proposed method has a good generalization capability. Trained on DRIVE’s training set, our model can produce segmentation and reconstruction-based artifact removal results stably on other datasets like CHASE-DB1 and STARE. The average F1-score of our segmentation results of DRIVE’s testing set reaches 0.7964, and the artifact-free reconstruction results can achieve an average PSNR of 24 dB." @default.
- W4308233814 created "2022-11-09" @default.
- W4308233814 creator A5038300748 @default.
- W4308233814 creator A5047421795 @default.
- W4308233814 creator A5056107539 @default.
- W4308233814 creator A5061941573 @default.
- W4308233814 creator A5089025176 @default.
- W4308233814 date "2022-10-16" @default.
- W4308233814 modified "2023-10-10" @default.
- W4308233814 title "Vessel Segmentation and Dirt/Reflection Detection For Retinal Fundus Photographs" @default.
- W4308233814 cites W166117271 @default.
- W4308233814 cites W1989321650 @default.
- W4308233814 cites W2072130234 @default.
- W4308233814 cites W2093545979 @default.
- W4308233814 cites W2097117768 @default.
- W4308233814 cites W2115185191 @default.
- W4308233814 cites W2145305441 @default.
- W4308233814 cites W2145803225 @default.
- W4308233814 cites W2150769593 @default.
- W4308233814 cites W2194775991 @default.
- W4308233814 cites W2955758626 @default.
- W4308233814 cites W2962793481 @default.
- W4308233814 cites W2962914239 @default.
- W4308233814 cites W2963073614 @default.
- W4308233814 cites W2982397699 @default.
- W4308233814 cites W3006089892 @default.
- W4308233814 cites W3013766724 @default.
- W4308233814 cites W3035131250 @default.
- W4308233814 cites W3035346684 @default.
- W4308233814 cites W3043431450 @default.
- W4308233814 cites W3195158041 @default.
- W4308233814 cites W3204269019 @default.
- W4308233814 doi "https://doi.org/10.1109/icip46576.2022.9897447" @default.
- W4308233814 hasPublicationYear "2022" @default.
- W4308233814 type Work @default.
- W4308233814 citedByCount "1" @default.
- W4308233814 crossrefType "proceedings-article" @default.
- W4308233814 hasAuthorship W4308233814A5038300748 @default.
- W4308233814 hasAuthorship W4308233814A5047421795 @default.
- W4308233814 hasAuthorship W4308233814A5056107539 @default.
- W4308233814 hasAuthorship W4308233814A5061941573 @default.
- W4308233814 hasAuthorship W4308233814A5089025176 @default.
- W4308233814 hasConcept C101738243 @default.
- W4308233814 hasConcept C108583219 @default.
- W4308233814 hasConcept C124504099 @default.
- W4308233814 hasConcept C153008295 @default.
- W4308233814 hasConcept C153180895 @default.
- W4308233814 hasConcept C154945302 @default.
- W4308233814 hasConcept C2779010991 @default.
- W4308233814 hasConcept C31972630 @default.
- W4308233814 hasConcept C41008148 @default.
- W4308233814 hasConcept C65885262 @default.
- W4308233814 hasConcept C89600930 @default.
- W4308233814 hasConceptScore W4308233814C101738243 @default.
- W4308233814 hasConceptScore W4308233814C108583219 @default.
- W4308233814 hasConceptScore W4308233814C124504099 @default.
- W4308233814 hasConceptScore W4308233814C153008295 @default.
- W4308233814 hasConceptScore W4308233814C153180895 @default.
- W4308233814 hasConceptScore W4308233814C154945302 @default.
- W4308233814 hasConceptScore W4308233814C2779010991 @default.
- W4308233814 hasConceptScore W4308233814C31972630 @default.
- W4308233814 hasConceptScore W4308233814C41008148 @default.
- W4308233814 hasConceptScore W4308233814C65885262 @default.
- W4308233814 hasConceptScore W4308233814C89600930 @default.
- W4308233814 hasLocation W43082338141 @default.
- W4308233814 hasOpenAccess W4308233814 @default.
- W4308233814 hasPrimaryLocation W43082338141 @default.
- W4308233814 hasRelatedWork W1669643531 @default.
- W4308233814 hasRelatedWork W1982826852 @default.
- W4308233814 hasRelatedWork W2005437358 @default.
- W4308233814 hasRelatedWork W2110230079 @default.
- W4308233814 hasRelatedWork W2384989255 @default.
- W4308233814 hasRelatedWork W2392905701 @default.
- W4308233814 hasRelatedWork W2517104666 @default.
- W4308233814 hasRelatedWork W2549936415 @default.
- W4308233814 hasRelatedWork W2566648451 @default.
- W4308233814 hasRelatedWork W1967061043 @default.
- W4308233814 isParatext "false" @default.
- W4308233814 isRetracted "false" @default.
- W4308233814 workType "article" @default.