Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204269019> ?p ?o ?g. }
- W3204269019 endingPage "44" @default.
- W3204269019 startingPage "34" @default.
- W3204269019 abstract "High fidelity segmentation of both macro and microvascular structure of the retina plays a pivotal role in determining degenerative retinal diseases, yet it is a difficult problem. Due to successive resolution loss in the encoding phase combined with the inability to recover this lost information in the decoding phase, autoencoding based segmentation approaches are limited in their ability to extract retinal microvascular structure. We propose RV-GAN, a new multi-scale generative architecture for accurate retinal vessel segmentation to alleviate this. The proposed architecture uses two generators and two multi-scale autoencoding discriminators for better microvessel localization and segmentation. In order to avoid the loss of fidelity suffered by traditional GAN-based segmentation systems, we introduce a novel weighted feature matching loss. This new loss incorporates and prioritizes features from the discriminator's decoder over the encoder. Doing so combined with the fact that the discriminator's decoder attempts to determine real or fake images at the pixel level better preserves macro and microvascular structure. By combining reconstruction and weighted feature matching loss, the proposed architecture achieves an area under the curve (AUC) of 0.9887, 0.9914, and 0.9887 in pixel-wise segmentation of retinal vasculature from three publicly available datasets, namely DRIVE, CHASE-DB1, and STARE, respectively. Additionally, RV-GAN outperforms other architectures in two additional relevant metrics, mean intersection-over-union (Mean-IOU) and structural similarity measure (SSIM)." @default.
- W3204269019 created "2021-10-11" @default.
- W3204269019 creator A5000504171 @default.
- W3204269019 creator A5016130703 @default.
- W3204269019 creator A5017262357 @default.
- W3204269019 creator A5017952778 @default.
- W3204269019 creator A5028080442 @default.
- W3204269019 creator A5077165075 @default.
- W3204269019 date "2021-01-01" @default.
- W3204269019 modified "2023-10-16" @default.
- W3204269019 title "RV-GAN: Segmenting Retinal Vascular Structure in Fundus Photographs Using a Novel Multi-scale Generative Adversarial Network" @default.
- W3204269019 cites W1861492603 @default.
- W3204269019 cites W1901129140 @default.
- W3204269019 cites W2037227137 @default.
- W3204269019 cites W2045227075 @default.
- W3204269019 cites W2072130234 @default.
- W3204269019 cites W2116628223 @default.
- W3204269019 cites W2133665775 @default.
- W3204269019 cites W2145305441 @default.
- W3204269019 cites W2150769593 @default.
- W3204269019 cites W2163344010 @default.
- W3204269019 cites W2339754110 @default.
- W3204269019 cites W2531409750 @default.
- W3204269019 cites W2898910301 @default.
- W3204269019 cites W2905338897 @default.
- W3204269019 cites W2962974533 @default.
- W3204269019 cites W2963073614 @default.
- W3204269019 cites W2963767194 @default.
- W3204269019 cites W2963800363 @default.
- W3204269019 cites W2964227007 @default.
- W3204269019 cites W2979798680 @default.
- W3204269019 cites W2982041717 @default.
- W3204269019 cites W3013766724 @default.
- W3204269019 cites W3018778187 @default.
- W3204269019 cites W3034600949 @default.
- W3204269019 cites W3048209253 @default.
- W3204269019 cites W3091449858 @default.
- W3204269019 cites W3113214702 @default.
- W3204269019 cites W3116658037 @default.
- W3204269019 doi "https://doi.org/10.1007/978-3-030-87237-3_4" @default.
- W3204269019 hasPublicationYear "2021" @default.
- W3204269019 type Work @default.
- W3204269019 sameAs 3204269019 @default.
- W3204269019 citedByCount "26" @default.
- W3204269019 countsByYear W32042690192021 @default.
- W3204269019 countsByYear W32042690192022 @default.
- W3204269019 countsByYear W32042690192023 @default.
- W3204269019 crossrefType "book-chapter" @default.
- W3204269019 hasAuthorship W3204269019A5000504171 @default.
- W3204269019 hasAuthorship W3204269019A5016130703 @default.
- W3204269019 hasAuthorship W3204269019A5017262357 @default.
- W3204269019 hasAuthorship W3204269019A5017952778 @default.
- W3204269019 hasAuthorship W3204269019A5028080442 @default.
- W3204269019 hasAuthorship W3204269019A5077165075 @default.
- W3204269019 hasBestOaLocation W32042690192 @default.
- W3204269019 hasConcept C11413529 @default.
- W3204269019 hasConcept C118487528 @default.
- W3204269019 hasConcept C124504099 @default.
- W3204269019 hasConcept C138885662 @default.
- W3204269019 hasConcept C153180895 @default.
- W3204269019 hasConcept C154945302 @default.
- W3204269019 hasConcept C2776391266 @default.
- W3204269019 hasConcept C2776401178 @default.
- W3204269019 hasConcept C2779803651 @default.
- W3204269019 hasConcept C31972630 @default.
- W3204269019 hasConcept C41008148 @default.
- W3204269019 hasConcept C41895202 @default.
- W3204269019 hasConcept C57273362 @default.
- W3204269019 hasConcept C71924100 @default.
- W3204269019 hasConcept C76155785 @default.
- W3204269019 hasConcept C89600930 @default.
- W3204269019 hasConcept C94915269 @default.
- W3204269019 hasConceptScore W3204269019C11413529 @default.
- W3204269019 hasConceptScore W3204269019C118487528 @default.
- W3204269019 hasConceptScore W3204269019C124504099 @default.
- W3204269019 hasConceptScore W3204269019C138885662 @default.
- W3204269019 hasConceptScore W3204269019C153180895 @default.
- W3204269019 hasConceptScore W3204269019C154945302 @default.
- W3204269019 hasConceptScore W3204269019C2776391266 @default.
- W3204269019 hasConceptScore W3204269019C2776401178 @default.
- W3204269019 hasConceptScore W3204269019C2779803651 @default.
- W3204269019 hasConceptScore W3204269019C31972630 @default.
- W3204269019 hasConceptScore W3204269019C41008148 @default.
- W3204269019 hasConceptScore W3204269019C41895202 @default.
- W3204269019 hasConceptScore W3204269019C57273362 @default.
- W3204269019 hasConceptScore W3204269019C71924100 @default.
- W3204269019 hasConceptScore W3204269019C76155785 @default.
- W3204269019 hasConceptScore W3204269019C89600930 @default.
- W3204269019 hasConceptScore W3204269019C94915269 @default.
- W3204269019 hasLocation W32042690191 @default.
- W3204269019 hasLocation W32042690192 @default.
- W3204269019 hasOpenAccess W3204269019 @default.
- W3204269019 hasPrimaryLocation W32042690191 @default.
- W3204269019 hasRelatedWork W1507266234 @default.
- W3204269019 hasRelatedWork W1669643531 @default.
- W3204269019 hasRelatedWork W2110230079 @default.
- W3204269019 hasRelatedWork W2117664411 @default.
- W3204269019 hasRelatedWork W2117933325 @default.