Matches in SemOpenAlex for { <https://semopenalex.org/work/W3124583721> ?p ?o ?g. }
- W3124583721 endingPage "1840002" @default.
- W3124583721 startingPage "1840002" @default.
- W3124583721 abstract "Early diagnosis is essential for the successful treatment of bowel cancers including colorectal cancer (CRC) and capsule endoscopic imaging with robotic actuation can be a valuable diagnostic tool when combined with automated image analysis. We present a deep learning rooted detection and segmentation framework for recognizing lesions in colonoscopy and capsule endoscopy images. We restructure established convolution architectures, such as VGG and ResNets, by converting them into fully-connected convolution networks (FCNs), fine-tune them and study their capabilities for polyp segmentation and detection. We additionally use Shape from-Shading (SfS) to recover depth and provide a richer representation of the tissue's structure in colonoscopy images. Depth is incorporated into our network models as an additional input channel to the RGB information and we demonstrate that the resulting network yields improved performance. Our networks are tested on publicly available datasets and the most accurate segmentation model achieved a mean segmentation IU of 47.78% and 56.95% on the ETIS-Larib and CVC-Colon datasets, respectively. For polyp detection, the top performing models we propose surpass the current state of the art with detection recalls superior to 90% for all datasets tested. To our knowledge, we present the first work to use FCNs for polyp segmentation in addition to proposing a novel combination of SfS and RGB that boosts performance" @default.
- W3124583721 created "2021-02-01" @default.
- W3124583721 creator A5028167448 @default.
- W3124583721 creator A5036187436 @default.
- W3124583721 creator A5048400975 @default.
- W3124583721 creator A5048610531 @default.
- W3124583721 creator A5049845313 @default.
- W3124583721 creator A5051955250 @default.
- W3124583721 creator A5059089719 @default.
- W3124583721 creator A5063963722 @default.
- W3124583721 creator A5072299664 @default.
- W3124583721 creator A5076392384 @default.
- W3124583721 creator A5077630267 @default.
- W3124583721 creator A5083114270 @default.
- W3124583721 date "2018-03-13" @default.
- W3124583721 modified "2023-09-30" @default.
- W3124583721 title "Towards a Computed-Aided Diagnosis System in Colonoscopy: Automatic Polyp Segmentation Using Convolution Neural Networks" @default.
- W3124583721 cites W2008359794 @default.
- W3124583721 cites W2034269173 @default.
- W3124583721 cites W2117539524 @default.
- W3124583721 cites W2132003031 @default.
- W3124583721 cites W2134138606 @default.
- W3124583721 cites W2140753590 @default.
- W3124583721 cites W2166767194 @default.
- W3124583721 cites W2285968993 @default.
- W3124583721 cites W2320150036 @default.
- W3124583721 cites W2346062110 @default.
- W3124583721 cites W2586952804 @default.
- W3124583721 doi "https://doi.org/10.1142/s2424905x18400020" @default.
- W3124583721 hasPublicationYear "2018" @default.
- W3124583721 type Work @default.
- W3124583721 sameAs 3124583721 @default.
- W3124583721 citedByCount "50" @default.
- W3124583721 countsByYear W31245837212018 @default.
- W3124583721 countsByYear W31245837212019 @default.
- W3124583721 countsByYear W31245837212020 @default.
- W3124583721 countsByYear W31245837212021 @default.
- W3124583721 countsByYear W31245837212022 @default.
- W3124583721 countsByYear W31245837212023 @default.
- W3124583721 crossrefType "journal-article" @default.
- W3124583721 hasAuthorship W3124583721A5028167448 @default.
- W3124583721 hasAuthorship W3124583721A5036187436 @default.
- W3124583721 hasAuthorship W3124583721A5048400975 @default.
- W3124583721 hasAuthorship W3124583721A5048610531 @default.
- W3124583721 hasAuthorship W3124583721A5049845313 @default.
- W3124583721 hasAuthorship W3124583721A5051955250 @default.
- W3124583721 hasAuthorship W3124583721A5059089719 @default.
- W3124583721 hasAuthorship W3124583721A5063963722 @default.
- W3124583721 hasAuthorship W3124583721A5072299664 @default.
- W3124583721 hasAuthorship W3124583721A5076392384 @default.
- W3124583721 hasAuthorship W3124583721A5077630267 @default.
- W3124583721 hasAuthorship W3124583721A5083114270 @default.
- W3124583721 hasBestOaLocation W31245837212 @default.
- W3124583721 hasConcept C108583219 @default.
- W3124583721 hasConcept C121608353 @default.
- W3124583721 hasConcept C124504099 @default.
- W3124583721 hasConcept C126322002 @default.
- W3124583721 hasConcept C126838900 @default.
- W3124583721 hasConcept C153180895 @default.
- W3124583721 hasConcept C154945302 @default.
- W3124583721 hasConcept C2777333622 @default.
- W3124583721 hasConcept C2778435480 @default.
- W3124583721 hasConcept C31972630 @default.
- W3124583721 hasConcept C41008148 @default.
- W3124583721 hasConcept C45347329 @default.
- W3124583721 hasConcept C50644808 @default.
- W3124583721 hasConcept C526805850 @default.
- W3124583721 hasConcept C71924100 @default.
- W3124583721 hasConcept C81363708 @default.
- W3124583721 hasConcept C82990744 @default.
- W3124583721 hasConcept C89600930 @default.
- W3124583721 hasConceptScore W3124583721C108583219 @default.
- W3124583721 hasConceptScore W3124583721C121608353 @default.
- W3124583721 hasConceptScore W3124583721C124504099 @default.
- W3124583721 hasConceptScore W3124583721C126322002 @default.
- W3124583721 hasConceptScore W3124583721C126838900 @default.
- W3124583721 hasConceptScore W3124583721C153180895 @default.
- W3124583721 hasConceptScore W3124583721C154945302 @default.
- W3124583721 hasConceptScore W3124583721C2777333622 @default.
- W3124583721 hasConceptScore W3124583721C2778435480 @default.
- W3124583721 hasConceptScore W3124583721C31972630 @default.
- W3124583721 hasConceptScore W3124583721C41008148 @default.
- W3124583721 hasConceptScore W3124583721C45347329 @default.
- W3124583721 hasConceptScore W3124583721C50644808 @default.
- W3124583721 hasConceptScore W3124583721C526805850 @default.
- W3124583721 hasConceptScore W3124583721C71924100 @default.
- W3124583721 hasConceptScore W3124583721C81363708 @default.
- W3124583721 hasConceptScore W3124583721C82990744 @default.
- W3124583721 hasConceptScore W3124583721C89600930 @default.
- W3124583721 hasFunder F4320338335 @default.
- W3124583721 hasIssue "02" @default.
- W3124583721 hasLocation W31245837211 @default.
- W3124583721 hasLocation W31245837212 @default.
- W3124583721 hasLocation W31245837213 @default.
- W3124583721 hasLocation W31245837214 @default.
- W3124583721 hasLocation W31245837215 @default.
- W3124583721 hasOpenAccess W3124583721 @default.
- W3124583721 hasPrimaryLocation W31245837211 @default.