FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3198147788> ?p ?o ?g. }

• W3198147788 endingPage "104815" @default.
• W3198147788 startingPage "104815" @default.
• W3198147788 abstract "Colonoscopy remains the gold-standard screening for colorectal cancer. However, significant miss rates for polyps have been reported, particularly when there are multiple small adenomas. This presents an opportunity to leverage computer-aided systems to support clinicians and reduce the number of polyps missed.In this work we introduce the Focus U-Net, a novel dual attention-gated deep neural network, which combines efficient spatial and channel-based attention into a single Focus Gate module to encourage selective learning of polyp features. The Focus U-Net incorporates several further architectural modifications, including the addition of short-range skip connections and deep supervision. Furthermore, we introduce the Hybrid Focal loss, a new compound loss function based on the Focal loss and Focal Tversky loss, designed to handle class-imbalanced image segmentation. For our experiments, we selected five public datasets containing images of polyps obtained during optical colonoscopy: CVC-ClinicDB, Kvasir-SEG, CVC-ColonDB, ETIS-Larib PolypDB and EndoScene test set. We first perform a series of ablation studies and then evaluate the Focus U-Net on the CVC-ClinicDB and Kvasir-SEG datasets separately, and on a combined dataset of all five public datasets. To evaluate model performance, we use the Dice similarity coefficient (DSC) and Intersection over Union (IoU) metrics.Our model achieves state-of-the-art results for both CVC-ClinicDB and Kvasir-SEG, with a mean DSC of 0.941 and 0.910, respectively. When evaluated on a combination of five public polyp datasets, our model similarly achieves state-of-the-art results with a mean DSC of 0.878 and mean IoU of 0.809, a 14% and 15% improvement over the previous state-of-the-art results of 0.768 and 0.702, respectively.This study shows the potential for deep learning to provide fast and accurate polyp segmentation results for use during colonoscopy. The Focus U-Net may be adapted for future use in newer non-invasive colorectal cancer screening and more broadly to other biomedical image segmentation tasks similarly involving class imbalance and requiring efficiency." @default.
• W3198147788 created "2021-09-13" @default.
• W3198147788 creator A5028460960 @default.
• W3198147788 creator A5033880300 @default.
• W3198147788 creator A5062142185 @default.
• W3198147788 creator A5081459146 @default.
• W3198147788 date "2021-10-01" @default.
• W3198147788 modified "2023-10-14" @default.
• W3198147788 title "Focus U-Net: A novel dual attention-gated CNN for polyp segmentation during colonoscopy" @default.
• W3198147788 cites W1969651471 @default.
• W3198147788 cites W1981444270 @default.
• W3198147788 cites W2008359794 @default.
• W3198147788 cites W2021088830 @default.
• W3198147788 cites W2034269173 @default.
• W3198147788 cites W2063979222 @default.
• W3198147788 cites W2082627290 @default.
• W3198147788 cites W2091723114 @default.
• W3198147788 cites W2140753590 @default.
• W3198147788 cites W2146430570 @default.
• W3198147788 cites W2147072570 @default.
• W3198147788 cites W2167597393 @default.
• W3198147788 cites W2285968993 @default.
• W3198147788 cites W2302003756 @default.
• W3198147788 cites W2320150036 @default.
• W3198147788 cites W2560328367 @default.
• W3198147788 cites W2560770519 @default.
• W3198147788 cites W2613041730 @default.
• W3198147788 cites W2739592885 @default.
• W3198147788 cites W2799387322 @default.
• W3198147788 cites W2888358068 @default.
• W3198147788 cites W2889646458 @default.
• W3198147788 cites W2928133111 @default.
• W3198147788 cites W2964334073 @default.
• W3198147788 cites W2978294504 @default.
• W3198147788 cites W2978457402 @default.
• W3198147788 cites W2996290406 @default.
• W3198147788 cites W3000643822 @default.
• W3198147788 cites W3013765727 @default.
• W3198147788 cites W3100548413 @default.
• W3198147788 cites W3104061658 @default.
• W3198147788 cites W3112701542 @default.
• W3198147788 cites W3120333390 @default.
• W3198147788 cites W3124583721 @default.
• W3198147788 cites W3157328277 @default.
• W3198147788 cites W3160038630 @default.
• W3198147788 cites W3169359689 @default.
• W3198147788 doi "https://doi.org/10.1016/j.compbiomed.2021.104815" @default.
• W3198147788 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8505797" @default.
• W3198147788 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34507156" @default.
• W3198147788 hasPublicationYear "2021" @default.
• W3198147788 type Work @default.
• W3198147788 sameAs 3198147788 @default.
• W3198147788 citedByCount "53" @default.
• W3198147788 countsByYear W31981477882021 @default.
• W3198147788 countsByYear W31981477882022 @default.
• W3198147788 countsByYear W31981477882023 @default.
• W3198147788 crossrefType "journal-article" @default.
• W3198147788 hasAuthorship W3198147788A5028460960 @default.
• W3198147788 hasAuthorship W3198147788A5033880300 @default.
• W3198147788 hasAuthorship W3198147788A5062142185 @default.
• W3198147788 hasAuthorship W3198147788A5081459146 @default.
• W3198147788 hasBestOaLocation W31981477881 @default.
• W3198147788 hasConcept C108583219 @default.
• W3198147788 hasConcept C119857082 @default.
• W3198147788 hasConcept C120665830 @default.
• W3198147788 hasConcept C121332964 @default.
• W3198147788 hasConcept C121608353 @default.
• W3198147788 hasConcept C124504099 @default.
• W3198147788 hasConcept C126322002 @default.
• W3198147788 hasConcept C153083717 @default.
• W3198147788 hasConcept C153180895 @default.
• W3198147788 hasConcept C154945302 @default.
• W3198147788 hasConcept C163892561 @default.
• W3198147788 hasConcept C169903167 @default.
• W3198147788 hasConcept C192209626 @default.
• W3198147788 hasConcept C2778435480 @default.
• W3198147788 hasConcept C41008148 @default.
• W3198147788 hasConcept C526805850 @default.
• W3198147788 hasConcept C71924100 @default.
• W3198147788 hasConcept C81363708 @default.
• W3198147788 hasConcept C89600930 @default.
• W3198147788 hasConceptScore W3198147788C108583219 @default.
• W3198147788 hasConceptScore W3198147788C119857082 @default.
• W3198147788 hasConceptScore W3198147788C120665830 @default.
• W3198147788 hasConceptScore W3198147788C121332964 @default.
• W3198147788 hasConceptScore W3198147788C121608353 @default.
• W3198147788 hasConceptScore W3198147788C124504099 @default.
• W3198147788 hasConceptScore W3198147788C126322002 @default.
• W3198147788 hasConceptScore W3198147788C153083717 @default.
• W3198147788 hasConceptScore W3198147788C153180895 @default.
• W3198147788 hasConceptScore W3198147788C154945302 @default.
• W3198147788 hasConceptScore W3198147788C163892561 @default.
• W3198147788 hasConceptScore W3198147788C169903167 @default.
• W3198147788 hasConceptScore W3198147788C192209626 @default.
• W3198147788 hasConceptScore W3198147788C2778435480 @default.
• W3198147788 hasConceptScore W3198147788C41008148 @default.
• W3198147788 hasConceptScore W3198147788C526805850 @default.
• W3198147788 hasConceptScore W3198147788C71924100 @default.

• next