FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199551447> ?p ?o ?g. }

• W3199551447 endingPage "108341" @default.
• W3199551447 startingPage "108341" @default.
• W3199551447 abstract "Segmentation of infections from CT scans is important for accurate diagnosis and follow-up in tackling the COVID-19. Although the convolutional neural network has great potential to automate the segmentation task, most existing deep learning-based infection segmentation methods require fully annotated ground-truth labels for training, which is time-consuming and labor-intensive. This paper proposed a novel weakly supervised segmentation method for COVID-19 infections in CT slices, which only requires scribble supervision and is enhanced with the uncertainty-aware self-ensembling and transformation-consistent techniques. Specifically, to deal with the difficulty caused by the shortage of supervision, an uncertainty-aware mean teacher is incorporated into the scribble-based segmentation method, encouraging the segmentation predictions to be consistent under different perturbations for an input image. This mean teacher model can guide the student model to be trained using information in images without requiring manual annotations. On the other hand, considering the output of the mean teacher contains both correct and unreliable predictions, equally treating each prediction in the teacher model may degrade the performance of the student network. To alleviate this problem, the pixel level uncertainty measure on the predictions of the teacher model is calculated, and then the student model is only guided by reliable predictions from the teacher model. To further regularize the network, a transformation-consistent strategy is also incorporated, which requires the prediction to follow the same transformation if a transform is performed on an input image of the network. The proposed method has been evaluated on two public datasets and one local dataset. The experimental results demonstrate that the proposed method is more effective than other weakly supervised methods and achieves similar performance as those fully supervised." @default.
• W3199551447 created "2021-09-27" @default.
• W3199551447 creator A5000937401 @default.
• W3199551447 creator A5020164684 @default.
• W3199551447 creator A5035447211 @default.
• W3199551447 creator A5039420859 @default.
• W3199551447 creator A5050725783 @default.
• W3199551447 creator A5056674934 @default.
• W3199551447 creator A5071162105 @default.
• W3199551447 creator A5075338951 @default.
• W3199551447 date "2022-02-01" @default.
• W3199551447 modified "2023-10-10" @default.
• W3199551447 title "Weakly Supervised Segmentation of COVID19 Infection with Scribble Annotation on CT Images" @default.
• W3199551447 cites W2026981875 @default.
• W3199551447 cites W2168031320 @default.
• W3199551447 cites W2395611524 @default.
• W3199551447 cites W2396622801 @default.
• W3199551447 cites W2533800772 @default.
• W3199551447 cites W2724710774 @default.
• W3199551447 cites W2742528628 @default.
• W3199551447 cites W2752246523 @default.
• W3199551447 cites W2804383999 @default.
• W3199551447 cites W2905660188 @default.
• W3199551447 cites W2963196212 @default.
• W3199551447 cites W2964227007 @default.
• W3199551447 cites W2971013993 @default.
• W3199551447 cites W2984353870 @default.
• W3199551447 cites W3006882119 @default.
• W3199551447 cites W3007497549 @default.
• W3199551447 cites W3010030563 @default.
• W3199551447 cites W3014795415 @default.
• W3199551447 cites W3020653337 @default.
• W3199551447 cites W3027763298 @default.
• W3199551447 cites W3028070348 @default.
• W3199551447 cites W3031923721 @default.
• W3199551447 cites W3033272814 @default.
• W3199551447 cites W3046359959 @default.
• W3199551447 cites W3104427612 @default.
• W3199551447 cites W3104810384 @default.
• W3199551447 cites W3108672867 @default.
• W3199551447 cites W3115781494 @default.
• W3199551447 cites W3127107873 @default.
• W3199551447 cites W3138558221 @default.
• W3199551447 cites W3158420105 @default.
• W3199551447 doi "https://doi.org/10.1016/j.patcog.2021.108341" @default.
• W3199551447 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8452156" @default.
• W3199551447 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34565913" @default.
• W3199551447 hasPublicationYear "2022" @default.
• W3199551447 type Work @default.
• W3199551447 sameAs 3199551447 @default.
• W3199551447 citedByCount "73" @default.
• W3199551447 countsByYear W31995514472021 @default.
• W3199551447 countsByYear W31995514472022 @default.
• W3199551447 countsByYear W31995514472023 @default.
• W3199551447 crossrefType "journal-article" @default.
• W3199551447 hasAuthorship W3199551447A5000937401 @default.
• W3199551447 hasAuthorship W3199551447A5020164684 @default.
• W3199551447 hasAuthorship W3199551447A5035447211 @default.
• W3199551447 hasAuthorship W3199551447A5039420859 @default.
• W3199551447 hasAuthorship W3199551447A5050725783 @default.
• W3199551447 hasAuthorship W3199551447A5056674934 @default.
• W3199551447 hasAuthorship W3199551447A5071162105 @default.
• W3199551447 hasAuthorship W3199551447A5075338951 @default.
• W3199551447 hasBestOaLocation W31995514471 @default.
• W3199551447 hasConcept C104317684 @default.
• W3199551447 hasConcept C108583219 @default.
• W3199551447 hasConcept C119857082 @default.
• W3199551447 hasConcept C124504099 @default.
• W3199551447 hasConcept C138885662 @default.
• W3199551447 hasConcept C146849305 @default.
• W3199551447 hasConcept C153180895 @default.
• W3199551447 hasConcept C154945302 @default.
• W3199551447 hasConcept C162324750 @default.
• W3199551447 hasConcept C185592680 @default.
• W3199551447 hasConcept C187736073 @default.
• W3199551447 hasConcept C194051981 @default.
• W3199551447 hasConcept C204241405 @default.
• W3199551447 hasConcept C2776321320 @default.
• W3199551447 hasConcept C2778137410 @default.
• W3199551447 hasConcept C2780451532 @default.
• W3199551447 hasConcept C31972630 @default.
• W3199551447 hasConcept C41008148 @default.
• W3199551447 hasConcept C41895202 @default.
• W3199551447 hasConcept C50644808 @default.
• W3199551447 hasConcept C55493867 @default.
• W3199551447 hasConcept C81363708 @default.
• W3199551447 hasConcept C89600930 @default.
• W3199551447 hasConceptScore W3199551447C104317684 @default.
• W3199551447 hasConceptScore W3199551447C108583219 @default.
• W3199551447 hasConceptScore W3199551447C119857082 @default.
• W3199551447 hasConceptScore W3199551447C124504099 @default.
• W3199551447 hasConceptScore W3199551447C138885662 @default.
• W3199551447 hasConceptScore W3199551447C146849305 @default.
• W3199551447 hasConceptScore W3199551447C153180895 @default.
• W3199551447 hasConceptScore W3199551447C154945302 @default.
• W3199551447 hasConceptScore W3199551447C162324750 @default.
• W3199551447 hasConceptScore W3199551447C185592680 @default.
• W3199551447 hasConceptScore W3199551447C187736073 @default.

• next