Matches in SemOpenAlex for { <https://semopenalex.org/work/W3168685463> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3168685463 endingPage "3944" @default.
- W3168685463 startingPage "3932" @default.
- W3168685463 abstract "Convolutional neural networks (CNNs) have the potential to automatically delineate primary nasopharyngeal carcinoma (NPC) on magnetic resonance imaging (MRI), but currently, the literature lacks a module to introduce valuable pre-computed features into a CNN. In addition, most CNNs for primary NPC delineation have focused on contrast-enhanced MRI. To enable the use of CNNs in clinical applications where it would be desirable to avoid contrast agents, such as cancer screening or intra-treatment monitoring, we aim to develop a CNN algorithm with a positional-textural fully-connected attention (FCA) module that can automatically delineate primary NPCs on contrast-free MRI.This retrospective study was performed in 404 patients with NPC who had undergone staging MRI. A proposed CNN algorithm incorporated with our positional-textural FCA module (Aproposed ) was trained on manually delineated tumours (M1st ) to automatically delineate primary NPCs on non-contrast-enhanced T2-weighted fat-suppressed (NE-T2W-FS) images. The performance of Aproposed , three well-established CNNs, Unet (Aunet ), Attention-Unet (Aatt ) and Dense-Unet (Adense ), and a second manual delineation repeated to evaluate human variability (M2nd ) were measured by comparing to the reference standard M1st to obtain the Dice similarity coefficient (DSC) and average surface distance (ASD). The Wilcoxon rank test was used to compare the performance of Aproposed against Aunet , Aatt , Adense and M2nd .Aproposed showed a median DSC of 0.79 (0.10) and ASD of 0.66 (0.84) mm. It performed better than the well-established networks Aunet [DSC =0.75 (0.12) and ASD =1.22 (1.73) mm], Aatt [DSC =0.75 (0.10) and ASD =0.96 (1.16) mm] and Adense [DSC =0.71 (0.14) and ASD =1.67 (1.92) mm] (all P<0.01), but slightly worse when compared to M2nd [DSC =0.81 (0.07) and ASD =0.56 (0.80) mm] (P<0.001).The proposed CNN algorithm has potential to accurately delineate primary NPCs on non-contrast-enhanced MRI." @default.
- W3168685463 created "2021-06-22" @default.
- W3168685463 creator A5001261828 @default.
- W3168685463 creator A5005567947 @default.
- W3168685463 creator A5022215035 @default.
- W3168685463 creator A5022870273 @default.
- W3168685463 creator A5023364103 @default.
- W3168685463 creator A5033886818 @default.
- W3168685463 creator A5057872518 @default.
- W3168685463 creator A5090777504 @default.
- W3168685463 date "2021-09-01" @default.
- W3168685463 modified "2023-10-16" @default.
- W3168685463 title "A convolutional neural network combined with positional and textural attention for the fully automatic delineation of primary nasopharyngeal carcinoma on non-contrast-enhanced MRI" @default.
- W3168685463 cites W1831841265 @default.
- W3168685463 cites W2001844373 @default.
- W3168685463 cites W2066208236 @default.
- W3168685463 cites W2127890285 @default.
- W3168685463 cites W2742681205 @default.
- W3168685463 cites W2883369084 @default.
- W3168685463 cites W2896909802 @default.
- W3168685463 cites W2905454744 @default.
- W3168685463 cites W2908040407 @default.
- W3168685463 cites W2911605224 @default.
- W3168685463 cites W2925142108 @default.
- W3168685463 cites W2944588218 @default.
- W3168685463 cites W2953914369 @default.
- W3168685463 cites W3007257886 @default.
- W3168685463 cites W3010707384 @default.
- W3168685463 cites W3039549155 @default.
- W3168685463 cites W3128918376 @default.
- W3168685463 doi "https://doi.org/10.21037/qims-21-196" @default.
- W3168685463 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8339644" @default.
- W3168685463 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34476179" @default.
- W3168685463 hasPublicationYear "2021" @default.
- W3168685463 type Work @default.
- W3168685463 sameAs 3168685463 @default.
- W3168685463 citedByCount "4" @default.
- W3168685463 countsByYear W31686854632022 @default.
- W3168685463 countsByYear W31686854632023 @default.
- W3168685463 crossrefType "journal-article" @default.
- W3168685463 hasAuthorship W3168685463A5001261828 @default.
- W3168685463 hasAuthorship W3168685463A5005567947 @default.
- W3168685463 hasAuthorship W3168685463A5022215035 @default.
- W3168685463 hasAuthorship W3168685463A5022870273 @default.
- W3168685463 hasAuthorship W3168685463A5023364103 @default.
- W3168685463 hasAuthorship W3168685463A5033886818 @default.
- W3168685463 hasAuthorship W3168685463A5057872518 @default.
- W3168685463 hasAuthorship W3168685463A5090777504 @default.
- W3168685463 hasBestOaLocation W31686854631 @default.
- W3168685463 hasConcept C126322002 @default.
- W3168685463 hasConcept C126838900 @default.
- W3168685463 hasConcept C12868164 @default.
- W3168685463 hasConcept C143409427 @default.
- W3168685463 hasConcept C153180895 @default.
- W3168685463 hasConcept C154945302 @default.
- W3168685463 hasConcept C206041023 @default.
- W3168685463 hasConcept C2776502983 @default.
- W3168685463 hasConcept C2778997737 @default.
- W3168685463 hasConcept C41008148 @default.
- W3168685463 hasConcept C509974204 @default.
- W3168685463 hasConcept C71924100 @default.
- W3168685463 hasConcept C81363708 @default.
- W3168685463 hasConceptScore W3168685463C126322002 @default.
- W3168685463 hasConceptScore W3168685463C126838900 @default.
- W3168685463 hasConceptScore W3168685463C12868164 @default.
- W3168685463 hasConceptScore W3168685463C143409427 @default.
- W3168685463 hasConceptScore W3168685463C153180895 @default.
- W3168685463 hasConceptScore W3168685463C154945302 @default.
- W3168685463 hasConceptScore W3168685463C206041023 @default.
- W3168685463 hasConceptScore W3168685463C2776502983 @default.
- W3168685463 hasConceptScore W3168685463C2778997737 @default.
- W3168685463 hasConceptScore W3168685463C41008148 @default.
- W3168685463 hasConceptScore W3168685463C509974204 @default.
- W3168685463 hasConceptScore W3168685463C71924100 @default.
- W3168685463 hasConceptScore W3168685463C81363708 @default.
- W3168685463 hasIssue "9" @default.
- W3168685463 hasLocation W31686854631 @default.
- W3168685463 hasLocation W31686854632 @default.
- W3168685463 hasLocation W31686854633 @default.
- W3168685463 hasOpenAccess W3168685463 @default.
- W3168685463 hasPrimaryLocation W31686854631 @default.
- W3168685463 hasRelatedWork W2047631959 @default.
- W3168685463 hasRelatedWork W2748454020 @default.
- W3168685463 hasRelatedWork W2767651786 @default.
- W3168685463 hasRelatedWork W2896909802 @default.
- W3168685463 hasRelatedWork W2912288872 @default.
- W3168685463 hasRelatedWork W3016958897 @default.
- W3168685463 hasRelatedWork W3181746755 @default.
- W3168685463 hasRelatedWork W4283379348 @default.
- W3168685463 hasRelatedWork W4312417841 @default.
- W3168685463 hasRelatedWork W564581980 @default.
- W3168685463 hasVolume "11" @default.
- W3168685463 isParatext "false" @default.
- W3168685463 isRetracted "false" @default.
- W3168685463 magId "3168685463" @default.
- W3168685463 workType "article" @default.