FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3153464404> ?p ?o ?g. }

• W3153464404 abstract "Significance: Speckle noise is an inherent limitation of optical coherence tomography (OCT) images that makes clinical interpretation challenging. The recent emergence of deep learning could offer a reliable method to reduce noise in OCT images. Aim: We sought to investigate the use of deep features (VGG) to limit the effect of blurriness and increase perceptual sharpness and to evaluate its impact on the performance of OCT image denoising (DnCNN). Approach: Fifty-one macula-centered OCT pairs were used in training of the network. Another set of 20 OCT pair was used for testing. The DnCNN model was cascaded with a VGG network that acted as a perceptual loss function instead of the traditional losses of L1 and L2. The VGG network remains fixed during the training process. We focused on the individual layers of the VGG-16 network to decipher the contribution of each distinctive layer as a loss function to produce denoised OCT images that were perceptually sharp and that preserved the faint features (retinal layer boundaries) essential for interpretation. The peak signal-to-noise ratio (PSNR), edge-preserving index, and no-reference image sharpness/blurriness [perceptual sharpness index (PSI), just noticeable blur (JNB), and spectral and spatial sharpness measure (S3)] metrics were used to compare deep feature losses with the traditional losses. Results: The deep feature loss produced images with high perceptual sharpness measures at the cost of less smoothness (PSNR) in OCT images. The deep feature loss outperformed the traditional losses (L1 and L2) for all of the evaluation metrics except for PSNR. The PSI, S3, and JNB estimates of deep feature loss performance were 0.31, 0.30, and 16.53, respectively. For L1 and L2 losses performance, the PSI, S3, and JNB were 0.21 and 0.21, 0.17 and 0.16, and 14.46 and 14.34, respectively. Conclusions: We demonstrate the potential of deep feature loss in denoising OCT images. Our preliminary findings suggest research directions for further investigation." @default.
• W3153464404 created "2021-04-26" @default.
• W3153464404 creator A5002372452 @default.
• W3153464404 creator A5009750573 @default.
• W3153464404 creator A5022009973 @default.
• W3153464404 creator A5037549464 @default.
• W3153464404 creator A5060018411 @default.
• W3153464404 creator A5063611049 @default.
• W3153464404 date "2021-04-23" @default.
• W3153464404 modified "2023-10-18" @default.
• W3153464404 title "Deep feature loss to denoise OCT images using deep neural networks" @default.
• W3153464404 cites W1756731880 @default.
• W3153464404 cites W1971940759 @default.
• W3153464404 cites W1996176493 @default.
• W3153464404 cites W2009790355 @default.
• W3153464404 cites W2021229920 @default.
• W3153464404 cites W2027606067 @default.
• W3153464404 cites W2047781078 @default.
• W3153464404 cites W2050348163 @default.
• W3153464404 cites W2058584842 @default.
• W3153464404 cites W2099430002 @default.
• W3153464404 cites W2112437734 @default.
• W3153464404 cites W2166086209 @default.
• W3153464404 cites W2298766618 @default.
• W3153464404 cites W2508457857 @default.
• W3153464404 cites W2894857791 @default.
• W3153464404 cites W2937484554 @default.
• W3153464404 cites W2950004209 @default.
• W3153464404 cites W2962976869 @default.
• W3153464404 cites W3000499123 @default.
• W3153464404 doi "https://doi.org/10.1117/1.jbo.26.4.046003" @default.
• W3153464404 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8062795" @default.
• W3153464404 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33893726" @default.
• W3153464404 hasPublicationYear "2021" @default.
• W3153464404 type Work @default.
• W3153464404 sameAs 3153464404 @default.
• W3153464404 citedByCount "15" @default.
• W3153464404 countsByYear W31534644042021 @default.
• W3153464404 countsByYear W31534644042022 @default.
• W3153464404 countsByYear W31534644042023 @default.
• W3153464404 crossrefType "journal-article" @default.
• W3153464404 hasAuthorship W3153464404A5002372452 @default.
• W3153464404 hasAuthorship W3153464404A5009750573 @default.
• W3153464404 hasAuthorship W3153464404A5022009973 @default.
• W3153464404 hasAuthorship W3153464404A5037549464 @default.
• W3153464404 hasAuthorship W3153464404A5060018411 @default.
• W3153464404 hasAuthorship W3153464404A5063611049 @default.
• W3153464404 hasBestOaLocation W31534644041 @default.
• W3153464404 hasConcept C102290492 @default.
• W3153464404 hasConcept C108583219 @default.
• W3153464404 hasConcept C115961682 @default.
• W3153464404 hasConcept C120665830 @default.
• W3153464404 hasConcept C121332964 @default.
• W3153464404 hasConcept C138885662 @default.
• W3153464404 hasConcept C153180895 @default.
• W3153464404 hasConcept C154945302 @default.
• W3153464404 hasConcept C163294075 @default.
• W3153464404 hasConcept C180940675 @default.
• W3153464404 hasConcept C2776401178 @default.
• W3153464404 hasConcept C2778818243 @default.
• W3153464404 hasConcept C31972630 @default.
• W3153464404 hasConcept C41008148 @default.
• W3153464404 hasConcept C41895202 @default.
• W3153464404 hasConcept C50644808 @default.
• W3153464404 hasConcept C99498987 @default.
• W3153464404 hasConceptScore W3153464404C102290492 @default.
• W3153464404 hasConceptScore W3153464404C108583219 @default.
• W3153464404 hasConceptScore W3153464404C115961682 @default.
• W3153464404 hasConceptScore W3153464404C120665830 @default.
• W3153464404 hasConceptScore W3153464404C121332964 @default.
• W3153464404 hasConceptScore W3153464404C138885662 @default.
• W3153464404 hasConceptScore W3153464404C153180895 @default.
• W3153464404 hasConceptScore W3153464404C154945302 @default.
• W3153464404 hasConceptScore W3153464404C163294075 @default.
• W3153464404 hasConceptScore W3153464404C180940675 @default.
• W3153464404 hasConceptScore W3153464404C2776401178 @default.
• W3153464404 hasConceptScore W3153464404C2778818243 @default.
• W3153464404 hasConceptScore W3153464404C31972630 @default.
• W3153464404 hasConceptScore W3153464404C41008148 @default.
• W3153464404 hasConceptScore W3153464404C41895202 @default.
• W3153464404 hasConceptScore W3153464404C50644808 @default.
• W3153464404 hasConceptScore W3153464404C99498987 @default.
• W3153464404 hasIssue "04" @default.
• W3153464404 hasLocation W31534644041 @default.
• W3153464404 hasLocation W31534644042 @default.
• W3153464404 hasLocation W31534644043 @default.
• W3153464404 hasOpenAccess W3153464404 @default.
• W3153464404 hasPrimaryLocation W31534644041 @default.
• W3153464404 hasRelatedWork W2088853231 @default.
• W3153464404 hasRelatedWork W2612576381 @default.
• W3153464404 hasRelatedWork W2741826584 @default.
• W3153464404 hasRelatedWork W2917926458 @default.
• W3153464404 hasRelatedWork W2954820311 @default.
• W3153464404 hasRelatedWork W2958229159 @default.
• W3153464404 hasRelatedWork W3094774741 @default.
• W3153464404 hasRelatedWork W3167851803 @default.
• W3153464404 hasRelatedWork W4307711312 @default.
• W3153464404 hasRelatedWork W4318243918 @default.
• W3153464404 hasVolume "26" @default.
• W3153464404 isParatext "false" @default.

• next