FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2801585709> ?p ?o ?g. }

• W2801585709 endingPage "1487" @default.
• W2801585709 startingPage "1478" @default.
• W2801585709 abstract "Motivated by the great potential of deep learning in medical imaging, we propose an iterative positron emission tomography reconstruction framework using a deep learning-based prior. We utilized the denoising convolutional neural network (DnCNN) method and trained the network using full-dose images as the ground truth and low dose images reconstructed from downsampled data by Poisson thinning as input. Since most published deep networks are trained at a predetermined noise level, the noise level disparity of training and testing data is a major problem for their applicability as a generalized prior. In particular, the noise level significantly changes in each iteration, which can potentially degrade the overall performance of iterative reconstruction. Due to insufficient existing studies, we conducted simulations and evaluated the degradation of performance at various noise conditions. Our findings indicated that DnCNN produces additional bias induced by the disparity of noise levels. To address this issue, we propose a local linear fitting function incorporated with the DnCNN prior to improve the image quality by preventing unwanted bias. We demonstrate that the resultant method is robust against noise level disparities despite the network being trained at a predetermined noise level. By means of bias and standard deviation studies via both simulations and clinical experiments, we show that the proposed method outperforms conventional methods based on total variation and non-local means penalties. We thereby confirm that the proposed method improves the reconstruction result both quantitatively and qualitatively." @default.
• W2801585709 created "2018-05-17" @default.
• W2801585709 creator A5013691634 @default.
• W2801585709 creator A5038806083 @default.
• W2801585709 creator A5044227206 @default.
• W2801585709 creator A5049372409 @default.
• W2801585709 creator A5051533773 @default.
• W2801585709 creator A5053436378 @default.
• W2801585709 creator A5057977985 @default.
• W2801585709 creator A5058429770 @default.
• W2801585709 creator A5089383440 @default.
• W2801585709 date "2018-06-01" @default.
• W2801585709 modified "2023-10-16" @default.
• W2801585709 title "Penalized PET Reconstruction Using Deep Learning Prior and Local Linear Fitting" @default.
• W2801585709 cites W1603307924 @default.
• W2801585709 cites W1965573563 @default.
• W2801585709 cites W1968238516 @default.
• W2801585709 cites W1995696377 @default.
• W2801585709 cites W2017162022 @default.
• W2801585709 cites W2032237670 @default.
• W2801585709 cites W2063928686 @default.
• W2801585709 cites W2093038246 @default.
• W2801585709 cites W2100556411 @default.
• W2801585709 cites W2119038831 @default.
• W2801585709 cites W2125188192 @default.
• W2801585709 cites W2129150528 @default.
• W2801585709 cites W2133594110 @default.
• W2801585709 cites W2149251622 @default.
• W2801585709 cites W2155893237 @default.
• W2801585709 cites W2194775991 @default.
• W2801585709 cites W2469946482 @default.
• W2801585709 cites W2508457857 @default.
• W2801585709 cites W2520016695 @default.
• W2801585709 cites W2570202822 @default.
• W2801585709 cites W2754956769 @default.
• W2801585709 cites W2964292098 @default.
• W2801585709 cites W3104324122 @default.
• W2801585709 cites W4292363360 @default.
• W2801585709 doi "https://doi.org/10.1109/tmi.2018.2832613" @default.
• W2801585709 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6375088" @default.
• W2801585709 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29870375" @default.
• W2801585709 hasPublicationYear "2018" @default.
• W2801585709 type Work @default.
• W2801585709 sameAs 2801585709 @default.
• W2801585709 citedByCount "147" @default.
• W2801585709 countsByYear W28015857092018 @default.
• W2801585709 countsByYear W28015857092019 @default.
• W2801585709 countsByYear W28015857092020 @default.
• W2801585709 countsByYear W28015857092021 @default.
• W2801585709 countsByYear W28015857092022 @default.
• W2801585709 countsByYear W28015857092023 @default.
• W2801585709 crossrefType "journal-article" @default.
• W2801585709 hasAuthorship W2801585709A5013691634 @default.
• W2801585709 hasAuthorship W2801585709A5038806083 @default.
• W2801585709 hasAuthorship W2801585709A5044227206 @default.
• W2801585709 hasAuthorship W2801585709A5049372409 @default.
• W2801585709 hasAuthorship W2801585709A5051533773 @default.
• W2801585709 hasAuthorship W2801585709A5053436378 @default.
• W2801585709 hasAuthorship W2801585709A5057977985 @default.
• W2801585709 hasAuthorship W2801585709A5058429770 @default.
• W2801585709 hasAuthorship W2801585709A5089383440 @default.
• W2801585709 hasBestOaLocation W28015857092 @default.
• W2801585709 hasConcept C108583219 @default.
• W2801585709 hasConcept C11413529 @default.
• W2801585709 hasConcept C115961682 @default.
• W2801585709 hasConcept C141379421 @default.
• W2801585709 hasConcept C146849305 @default.
• W2801585709 hasConcept C153180895 @default.
• W2801585709 hasConcept C154945302 @default.
• W2801585709 hasConcept C163294075 @default.
• W2801585709 hasConcept C29265498 @default.
• W2801585709 hasConcept C41008148 @default.
• W2801585709 hasConcept C81363708 @default.
• W2801585709 hasConcept C99498987 @default.
• W2801585709 hasConceptScore W2801585709C108583219 @default.
• W2801585709 hasConceptScore W2801585709C11413529 @default.
• W2801585709 hasConceptScore W2801585709C115961682 @default.
• W2801585709 hasConceptScore W2801585709C141379421 @default.
• W2801585709 hasConceptScore W2801585709C146849305 @default.
• W2801585709 hasConceptScore W2801585709C153180895 @default.
• W2801585709 hasConceptScore W2801585709C154945302 @default.
• W2801585709 hasConceptScore W2801585709C163294075 @default.
• W2801585709 hasConceptScore W2801585709C29265498 @default.
• W2801585709 hasConceptScore W2801585709C41008148 @default.
• W2801585709 hasConceptScore W2801585709C81363708 @default.
• W2801585709 hasConceptScore W2801585709C99498987 @default.
• W2801585709 hasIssue "6" @default.
• W2801585709 hasLocation W28015857091 @default.
• W2801585709 hasLocation W28015857092 @default.
• W2801585709 hasLocation W28015857093 @default.
• W2801585709 hasLocation W28015857094 @default.
• W2801585709 hasOpenAccess W2801585709 @default.
• W2801585709 hasPrimaryLocation W28015857091 @default.
• W2801585709 hasRelatedWork W2542218918 @default.
• W2801585709 hasRelatedWork W2732542196 @default.
• W2801585709 hasRelatedWork W2738221750 @default.
• W2801585709 hasRelatedWork W2751100193 @default.
• W2801585709 hasRelatedWork W2774444957 @default.

• next