FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2898099302> ?p ?o ?g. }

• W2898099302 endingPage "115" @default.
• W2898099302 startingPage "104" @default.
• W2898099302 abstract "Purpose Sparsely sampled computed tomography (CT) has been attracting attention as a technique that can reduce the high radiation dose of conventional CT. In general, iterative reconstruction techniques have been applied to sparsely sampled CT to realize high quality images. These methodologies require high computing power due to the modeling of the system and the trajectory of radiation rays. Therefore, the purpose of this study was to obtain high quality three-dimensional (3D) reconstructed images with deep learning under sparse sampling conditions. Methods We used a deep learning model based on a fully convolutional network and a wavelet transform to predict high quality images. To reduce the spatial resolution loss of predicted images, we replaced the pooling layer with a wavelet transform. Three different domains were evaluated — the sinogram domain, the image domain, and the hybrid domain — to optimize a reconstruction technique based on deep learning. To train and develop a deep learning model, The Cancer Imaging Archive (TCIA) dataset was used. Results Streak artifacts, which generally occur under sparse sampling conditions, were effectively removed from deep learning-based sparsely sampled reconstructed images. However, image characteristics of fine structures varied depending on the application of deep learning technologies. The use of deep learning techniques in the sinogram domain removed streak artifacts well, but some image noise remained. Likewise, when applying deep learning technology to the image domain, a blurring effect occurred. The proposed hybrid domain sparsely sampled reconstruction based on deep learning was able to restore images to a quality similar to fully sampled images. The structural similarity (SSIM) index values of sparsely sampled CT reconstruction based on deep learning technology were 0.85 or higher. Among the three domains studied, the hybrid domain techniques achieved the highest SSIM index values (0.9 or more). Conclusion We proposed a method of sparsely sampled CT reconstruction from a new perspective — unlike iterative reconstruction. In addition, we developed an optimal deep learning-based sparse sampling reconstruction technique by evaluating image quality with deep learning technologies." @default.
• W2898099302 created "2018-11-02" @default.
• W2898099302 creator A5008863789 @default.
• W2898099302 creator A5013341396 @default.
• W2898099302 creator A5065309573 @default.
• W2898099302 date "2018-11-28" @default.
• W2898099302 modified "2023-10-17" @default.
• W2898099302 title "High quality imaging from sparsely sampled computed tomography data with deep learning and wavelet transform in various domains" @default.
• W2898099302 cites W1899329334 @default.
• W2898099302 cites W1901129140 @default.
• W2898099302 cites W1972663706 @default.
• W2898099302 cites W1987844103 @default.
• W2898099302 cites W2003832256 @default.
• W2898099302 cites W2004210109 @default.
• W2898099302 cites W2005089986 @default.
• W2898099302 cites W2015861736 @default.
• W2898099302 cites W2017399967 @default.
• W2898099302 cites W2020820596 @default.
• W2898099302 cites W2037067321 @default.
• W2898099302 cites W2039311608 @default.
• W2898099302 cites W2064076387 @default.
• W2898099302 cites W2081373027 @default.
• W2898099302 cites W2096309518 @default.
• W2898099302 cites W2121039635 @default.
• W2898099302 cites W2122897083 @default.
• W2898099302 cites W2135143650 @default.
• W2898099302 cites W2142224912 @default.
• W2898099302 cites W2145287260 @default.
• W2898099302 cites W2152613426 @default.
• W2898099302 cites W2153777140 @default.
• W2898099302 cites W2167403983 @default.
• W2898099302 cites W2253429366 @default.
• W2898099302 cites W2331143823 @default.
• W2898099302 cites W2341106171 @default.
• W2898099302 cites W2345010043 @default.
• W2898099302 cites W2395611524 @default.
• W2898099302 cites W2501312908 @default.
• W2898099302 cites W2559597482 @default.
• W2898099302 cites W2592929672 @default.
• W2898099302 cites W2776327255 @default.
• W2898099302 cites W2777802649 @default.
• W2898099302 cites W2785821534 @default.
• W2898099302 cites W2791154958 @default.
• W2898099302 cites W2792124974 @default.
• W2898099302 cites W2919115771 @default.
• W2898099302 cites W2962914239 @default.
• W2898099302 cites W2963392702 @default.
• W2898099302 cites W3104324122 @default.
• W2898099302 doi "https://doi.org/10.1002/mp.13258" @default.
• W2898099302 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30362117" @default.
• W2898099302 hasPublicationYear "2018" @default.
• W2898099302 type Work @default.
• W2898099302 sameAs 2898099302 @default.
• W2898099302 citedByCount "37" @default.
• W2898099302 countsByYear W28980993022019 @default.
• W2898099302 countsByYear W28980993022020 @default.
• W2898099302 countsByYear W28980993022021 @default.
• W2898099302 countsByYear W28980993022022 @default.
• W2898099302 countsByYear W28980993022023 @default.
• W2898099302 crossrefType "journal-article" @default.
• W2898099302 hasAuthorship W2898099302A5008863789 @default.
• W2898099302 hasAuthorship W2898099302A5013341396 @default.
• W2898099302 hasAuthorship W2898099302A5065309573 @default.
• W2898099302 hasBestOaLocation W28980993021 @default.
• W2898099302 hasConcept C108583219 @default.
• W2898099302 hasConcept C115961682 @default.
• W2898099302 hasConcept C120665830 @default.
• W2898099302 hasConcept C121332964 @default.
• W2898099302 hasConcept C141379421 @default.
• W2898099302 hasConcept C153180895 @default.
• W2898099302 hasConcept C154945302 @default.
• W2898099302 hasConcept C31972630 @default.
• W2898099302 hasConcept C41008148 @default.
• W2898099302 hasConcept C47432892 @default.
• W2898099302 hasConcept C55020928 @default.
• W2898099302 hasConcept C65185188 @default.
• W2898099302 hasConcept C81363708 @default.
• W2898099302 hasConceptScore W2898099302C108583219 @default.
• W2898099302 hasConceptScore W2898099302C115961682 @default.
• W2898099302 hasConceptScore W2898099302C120665830 @default.
• W2898099302 hasConceptScore W2898099302C121332964 @default.
• W2898099302 hasConceptScore W2898099302C141379421 @default.
• W2898099302 hasConceptScore W2898099302C153180895 @default.
• W2898099302 hasConceptScore W2898099302C154945302 @default.
• W2898099302 hasConceptScore W2898099302C31972630 @default.
• W2898099302 hasConceptScore W2898099302C41008148 @default.
• W2898099302 hasConceptScore W2898099302C47432892 @default.
• W2898099302 hasConceptScore W2898099302C55020928 @default.
• W2898099302 hasConceptScore W2898099302C65185188 @default.
• W2898099302 hasConceptScore W2898099302C81363708 @default.
• W2898099302 hasFunder F4320322120 @default.
• W2898099302 hasIssue "1" @default.
• W2898099302 hasLocation W28980993021 @default.
• W2898099302 hasLocation W28980993022 @default.
• W2898099302 hasOpenAccess W2898099302 @default.
• W2898099302 hasPrimaryLocation W28980993021 @default.
• W2898099302 hasRelatedWork W2731899572 @default.
• W2898099302 hasRelatedWork W2732542196 @default.

• next