FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4291019945> ?p ?o ?g. }

• W4291019945 abstract "Machine learning studies require a large number of images often obtained on different PET scanners. When merging these images, the use of harmonized images following EARL-standards is essential. However, when including retrospective images, EARL accreditation might not have been in place. The aim of this study was to develop a convolutional neural network (CNN) that can identify retrospectively if an image is EARL compliant and if it is meeting older or newer EARL-standards.96 PET images acquired on three PET/CT systems were included in the study. All images were reconstructed with the locally clinically preferred, EARL1, and EARL2 compliant reconstruction protocols. After image pre-processing, one CNN was trained to separate clinical and EARL compliant reconstructions. A second CNN was optimized to identify EARL1 and EARL2 compliant images. The accuracy of both CNNs was assessed using fivefold cross-validation. The CNNs were validated on 24 images acquired on a PET scanner not included in the training data. To assess the impact of image noise on the CNN decision, the 24 images were reconstructed with different scan durations.In the cross-validation, the first CNN classified all images correctly. When identifying EARL1 and EARL2 compliant images, the second CNN identified 100% EARL1 compliant and 85% EARL2 compliant images correctly. The accuracy in the independent dataset was comparable to the cross-validation accuracy. The scan duration had almost no impact on the results.The two CNNs trained in this study can be used to retrospectively include images in a multi-center setting by, e.g., adding additional smoothing. This method is especially important for machine learning studies where the harmonization of images from different PET systems is essential." @default.
• W4291019945 created "2022-08-13" @default.
• W4291019945 creator A5002279880 @default.
• W4291019945 creator A5026685751 @default.
• W4291019945 creator A5029713359 @default.
• W4291019945 creator A5038187829 @default.
• W4291019945 creator A5049912159 @default.
• W4291019945 creator A5068013617 @default.
• W4291019945 creator A5072881153 @default.
• W4291019945 creator A5087967286 @default.
• W4291019945 creator A5088874257 @default.
• W4291019945 date "2022-08-09" @default.
• W4291019945 modified "2023-10-06" @default.
• W4291019945 title "Convolutional neural networks for automatic image quality control and EARL compliance of PET images" @default.
• W4291019945 cites W1770272687 @default.
• W4291019945 cites W1871263388 @default.
• W4291019945 cites W2002052629 @default.
• W4291019945 cites W2012437716 @default.
• W4291019945 cites W2015118555 @default.
• W4291019945 cites W2088783247 @default.
• W4291019945 cites W2096719319 @default.
• W4291019945 cites W2142624390 @default.
• W4291019945 cites W2145938281 @default.
• W4291019945 cites W2165496688 @default.
• W4291019945 cites W2335867152 @default.
• W4291019945 cites W2409456704 @default.
• W4291019945 cites W2625583840 @default.
• W4291019945 cites W2790159993 @default.
• W4291019945 cites W2922107388 @default.
• W4291019945 cites W2969118048 @default.
• W4291019945 cites W2971304437 @default.
• W4291019945 cites W2997842132 @default.
• W4291019945 cites W3118104194 @default.
• W4291019945 cites W3127622022 @default.
• W4291019945 doi "https://doi.org/10.1186/s40658-022-00468-w" @default.
• W4291019945 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35943622" @default.
• W4291019945 hasPublicationYear "2022" @default.
• W4291019945 type Work @default.
• W4291019945 citedByCount "3" @default.
• W4291019945 countsByYear W42910199452023 @default.
• W4291019945 crossrefType "journal-article" @default.
• W4291019945 hasAuthorship W4291019945A5002279880 @default.
• W4291019945 hasAuthorship W4291019945A5026685751 @default.
• W4291019945 hasAuthorship W4291019945A5029713359 @default.
• W4291019945 hasAuthorship W4291019945A5038187829 @default.
• W4291019945 hasAuthorship W4291019945A5049912159 @default.
• W4291019945 hasAuthorship W4291019945A5068013617 @default.
• W4291019945 hasAuthorship W4291019945A5072881153 @default.
• W4291019945 hasAuthorship W4291019945A5087967286 @default.
• W4291019945 hasAuthorship W4291019945A5088874257 @default.
• W4291019945 hasBestOaLocation W42910199451 @default.
• W4291019945 hasConcept C108583219 @default.
• W4291019945 hasConcept C115961682 @default.
• W4291019945 hasConcept C153180895 @default.
• W4291019945 hasConcept C154945302 @default.
• W4291019945 hasConcept C2779751349 @default.
• W4291019945 hasConcept C31972630 @default.
• W4291019945 hasConcept C41008148 @default.
• W4291019945 hasConcept C55020928 @default.
• W4291019945 hasConcept C81363708 @default.
• W4291019945 hasConcept C99498987 @default.
• W4291019945 hasConceptScore W4291019945C108583219 @default.
• W4291019945 hasConceptScore W4291019945C115961682 @default.
• W4291019945 hasConceptScore W4291019945C153180895 @default.
• W4291019945 hasConceptScore W4291019945C154945302 @default.
• W4291019945 hasConceptScore W4291019945C2779751349 @default.
• W4291019945 hasConceptScore W4291019945C31972630 @default.
• W4291019945 hasConceptScore W4291019945C41008148 @default.
• W4291019945 hasConceptScore W4291019945C55020928 @default.
• W4291019945 hasConceptScore W4291019945C81363708 @default.
• W4291019945 hasConceptScore W4291019945C99498987 @default.
• W4291019945 hasIssue "1" @default.
• W4291019945 hasLocation W42910199451 @default.
• W4291019945 hasLocation W42910199452 @default.
• W4291019945 hasLocation W42910199453 @default.
• W4291019945 hasLocation W42910199454 @default.
• W4291019945 hasLocation W42910199455 @default.
• W4291019945 hasLocation W42910199456 @default.
• W4291019945 hasLocation W42910199457 @default.
• W4291019945 hasOpenAccess W4291019945 @default.
• W4291019945 hasPrimaryLocation W42910199451 @default.
• W4291019945 hasRelatedWork W2731899572 @default.
• W4291019945 hasRelatedWork W2999805992 @default.
• W4291019945 hasRelatedWork W3011074480 @default.
• W4291019945 hasRelatedWork W3116150086 @default.
• W4291019945 hasRelatedWork W3133861977 @default.
• W4291019945 hasRelatedWork W3192840557 @default.
• W4291019945 hasRelatedWork W4200173597 @default.
• W4291019945 hasRelatedWork W4291897433 @default.
• W4291019945 hasRelatedWork W4312417841 @default.
• W4291019945 hasRelatedWork W4321369474 @default.
• W4291019945 hasVolume "9" @default.
• W4291019945 isParatext "false" @default.
• W4291019945 isRetracted "false" @default.
• W4291019945 workType "article" @default.