FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210363615> ?p ?o ?g. }

• W3210363615 endingPage "237" @default.
• W3210363615 startingPage "229" @default.
• W3210363615 abstract "Abstract Purpose This study aims at exploiting artificial intelligence (AI) for the identification, segmentation and quantification of COVID-19 pulmonary lesions. The limited data availability and the annotation quality are relevant factors in training AI-methods. We investigated the effects of using multiple datasets, heterogeneously populated and annotated according to different criteria. Methods We developed an automated analysis pipeline, the LungQuant system, based on a cascade of two U-nets. The first one (U-net $$_1$$ <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML> <mml:msub> <mml:mrow /> <mml:mn>1</mml:mn> </mml:msub> </mml:math> ) is devoted to the identification of the lung parenchyma; the second one (U-net $$_2$$ <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML> <mml:msub> <mml:mrow /> <mml:mn>2</mml:mn> </mml:msub> </mml:math> ) acts on a bounding box enclosing the segmented lungs to identify the areas affected by COVID-19 lesions. Different public datasets were used to train the U-nets and to evaluate their segmentation performances, which have been quantified in terms of the Dice Similarity Coefficients. The accuracy in predicting the CT-Severity Score (CT-SS) of the LungQuant system has been also evaluated. Results Both the volumetric DSC (vDSC) and the accuracy showed a dependency on the annotation quality of the released data samples. On an independent dataset (COVID-19-CT-Seg), both the vDSC and the surface DSC (sDSC) were measured between the masks predicted by LungQuant system and the reference ones. The vDSC (sDSC) values of 0.95±0.01 and 0.66±0.13 (0.95±0.02 and 0.76±0.18, with 5 mm tolerance) were obtained for the segmentation of lungs and COVID-19 lesions, respectively. The system achieved an accuracy of 90% in CT-SS identification on this benchmark dataset. Conclusion We analysed the impact of using data samples with different annotation criteria in training an AI-based quantification system for pulmonary involvement in COVID-19 pneumonia. In terms of vDSC measures, the U-net segmentation strongly depends on the quality of the lesion annotations. Nevertheless, the CT-SS can be accurately predicted on independent test sets, demonstrating the satisfactory generalization ability of the LungQuant ." @default.
• W3210363615 created "2021-11-08" @default.
• W3210363615 creator A5002508453 @default.
• W3210363615 creator A5004460160 @default.
• W3210363615 creator A5011316927 @default.
• W3210363615 creator A5028619082 @default.
• W3210363615 creator A5030507808 @default.
• W3210363615 creator A5050300810 @default.
• W3210363615 creator A5053090175 @default.
• W3210363615 creator A5053399221 @default.
• W3210363615 creator A5058175158 @default.
• W3210363615 creator A5066058802 @default.
• W3210363615 creator A5066629135 @default.
• W3210363615 creator A5073489967 @default.
• W3210363615 creator A5079827499 @default.
• W3210363615 creator A5088889549 @default.
• W3210363615 date "2021-10-26" @default.
• W3210363615 modified "2023-10-12" @default.
• W3210363615 title "Quantification of pulmonary involvement in COVID-19 pneumonia by means of a cascade of two U-nets: training and assessment on multiple datasets using different annotation criteria" @default.
• W3210363615 cites W1901129140 @default.
• W3210363615 cites W2950086191 @default.
• W3210363615 cites W3026637813 @default.
• W3210363615 cites W3033130830 @default.
• W3210363615 cites W3035367255 @default.
• W3210363615 cites W3045596310 @default.
• W3210363615 cites W3047489308 @default.
• W3210363615 cites W3054666633 @default.
• W3210363615 cites W3098046820 @default.
• W3210363615 cites W3115781494 @default.
• W3210363615 cites W3121234312 @default.
• W3210363615 cites W3165529692 @default.
• W3210363615 doi "https://doi.org/10.1007/s11548-021-02501-2" @default.
• W3210363615 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8547130" @default.
• W3210363615 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34698988" @default.
• W3210363615 hasPublicationYear "2021" @default.
• W3210363615 type Work @default.
• W3210363615 sameAs 3210363615 @default.
• W3210363615 citedByCount "7" @default.
• W3210363615 countsByYear W32103636152021 @default.
• W3210363615 countsByYear W32103636152022 @default.
• W3210363615 countsByYear W32103636152023 @default.
• W3210363615 crossrefType "journal-article" @default.
• W3210363615 hasAuthorship W3210363615A5002508453 @default.
• W3210363615 hasAuthorship W3210363615A5004460160 @default.
• W3210363615 hasAuthorship W3210363615A5011316927 @default.
• W3210363615 hasAuthorship W3210363615A5028619082 @default.
• W3210363615 hasAuthorship W3210363615A5030507808 @default.
• W3210363615 hasAuthorship W3210363615A5050300810 @default.
• W3210363615 hasAuthorship W3210363615A5053090175 @default.
• W3210363615 hasAuthorship W3210363615A5053399221 @default.
• W3210363615 hasAuthorship W3210363615A5058175158 @default.
• W3210363615 hasAuthorship W3210363615A5066058802 @default.
• W3210363615 hasAuthorship W3210363615A5066629135 @default.
• W3210363615 hasAuthorship W3210363615A5073489967 @default.
• W3210363615 hasAuthorship W3210363615A5079827499 @default.
• W3210363615 hasAuthorship W3210363615A5088889549 @default.
• W3210363615 hasBestOaLocation W32103636151 @default.
• W3210363615 hasConcept C11413529 @default.
• W3210363615 hasConcept C116834253 @default.
• W3210363615 hasConcept C119857082 @default.
• W3210363615 hasConcept C142724271 @default.
• W3210363615 hasConcept C154945302 @default.
• W3210363615 hasConcept C2776321320 @default.
• W3210363615 hasConcept C2779134260 @default.
• W3210363615 hasConcept C3008058167 @default.
• W3210363615 hasConcept C41008148 @default.
• W3210363615 hasConcept C524204448 @default.
• W3210363615 hasConcept C59822182 @default.
• W3210363615 hasConcept C71924100 @default.
• W3210363615 hasConcept C86803240 @default.
• W3210363615 hasConcept C89600930 @default.
• W3210363615 hasConceptScore W3210363615C11413529 @default.
• W3210363615 hasConceptScore W3210363615C116834253 @default.
• W3210363615 hasConceptScore W3210363615C119857082 @default.
• W3210363615 hasConceptScore W3210363615C142724271 @default.
• W3210363615 hasConceptScore W3210363615C154945302 @default.
• W3210363615 hasConceptScore W3210363615C2776321320 @default.
• W3210363615 hasConceptScore W3210363615C2779134260 @default.
• W3210363615 hasConceptScore W3210363615C3008058167 @default.
• W3210363615 hasConceptScore W3210363615C41008148 @default.
• W3210363615 hasConceptScore W3210363615C524204448 @default.
• W3210363615 hasConceptScore W3210363615C59822182 @default.
• W3210363615 hasConceptScore W3210363615C71924100 @default.
• W3210363615 hasConceptScore W3210363615C86803240 @default.
• W3210363615 hasConceptScore W3210363615C89600930 @default.
• W3210363615 hasFunder F4320311012 @default.
• W3210363615 hasIssue "2" @default.
• W3210363615 hasLocation W32103636151 @default.
• W3210363615 hasLocation W32103636152 @default.
• W3210363615 hasLocation W32103636153 @default.
• W3210363615 hasOpenAccess W3210363615 @default.
• W3210363615 hasPrimaryLocation W32103636151 @default.
• W3210363615 hasRelatedWork W1533177136 @default.
• W3210363615 hasRelatedWork W2218034408 @default.
• W3210363615 hasRelatedWork W2263699433 @default.
• W3210363615 hasRelatedWork W2358755282 @default.
• W3210363615 hasRelatedWork W2361861616 @default.
• W3210363615 hasRelatedWork W2377979023 @default.

• next