FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313488375> ?p ?o ?g. }

• W4313488375 abstract "Chest radiographs (CXRs) are the most widely available radiographic imaging modality used to detect respiratory diseases that result in lung opacities. CXR reports often use non-standardized language that result in subjective, qualitative, and non-reproducible opacity estimates. Our goal was to develop a robust deep transfer learning framework and adapt it to estimate the degree of lung opacity from CXRs. Following CXR data selection based on exclusion criteria, segmentation schemes were used for ROI (Region Of Interest) extraction, and all combinations of segmentation, data balancing, and classification methods were tested to pick the top performing models. Multifold cross validation was used to determine the best model from the initial selected top models, based on appropriate performance metrics, as well as a novel Macro-Averaged Heatmap Concordance Score (MA HCS). Performance of the best model is compared against that of expert physician annotators, and heatmaps were produced. Finally, model performance sensitivity analysis across patient populations of interest was performed. The proposed framework was adapted to the specific use case of estimation of degree of CXR lung opacity using ordinal multiclass classification. Acquired between March 24, 2020, and May 22, 2020, 38,365 prospectively annotated CXRs from 17,418 patients were used. We tested three neural network architectures (ResNet-50, VGG-16, and ChexNet), three segmentation schemes (no segmentation, lung segmentation, and lateral segmentation based on spine detection), and three data balancing strategies (undersampling, double-stage sampling, and synthetic minority oversampling) using 38,079 CXR images for training, and validation with 286 images as the out-of-the-box dataset that underwent expert radiologist adjudication. Based on the results of these experiments, the ResNet-50 model with undersampling and no ROI segmentation is recommended for lung opacity classification, based on optimal values for the MAE metric and HCS (Heatmap Concordance Score). The degree of agreement between the opacity scores predicted by this model with respect to the two sets of radiologist scores (OR or Original Reader and OOBTR or Out Of Box Reader) in terms of performance metrics is superior to the inter-radiologist opacity score agreement." @default.
• W4313488375 created "2023-01-06" @default.
• W4313488375 creator A5018061519 @default.
• W4313488375 creator A5026931031 @default.
• W4313488375 creator A5032529565 @default.
• W4313488375 creator A5038913948 @default.
• W4313488375 creator A5068492860 @default.
• W4313488375 creator A5075591650 @default.
• W4313488375 creator A5077525711 @default.
• W4313488375 date "2023-01-03" @default.
• W4313488375 modified "2023-10-09" @default.
• W4313488375 title "A radiographic, deep transfer learning framework, adapted to estimate lung opacities from chest x-rays" @default.
• W4313488375 cites W1901129140 @default.
• W4313488375 cites W1998473914 @default.
• W4313488375 cites W2024798729 @default.
• W4313488375 cites W2142514727 @default.
• W4313488375 cites W2240067561 @default.
• W4313488375 cites W2559874490 @default.
• W4313488375 cites W2588978745 @default.
• W4313488375 cites W2809254203 @default.
• W4313488375 cites W2936503027 @default.
• W4313488375 cites W2964317695 @default.
• W4313488375 cites W2973134727 @default.
• W4313488375 cites W3020614853 @default.
• W4313488375 cites W3023402713 @default.
• W4313488375 cites W3033616466 @default.
• W4313488375 cites W3036688711 @default.
• W4313488375 cites W3045464882 @default.
• W4313488375 cites W3045975320 @default.
• W4313488375 cites W3087359029 @default.
• W4313488375 cites W3092018978 @default.
• W4313488375 cites W3092171282 @default.
• W4313488375 cites W3096778054 @default.
• W4313488375 cites W3102564565 @default.
• W4313488375 cites W3112767349 @default.
• W4313488375 cites W3122236046 @default.
• W4313488375 cites W3136933888 @default.
• W4313488375 cites W3142630538 @default.
• W4313488375 cites W3148908072 @default.
• W4313488375 cites W3156011032 @default.
• W4313488375 cites W3177044444 @default.
• W4313488375 cites W3199511737 @default.
• W4313488375 cites W3199732613 @default.
• W4313488375 cites W4200191097 @default.
• W4313488375 cites W4213123209 @default.
• W4313488375 cites W4221027618 @default.
• W4313488375 cites W4225597912 @default.
• W4313488375 cites W4283774067 @default.
• W4313488375 doi "https://doi.org/10.1186/s42234-022-00103-0" @default.
• W4313488375 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36597113" @default.
• W4313488375 hasPublicationYear "2023" @default.
• W4313488375 type Work @default.
• W4313488375 citedByCount "3" @default.
• W4313488375 countsByYear W43134883752023 @default.
• W4313488375 crossrefType "journal-article" @default.
• W4313488375 hasAuthorship W4313488375A5018061519 @default.
• W4313488375 hasAuthorship W4313488375A5026931031 @default.
• W4313488375 hasAuthorship W4313488375A5032529565 @default.
• W4313488375 hasAuthorship W4313488375A5038913948 @default.
• W4313488375 hasAuthorship W4313488375A5068492860 @default.
• W4313488375 hasAuthorship W4313488375A5075591650 @default.
• W4313488375 hasAuthorship W4313488375A5077525711 @default.
• W4313488375 hasBestOaLocation W43134883751 @default.
• W4313488375 hasConcept C126838900 @default.
• W4313488375 hasConcept C136536468 @default.
• W4313488375 hasConcept C150899416 @default.
• W4313488375 hasConcept C153180895 @default.
• W4313488375 hasConcept C154945302 @default.
• W4313488375 hasConcept C36454342 @default.
• W4313488375 hasConcept C41008148 @default.
• W4313488375 hasConcept C71924100 @default.
• W4313488375 hasConcept C89600930 @default.
• W4313488375 hasConceptScore W4313488375C126838900 @default.
• W4313488375 hasConceptScore W4313488375C136536468 @default.
• W4313488375 hasConceptScore W4313488375C150899416 @default.
• W4313488375 hasConceptScore W4313488375C153180895 @default.
• W4313488375 hasConceptScore W4313488375C154945302 @default.
• W4313488375 hasConceptScore W4313488375C36454342 @default.
• W4313488375 hasConceptScore W4313488375C41008148 @default.
• W4313488375 hasConceptScore W4313488375C71924100 @default.
• W4313488375 hasConceptScore W4313488375C89600930 @default.
• W4313488375 hasIssue "1" @default.
• W4313488375 hasLocation W43134883751 @default.
• W4313488375 hasLocation W43134883752 @default.
• W4313488375 hasLocation W43134883753 @default.
• W4313488375 hasOpenAccess W4313488375 @default.
• W4313488375 hasPrimaryLocation W43134883751 @default.
• W4313488375 hasRelatedWork W1568701304 @default.
• W4313488375 hasRelatedWork W1988052614 @default.
• W4313488375 hasRelatedWork W2411545073 @default.
• W4313488375 hasRelatedWork W2748952813 @default.
• W4313488375 hasRelatedWork W2899084033 @default.
• W4313488375 hasRelatedWork W4230773746 @default.
• W4313488375 hasRelatedWork W4235484761 @default.
• W4313488375 hasRelatedWork W4250549352 @default.
• W4313488375 hasRelatedWork W4322722608 @default.
• W4313488375 hasRelatedWork W4386041617 @default.
• W4313488375 hasVolume "9" @default.
• W4313488375 isParatext "false" @default.
• W4313488375 isRetracted "false" @default.

• next