FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313256530> ?p ?o ?g. }

• W4313256530 endingPage "101163" @default.
• W4313256530 startingPage "101163" @default.
• W4313256530 abstract "PurposeDeep learning (DL) techniques have been successful in disease prediction tasks and could improve the prediction of mandible osteoradionecrosis (ORN) resulting from head and neck cancer (HNC) radiation therapy. In this study, we retrospectively compared the performance of DL algorithms and traditional machine learning (ML) techniques to predict mandible ORN binary outcome in an extensive cohort of HNC patients.Methods and MaterialsPatients who received HNC radiation therapy at XXX from 2005 to 2015 were identified for the ML (n = 1259) and DL (n = 1236) studies. The subjects were followed for ORN development for at least 12 months, with 173 developing ORN and 1086 having no evidence of ORN. ML models used dose-volume histogram parameters to predict ORN development. These models included logistic regression, random forest, support vector machine, and a random classifier reference. DL models were based on ResNet, DenseNet, and autoencoder-based architectures. DL models used each subject's dose cropped to the mandible. The effect of increasing the amount of available training data on the DL models’ prediction performance was evaluated by training the DL models using increasing ratios of the original training data.ResultsThe F1 score for the logistic regression model, the best performing ML model, was 0.3. The best performing ResNet, DenseNet, and autoencoder-based models had F1 scores of 0.07, 0.14, and 0.23, respectively, whereas the random classifier's F1 score was 0.17. No performance increase was apparent when we increased the amount of training data available for DL model training.ConclusionsThe ML models had superior performance to their DL counterparts. The lack of improvement in DL performance with increased training data suggests that either more data is needed for appropriate DL model construction or that the image features used in DL models are not suitable for this task." @default.
• W4313256530 created "2023-01-06" @default.
• W4313256530 creator A5003923687 @default.
• W4313256530 creator A5023293646 @default.
• W4313256530 creator A5028995506 @default.
• W4313256530 creator A5071409978 @default.
• W4313256530 creator A5077206109 @default.
• W4313256530 creator A5081622824 @default.
• W4313256530 creator A5090769285 @default.
• W4313256530 date "2023-07-01" @default.
• W4313256530 modified "2023-10-16" @default.
• W4313256530 title "Comparison of Machine-Learning and Deep-Learning Methods for the Prediction of Osteoradionecrosis Resulting From Head and Neck Cancer Radiation Therapy" @default.
• W4313256530 cites W1831050183 @default.
• W4313256530 cites W1984541015 @default.
• W4313256530 cites W2006617902 @default.
• W4313256530 cites W2052192870 @default.
• W4313256530 cites W2088697320 @default.
• W4313256530 cites W2110664940 @default.
• W4313256530 cites W2124363070 @default.
• W4313256530 cites W2484551283 @default.
• W4313256530 cites W2691215197 @default.
• W4313256530 cites W2889412653 @default.
• W4313256530 cites W2896629008 @default.
• W4313256530 cites W2945326203 @default.
• W4313256530 cites W2950591923 @default.
• W4313256530 cites W2966349638 @default.
• W4313256530 cites W2968560098 @default.
• W4313256530 cites W3036562742 @default.
• W4313256530 cites W3119056788 @default.
• W4313256530 cites W3119494755 @default.
• W4313256530 cites W3120795911 @default.
• W4313256530 cites W3134475970 @default.
• W4313256530 cites W3135490782 @default.
• W4313256530 cites W3140854437 @default.
• W4313256530 cites W3160841095 @default.
• W4313256530 cites W3162617061 @default.
• W4313256530 cites W3199559025 @default.
• W4313256530 cites W4200564159 @default.
• W4313256530 cites W4206693420 @default.
• W4313256530 doi "https://doi.org/10.1016/j.adro.2022.101163" @default.
• W4313256530 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36798732" @default.
• W4313256530 hasPublicationYear "2023" @default.
• W4313256530 type Work @default.
• W4313256530 citedByCount "1" @default.
• W4313256530 countsByYear W43132565302023 @default.
• W4313256530 crossrefType "journal-article" @default.
• W4313256530 hasAuthorship W4313256530A5003923687 @default.
• W4313256530 hasAuthorship W4313256530A5023293646 @default.
• W4313256530 hasAuthorship W4313256530A5028995506 @default.
• W4313256530 hasAuthorship W4313256530A5071409978 @default.
• W4313256530 hasAuthorship W4313256530A5077206109 @default.
• W4313256530 hasAuthorship W4313256530A5081622824 @default.
• W4313256530 hasAuthorship W4313256530A5090769285 @default.
• W4313256530 hasBestOaLocation W43132565301 @default.
• W4313256530 hasConcept C101738243 @default.
• W4313256530 hasConcept C108583219 @default.
• W4313256530 hasConcept C119857082 @default.
• W4313256530 hasConcept C126322002 @default.
• W4313256530 hasConcept C141071460 @default.
• W4313256530 hasConcept C151956035 @default.
• W4313256530 hasConcept C154945302 @default.
• W4313256530 hasConcept C169258074 @default.
• W4313256530 hasConcept C2776530083 @default.
• W4313256530 hasConcept C2780037786 @default.
• W4313256530 hasConcept C41008148 @default.
• W4313256530 hasConcept C509974204 @default.
• W4313256530 hasConcept C71924100 @default.
• W4313256530 hasConcept C72563966 @default.
• W4313256530 hasConceptScore W4313256530C101738243 @default.
• W4313256530 hasConceptScore W4313256530C108583219 @default.
• W4313256530 hasConceptScore W4313256530C119857082 @default.
• W4313256530 hasConceptScore W4313256530C126322002 @default.
• W4313256530 hasConceptScore W4313256530C141071460 @default.
• W4313256530 hasConceptScore W4313256530C151956035 @default.
• W4313256530 hasConceptScore W4313256530C154945302 @default.
• W4313256530 hasConceptScore W4313256530C169258074 @default.
• W4313256530 hasConceptScore W4313256530C2776530083 @default.
• W4313256530 hasConceptScore W4313256530C2780037786 @default.
• W4313256530 hasConceptScore W4313256530C41008148 @default.
• W4313256530 hasConceptScore W4313256530C509974204 @default.
• W4313256530 hasConceptScore W4313256530C71924100 @default.
• W4313256530 hasConceptScore W4313256530C72563966 @default.
• W4313256530 hasIssue "4" @default.
• W4313256530 hasLocation W43132565301 @default.
• W4313256530 hasLocation W43132565302 @default.
• W4313256530 hasLocation W43132565303 @default.
• W4313256530 hasOpenAccess W4313256530 @default.
• W4313256530 hasPrimaryLocation W43132565301 @default.
• W4313256530 hasRelatedWork W2968586400 @default.
• W4313256530 hasRelatedWork W3044458868 @default.
• W4313256530 hasRelatedWork W3211546796 @default.
• W4313256530 hasRelatedWork W4213225422 @default.
• W4313256530 hasRelatedWork W4223564025 @default.
• W4313256530 hasRelatedWork W4226246648 @default.
• W4313256530 hasRelatedWork W4281616679 @default.
• W4313256530 hasRelatedWork W4281986673 @default.
• W4313256530 hasRelatedWork W4311106074 @default.
• W4313256530 hasRelatedWork W4322727400 @default.

• next