FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381513963> ?p ?o ?g. }

• W4381513963 endingPage "104588" @default.
• W4381513963 startingPage "104588" @default.
• W4381513963 abstract "Periapical radiographs are oftentimes taken in series to display all teeth present in the oral cavity. Our aim was to automatically assemble such a series of periapical radiographs into an anatomically correct status using a multi-modal deep learning model.4,707 periapical images from 387 patients (on average, 12 images per patient) were used. Radiographs were labeled according to their field of view and the dataset split into a training, validation, and test set, stratified by patient. In addition to the radiograph the timestamp of image generation was extracted and abstracted as follows: A matrix, containing the normalized timestamps of all images of a patient was constructed, representing the order in which images were taken, providing temporal context information to the deep learning model. Using the image data together with the time sequence data a multi-modal deep learning model consisting of two residual convolutional neural networks (ResNet-152 for image data, ResNet-50 for time data) was trained. Additionally, two uni-modal models were trained on image data and time data, respectively. A custom scoring technique was used to measure model performance.Multi-modal deep learning outperformed both uni-modal image-based learning (p<0.001) and time-based learning (p<0.05). The multi-modal deep learning model predicted tooth labels with an F1-score, sensitivity and precision of 0.79, respectively, and an accuracy of 0.99. 37 out of 77 patient datasets were fully correctly assembled by multi-modal learning; in the remaining ones, usually only one image was incorrectly labeled.Multi-modal modeling allowed automated assembly of periapical radiographs and outperformed both uni-modal models. Dental machine learning models can benefit from additional data modalities.Like humans, deep learning models may profit from multiple data sources for decision-making. We demonstrate how multi-modal learning can assist assembling periapical radiographs into an anatomically correct status. Multi-modal learning should be considered for more complex tasks, as clinically a wealth of data is usually available and could be leveraged." @default.
• W4381513963 created "2023-06-22" @default.
• W4381513963 creator A5007784163 @default.
• W4381513963 creator A5033498552 @default.
• W4381513963 creator A5063934370 @default.
• W4381513963 creator A5064671722 @default.
• W4381513963 creator A5065895211 @default.
• W4381513963 creator A5092225255 @default.
• W4381513963 date "2023-08-01" @default.
• W4381513963 modified "2023-10-02" @default.
• W4381513963 title "Multi-modal deep learning for automated assembly of periapical radiographs" @default.
• W4381513963 cites W2028760666 @default.
• W4381513963 cites W2035996655 @default.
• W4381513963 cites W2602382095 @default.
• W4381513963 cites W2619383789 @default.
• W4381513963 cites W2892035503 @default.
• W4381513963 cites W2968847082 @default.
• W4381513963 cites W3112990870 @default.
• W4381513963 cites W3130719814 @default.
• W4381513963 cites W3138815386 @default.
• W4381513963 cites W3147177562 @default.
• W4381513963 cites W3159142334 @default.
• W4381513963 cites W3176016422 @default.
• W4381513963 cites W3182250456 @default.
• W4381513963 cites W3197040406 @default.
• W4381513963 cites W3205594709 @default.
• W4381513963 cites W4220976109 @default.
• W4381513963 cites W4224947621 @default.
• W4381513963 cites W4288068807 @default.
• W4381513963 cites W4294151811 @default.
• W4381513963 cites W4295951577 @default.
• W4381513963 cites W4304014045 @default.
• W4381513963 cites W4308885870 @default.
• W4381513963 doi "https://doi.org/10.1016/j.jdent.2023.104588" @default.
• W4381513963 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37348642" @default.
• W4381513963 hasPublicationYear "2023" @default.
• W4381513963 type Work @default.
• W4381513963 citedByCount "0" @default.
• W4381513963 crossrefType "journal-article" @default.
• W4381513963 hasAuthorship W4381513963A5007784163 @default.
• W4381513963 hasAuthorship W4381513963A5033498552 @default.
• W4381513963 hasAuthorship W4381513963A5063934370 @default.
• W4381513963 hasAuthorship W4381513963A5064671722 @default.
• W4381513963 hasAuthorship W4381513963A5065895211 @default.
• W4381513963 hasAuthorship W4381513963A5092225255 @default.
• W4381513963 hasConcept C108583219 @default.
• W4381513963 hasConcept C113954288 @default.
• W4381513963 hasConcept C126838900 @default.
• W4381513963 hasConcept C151730666 @default.
• W4381513963 hasConcept C153180895 @default.
• W4381513963 hasConcept C154945302 @default.
• W4381513963 hasConcept C185592680 @default.
• W4381513963 hasConcept C188027245 @default.
• W4381513963 hasConcept C2779343474 @default.
• W4381513963 hasConcept C36454342 @default.
• W4381513963 hasConcept C38652104 @default.
• W4381513963 hasConcept C41008148 @default.
• W4381513963 hasConcept C58489278 @default.
• W4381513963 hasConcept C71139939 @default.
• W4381513963 hasConcept C71924100 @default.
• W4381513963 hasConcept C81363708 @default.
• W4381513963 hasConcept C86803240 @default.
• W4381513963 hasConceptScore W4381513963C108583219 @default.
• W4381513963 hasConceptScore W4381513963C113954288 @default.
• W4381513963 hasConceptScore W4381513963C126838900 @default.
• W4381513963 hasConceptScore W4381513963C151730666 @default.
• W4381513963 hasConceptScore W4381513963C153180895 @default.
• W4381513963 hasConceptScore W4381513963C154945302 @default.
• W4381513963 hasConceptScore W4381513963C185592680 @default.
• W4381513963 hasConceptScore W4381513963C188027245 @default.
• W4381513963 hasConceptScore W4381513963C2779343474 @default.
• W4381513963 hasConceptScore W4381513963C36454342 @default.
• W4381513963 hasConceptScore W4381513963C38652104 @default.
• W4381513963 hasConceptScore W4381513963C41008148 @default.
• W4381513963 hasConceptScore W4381513963C58489278 @default.
• W4381513963 hasConceptScore W4381513963C71139939 @default.
• W4381513963 hasConceptScore W4381513963C71924100 @default.
• W4381513963 hasConceptScore W4381513963C81363708 @default.
• W4381513963 hasConceptScore W4381513963C86803240 @default.
• W4381513963 hasLocation W43815139631 @default.
• W4381513963 hasLocation W43815139632 @default.
• W4381513963 hasOpenAccess W4381513963 @default.
• W4381513963 hasPrimaryLocation W43815139631 @default.
• W4381513963 hasRelatedWork W2731899572 @default.
• W4381513963 hasRelatedWork W2999805992 @default.
• W4381513963 hasRelatedWork W3011074480 @default.
• W4381513963 hasRelatedWork W3116150086 @default.
• W4381513963 hasRelatedWork W3133861977 @default.
• W4381513963 hasRelatedWork W3192840557 @default.
• W4381513963 hasRelatedWork W4200173597 @default.
• W4381513963 hasRelatedWork W4291897433 @default.
• W4381513963 hasRelatedWork W4312417841 @default.
• W4381513963 hasRelatedWork W4321369474 @default.
• W4381513963 hasVolume "135" @default.
• W4381513963 isParatext "false" @default.
• W4381513963 isRetracted "false" @default.
• W4381513963 workType "article" @default.