Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199202390> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3199202390 endingPage "487" @default.
- W3199202390 startingPage "478" @default.
- W3199202390 abstract "Dental landmark localization is a fundamental step to analyzing dental models in the planning of orthodontic or orthognathic surgery. However, current clinical practices require clinicians to manually digitize more than 60 landmarks on 3D dental models. Automatic methods to detect landmarks can release clinicians from the tedious labor of manual annotation and improve localization accuracy. Most existing landmark detection methods fail to capture local geometric contexts, causing large errors and misdetections. We propose an end-to-end learning framework to automatically localize 68 landmarks on high-resolution dental surfaces. Our network hierarchically extracts multi-scale local contextual features along two paths: a landmark localization path and a landmark area-of-interest segmentation path. Higher-level features are learned by combining local-to-global features from the two paths by feature fusion to predict the landmark heatmap and the landmark area segmentation map. An attention mechanism is then applied to the two maps to refine the landmark position. We evaluated our framework on a real-patient dataset consisting of 77 high-resolution dental surfaces. Our approach achieves an average localization error of 0.42 mm, significantly outperforming related start-of-the-art methods." @default.
- W3199202390 created "2021-09-27" @default.
- W3199202390 creator A5000641105 @default.
- W3199202390 creator A5012191313 @default.
- W3199202390 creator A5012191915 @default.
- W3199202390 creator A5015071060 @default.
- W3199202390 creator A5023955845 @default.
- W3199202390 creator A5028576035 @default.
- W3199202390 creator A5054315643 @default.
- W3199202390 creator A5077300873 @default.
- W3199202390 date "2021-01-01" @default.
- W3199202390 modified "2023-10-18" @default.
- W3199202390 title "DLLNet: An Attention-Based Deep Learning Method for Dental Landmark Localization on High-Resolution 3D Digital Dental Models" @default.
- W3199202390 cites W1903029394 @default.
- W3199202390 cites W1982424300 @default.
- W3199202390 cites W2525974879 @default.
- W3199202390 cites W2724710774 @default.
- W3199202390 cites W2737081152 @default.
- W3199202390 cites W2752415006 @default.
- W3199202390 cites W2942086449 @default.
- W3199202390 cites W2963231572 @default.
- W3199202390 cites W2972520432 @default.
- W3199202390 cites W2982772166 @default.
- W3199202390 cites W3004849003 @default.
- W3199202390 cites W3034365175 @default.
- W3199202390 doi "https://doi.org/10.1007/978-3-030-87202-1_46" @default.
- W3199202390 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34927177" @default.
- W3199202390 hasPublicationYear "2021" @default.
- W3199202390 type Work @default.
- W3199202390 sameAs 3199202390 @default.
- W3199202390 citedByCount "4" @default.
- W3199202390 countsByYear W31992023902022 @default.
- W3199202390 crossrefType "book-chapter" @default.
- W3199202390 hasAuthorship W3199202390A5000641105 @default.
- W3199202390 hasAuthorship W3199202390A5012191313 @default.
- W3199202390 hasAuthorship W3199202390A5012191915 @default.
- W3199202390 hasAuthorship W3199202390A5015071060 @default.
- W3199202390 hasAuthorship W3199202390A5023955845 @default.
- W3199202390 hasAuthorship W3199202390A5028576035 @default.
- W3199202390 hasAuthorship W3199202390A5054315643 @default.
- W3199202390 hasAuthorship W3199202390A5077300873 @default.
- W3199202390 hasBestOaLocation W31992023902 @default.
- W3199202390 hasConcept C138885662 @default.
- W3199202390 hasConcept C153180895 @default.
- W3199202390 hasConcept C154945302 @default.
- W3199202390 hasConcept C2776401178 @default.
- W3199202390 hasConcept C2780297707 @default.
- W3199202390 hasConcept C31972630 @default.
- W3199202390 hasConcept C41008148 @default.
- W3199202390 hasConcept C41895202 @default.
- W3199202390 hasConcept C89600930 @default.
- W3199202390 hasConceptScore W3199202390C138885662 @default.
- W3199202390 hasConceptScore W3199202390C153180895 @default.
- W3199202390 hasConceptScore W3199202390C154945302 @default.
- W3199202390 hasConceptScore W3199202390C2776401178 @default.
- W3199202390 hasConceptScore W3199202390C2780297707 @default.
- W3199202390 hasConceptScore W3199202390C31972630 @default.
- W3199202390 hasConceptScore W3199202390C41008148 @default.
- W3199202390 hasConceptScore W3199202390C41895202 @default.
- W3199202390 hasConceptScore W3199202390C89600930 @default.
- W3199202390 hasLocation W31992023901 @default.
- W3199202390 hasLocation W31992023902 @default.
- W3199202390 hasLocation W31992023903 @default.
- W3199202390 hasOpenAccess W3199202390 @default.
- W3199202390 hasPrimaryLocation W31992023901 @default.
- W3199202390 hasRelatedWork W166366606 @default.
- W3199202390 hasRelatedWork W2016546218 @default.
- W3199202390 hasRelatedWork W2098911910 @default.
- W3199202390 hasRelatedWork W2148343984 @default.
- W3199202390 hasRelatedWork W2352223314 @default.
- W3199202390 hasRelatedWork W2509104183 @default.
- W3199202390 hasRelatedWork W2509618504 @default.
- W3199202390 hasRelatedWork W2970216048 @default.
- W3199202390 hasRelatedWork W586143910 @default.
- W3199202390 hasRelatedWork W2156243485 @default.
- W3199202390 isParatext "false" @default.
- W3199202390 isRetracted "false" @default.
- W3199202390 magId "3199202390" @default.
- W3199202390 workType "book-chapter" @default.