FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3193576071> ?p ?o ?g. }

• W3193576071 endingPage "103786" @default.
• W3193576071 startingPage "103786" @default.
• W3193576071 abstract "To develop and validate a layered deep learning algorithm which automatically creates three-dimensional (3D) surface models of the human mandible out of cone-beam computed tomography (CBCT) imaging. Two convolutional networks using a 3D U-Net architecture were combined and deployed in a cloud-based artificial intelligence (AI) model. The AI model was trained in two phases and iteratively improved to optimize the segmentation result using 160 anonymized full skull CBCT scans of orthognathic surgery patients (70 preoperative scans and 90 postoperative scans). Finally, the final AI model was tested by assessing timing, consistency, and accuracy on a separate testing dataset of 15 pre- and 15 postoperative full skull CBCT scans. The AI model was compared to user refined AI segmentations (RAI) and to semi-automatic segmentation (SA), which is the current clinical standard. The time needed for segmentation was measured in seconds. Intra- and inter-operator consistency were assessed to check if the segmentation protocols delivered reproducible results. The following consistency metrics were used: intersection over union (IoU), dice similarity coefficient (DSC), Hausdorff distance (HD), absolute volume difference and root mean square (RMS) distance. To evaluate the match of the AI and RAI results to those of the SA method, their accuracy was measured using IoU, DSC, HD, absolute volume difference and RMS distance. On average, SA took 1218.4s. RAI showed a significant drop (p<0.0001) in timing to 456.5s (2.7-fold decrease). The AI method only took 17s (71.3-fold decrease). The average intra-operator IoU for RAI was 99.5% compared to 96.9% for SA. For inter-operator consistency, RAI scored an IoU of 99.6% compared to 94.6% for SA. The AI method was always consistent by default. In both the intra- and inter-operator consistency assessments, RAI outperformed SA on all metrics indicative of better consistency. With SA as the ground truth, AI and RAI scored an IoU of 94.6% and 94.4%, respectively. All accuracy metrics were similar for AI and RAI, meaning that both methods produce 3D models that closely match those produced by SA. A layered 3D U-Net architecture deep learning algorithm, with and without additional user refinements, improves time-efficiency, reduces operator error, and provides excellent accuracy when benchmarked against the clinical standard. Semi-automatic segmentation in CBCT imaging is time-consuming and allows user-induced errors. Layered convolutional neural networks using a 3D U-Net architecture allow direct segmentation of high-resolution CBCT images. This approach creates 3D mandibular models in a more time-efficient and consistent way. It is accurate when benchmarked to semi-automatic segmentation." @default.
• W3193576071 created "2021-08-30" @default.
• W3193576071 creator A5002015279 @default.
• W3193576071 creator A5006036825 @default.
• W3193576071 creator A5025767182 @default.
• W3193576071 creator A5026867230 @default.
• W3193576071 creator A5041955556 @default.
• W3193576071 creator A5042940223 @default.
• W3193576071 creator A5043253661 @default.
• W3193576071 creator A5076456853 @default.
• W3193576071 creator A5081643670 @default.
• W3193576071 creator A5087990309 @default.
• W3193576071 date "2021-11-01" @default.
• W3193576071 modified "2023-10-12" @default.
• W3193576071 title "Layered deep learning for automatic mandibular segmentation in cone-beam computed tomography" @default.
• W3193576071 cites W1973569499 @default.
• W3193576071 cites W2032081375 @default.
• W3193576071 cites W2063068378 @default.
• W3193576071 cites W2101926813 @default.
• W3193576071 cites W2147800946 @default.
• W3193576071 cites W2161780882 @default.
• W3193576071 cites W2170607862 @default.
• W3193576071 cites W2206910287 @default.
• W3193576071 cites W2562643378 @default.
• W3193576071 cites W2618530766 @default.
• W3193576071 cites W2763160469 @default.
• W3193576071 cites W2809352434 @default.
• W3193576071 cites W2888529080 @default.
• W3193576071 cites W2888667538 @default.
• W3193576071 cites W2956095506 @default.
• W3193576071 cites W2970786890 @default.
• W3193576071 cites W2996774366 @default.
• W3193576071 cites W2999934826 @default.
• W3193576071 cites W3004868960 @default.
• W3193576071 cites W3015126388 @default.
• W3193576071 cites W3047537895 @default.
• W3193576071 cites W3116495124 @default.
• W3193576071 cites W3118849169 @default.
• W3193576071 cites W3130719814 @default.
• W3193576071 cites W3132455321 @default.
• W3193576071 cites W3141513209 @default.
• W3193576071 cites W3158130713 @default.
• W3193576071 cites W4238100585 @default.
• W3193576071 doi "https://doi.org/10.1016/j.jdent.2021.103786" @default.
• W3193576071 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34425172" @default.
• W3193576071 hasPublicationYear "2021" @default.
• W3193576071 type Work @default.
• W3193576071 sameAs 3193576071 @default.
• W3193576071 citedByCount "40" @default.
• W3193576071 countsByYear W31935760712022 @default.
• W3193576071 countsByYear W31935760712023 @default.
• W3193576071 crossrefType "journal-article" @default.
• W3193576071 hasAuthorship W3193576071A5002015279 @default.
• W3193576071 hasAuthorship W3193576071A5006036825 @default.
• W3193576071 hasAuthorship W3193576071A5025767182 @default.
• W3193576071 hasAuthorship W3193576071A5026867230 @default.
• W3193576071 hasAuthorship W3193576071A5041955556 @default.
• W3193576071 hasAuthorship W3193576071A5042940223 @default.
• W3193576071 hasAuthorship W3193576071A5043253661 @default.
• W3193576071 hasAuthorship W3193576071A5076456853 @default.
• W3193576071 hasAuthorship W3193576071A5081643670 @default.
• W3193576071 hasAuthorship W3193576071A5087990309 @default.
• W3193576071 hasBestOaLocation W31935760712 @default.
• W3193576071 hasConcept C108583219 @default.
• W3193576071 hasConcept C126838900 @default.
• W3193576071 hasConcept C141898687 @default.
• W3193576071 hasConcept C153180895 @default.
• W3193576071 hasConcept C154945302 @default.
• W3193576071 hasConcept C2776436953 @default.
• W3193576071 hasConcept C2779813781 @default.
• W3193576071 hasConcept C2989005 @default.
• W3193576071 hasConcept C41008148 @default.
• W3193576071 hasConcept C544519230 @default.
• W3193576071 hasConcept C71924100 @default.
• W3193576071 hasConcept C89600930 @default.
• W3193576071 hasConceptScore W3193576071C108583219 @default.
• W3193576071 hasConceptScore W3193576071C126838900 @default.
• W3193576071 hasConceptScore W3193576071C141898687 @default.
• W3193576071 hasConceptScore W3193576071C153180895 @default.
• W3193576071 hasConceptScore W3193576071C154945302 @default.
• W3193576071 hasConceptScore W3193576071C2776436953 @default.
• W3193576071 hasConceptScore W3193576071C2779813781 @default.
• W3193576071 hasConceptScore W3193576071C2989005 @default.
• W3193576071 hasConceptScore W3193576071C41008148 @default.
• W3193576071 hasConceptScore W3193576071C544519230 @default.
• W3193576071 hasConceptScore W3193576071C71924100 @default.
• W3193576071 hasConceptScore W3193576071C89600930 @default.
• W3193576071 hasFunder F4320313460 @default.
• W3193576071 hasLocation W31935760711 @default.
• W3193576071 hasLocation W31935760712 @default.
• W3193576071 hasLocation W31935760713 @default.
• W3193576071 hasOpenAccess W3193576071 @default.
• W3193576071 hasPrimaryLocation W31935760711 @default.
• W3193576071 hasRelatedWork W1942697116 @default.
• W3193576071 hasRelatedWork W2136359393 @default.
• W3193576071 hasRelatedWork W3047746737 @default.
• W3193576071 hasRelatedWork W3125779006 @default.
• W3193576071 hasRelatedWork W3197673523 @default.

• next