FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3186019557> ?p ?o ?g. }

• W3186019557 endingPage "106295" @default.
• W3186019557 startingPage "106295" @default.
• W3186019557 abstract "• Classification of tooth type from single 3D point cloud model was investigated. • Hierarchical CNN-based occlusal surface morphology was analyzed. • Image augmentations were applied to improve classification performance. • Grad-cam demonstrate smaller important region for better generality by augmented images. 3D Digitization of dental model is growing in popularity for dental application. Classification of tooth type from single 3D point cloud model without assist of relative position among teeth is still a challenging task. In this paper, 8-class posterior tooth type classification (first premolar, second premolar, first molar, second molar in maxilla and mandible respectively) was investigated by convolutional neural network (CNN)-based occlusal surface morphology analysis. 3D occlusal surface was transformed to depth image for basic CNN-based classification. Considering the logical hierarchy of tooth categories, a hierarchical classification structure was proposed to decompose 8-class classification task into two-stage cascaded classification subtasks. Image augmentations including traditional geometrical transformation and deep convolutional generative adversarial networks (DCGANs) were applied for each subnetworks and cascaded network. Results indicate that combing traditional and DCGAN-based augmented images to train CNN models can improve classification performance. In the paper, we achieve overall accuracy 91.35%, macro precision 91.49%, macro-recall 91.29%, and macro-F1 0.9139 for the 8-class posterior tooth type classification, which outperform other deep learning models. Meanwhile, Grad-cam results demonstrate that CNN model trained by our augmented images will focus on smaller important region for better generality. And anatomic landmarks of cusp, fossa, and groove work as important regions for cascaded classification model. The reported work has proved that using basic CNN to construct two-stage hierarchical structure can achieve the best classification performance of posterior tooth type in 3D model without assistance of relative position information. The proposed method has advantages of easy training, great ability to learn discriminative features from small image region." @default.
• W3186019557 created "2021-08-02" @default.
• W3186019557 creator A5002420822 @default.
• W3186019557 creator A5003582980 @default.
• W3186019557 creator A5009224402 @default.
• W3186019557 creator A5016335119 @default.
• W3186019557 creator A5027842206 @default.
• W3186019557 creator A5066640052 @default.
• W3186019557 creator A5090187041 @default.
• W3186019557 date "2021-09-01" @default.
• W3186019557 modified "2023-10-16" @default.
• W3186019557 title "Hierarchical CNN-based occlusal surface morphology analysis for classifying posterior tooth type using augmented images from 3D dental surface models" @default.
• W3186019557 cites W2018656768 @default.
• W3186019557 cites W2140735364 @default.
• W3186019557 cites W2229536762 @default.
• W3186019557 cites W2555989946 @default.
• W3186019557 cites W2772159282 @default.
• W3186019557 cites W2787760474 @default.
• W3186019557 cites W2794022343 @default.
• W3186019557 cites W2804967795 @default.
• W3186019557 cites W2890018557 @default.
• W3186019557 cites W2890139949 @default.
• W3186019557 cites W2896196878 @default.
• W3186019557 cites W2899198451 @default.
• W3186019557 cites W2918471352 @default.
• W3186019557 cites W2942304876 @default.
• W3186019557 cites W2951864735 @default.
• W3186019557 cites W2963261650 @default.
• W3186019557 cites W2963459241 @default.
• W3186019557 cites W2974859516 @default.
• W3186019557 cites W2981036610 @default.
• W3186019557 cites W2988325738 @default.
• W3186019557 cites W2998072408 @default.
• W3186019557 cites W2999905587 @default.
• W3186019557 cites W3004849003 @default.
• W3186019557 cites W3009705059 @default.
• W3186019557 cites W3029477994 @default.
• W3186019557 cites W3037824960 @default.
• W3186019557 doi "https://doi.org/10.1016/j.cmpb.2021.106295" @default.
• W3186019557 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34329895" @default.
• W3186019557 hasPublicationYear "2021" @default.
• W3186019557 type Work @default.
• W3186019557 sameAs 3186019557 @default.
• W3186019557 citedByCount "4" @default.
• W3186019557 countsByYear W31860195572021 @default.
• W3186019557 countsByYear W31860195572022 @default.
• W3186019557 countsByYear W31860195572023 @default.
• W3186019557 crossrefType "journal-article" @default.
• W3186019557 hasAuthorship W3186019557A5002420822 @default.
• W3186019557 hasAuthorship W3186019557A5003582980 @default.
• W3186019557 hasAuthorship W3186019557A5009224402 @default.
• W3186019557 hasAuthorship W3186019557A5016335119 @default.
• W3186019557 hasAuthorship W3186019557A5027842206 @default.
• W3186019557 hasAuthorship W3186019557A5066640052 @default.
• W3186019557 hasAuthorship W3186019557A5090187041 @default.
• W3186019557 hasConcept C127313418 @default.
• W3186019557 hasConcept C151730666 @default.
• W3186019557 hasConcept C153180895 @default.
• W3186019557 hasConcept C154945302 @default.
• W3186019557 hasConcept C199343813 @default.
• W3186019557 hasConcept C2524010 @default.
• W3186019557 hasConcept C2776799497 @default.
• W3186019557 hasConcept C29694066 @default.
• W3186019557 hasConcept C31972630 @default.
• W3186019557 hasConcept C33923547 @default.
• W3186019557 hasConcept C41008148 @default.
• W3186019557 hasConcept C499950583 @default.
• W3186019557 hasConcept C71924100 @default.
• W3186019557 hasConceptScore W3186019557C127313418 @default.
• W3186019557 hasConceptScore W3186019557C151730666 @default.
• W3186019557 hasConceptScore W3186019557C153180895 @default.
• W3186019557 hasConceptScore W3186019557C154945302 @default.
• W3186019557 hasConceptScore W3186019557C199343813 @default.
• W3186019557 hasConceptScore W3186019557C2524010 @default.
• W3186019557 hasConceptScore W3186019557C2776799497 @default.
• W3186019557 hasConceptScore W3186019557C29694066 @default.
• W3186019557 hasConceptScore W3186019557C31972630 @default.
• W3186019557 hasConceptScore W3186019557C33923547 @default.
• W3186019557 hasConceptScore W3186019557C41008148 @default.
• W3186019557 hasConceptScore W3186019557C499950583 @default.
• W3186019557 hasConceptScore W3186019557C71924100 @default.
• W3186019557 hasLocation W31860195571 @default.
• W3186019557 hasOpenAccess W3186019557 @default.
• W3186019557 hasPrimaryLocation W31860195571 @default.
• W3186019557 hasRelatedWork W1891287906 @default.
• W3186019557 hasRelatedWork W1969923398 @default.
• W3186019557 hasRelatedWork W2036807459 @default.
• W3186019557 hasRelatedWork W2058170566 @default.
• W3186019557 hasRelatedWork W2166024367 @default.
• W3186019557 hasRelatedWork W2229312674 @default.
• W3186019557 hasRelatedWork W2755342338 @default.
• W3186019557 hasRelatedWork W2772917594 @default.
• W3186019557 hasRelatedWork W2775347418 @default.
• W3186019557 hasRelatedWork W3116076068 @default.
• W3186019557 hasVolume "208" @default.
• W3186019557 isParatext "false" @default.
• W3186019557 isRetracted "false" @default.
• W3186019557 magId "3186019557" @default.

• next