Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387483313> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4387483313 abstract "Accurate segmentation of various anatomical structures from dental panoramic radiographs is essential for the diagnosis and treatment planning of various diseases in digital dentistry. In this paper, we propose a novel deep learning-based method for accurate and fully automatic segmentation of the maxillary sinus, mandibular condyle, mandibular nerve, alveolar bone and teeth on panoramic radiographs.
Approach: A two-stage coarse-to-fine prior-guided segmentation framework is proposed to segment multiple structures on dental panoramic radiographs. In the coarse stage, a multi-label segmentation network is used to generate the coarse segmentation mask, and in the fine-tuning stage, a prior-guided attention network with an encoder-decoder architecture is proposed to precisely predict the mask of each anatomical structure. First, a prior-guided edge fusion module (PEFM) is incorporated into the network at the input of each convolution level of the encode path to generate edge-enhanced image feature maps. Second, a prior-guided spatial attention module (PSAM) is proposed to guide the network to extract relevant spatial features from foreground regions based on the combination of the prior information and the spatial attention mechanism. Finally, a prior-guided hybrid attention module (PHAM) is integrated at the bottleneck of the network to explore global context from both spatial and category perspectives.
Main results: We evaluated the segmentation performance of our method on a testing dataset that contains 150 panoramic radiographs collected from real-world clinical scenarios. The segmentation results indicate that our proposed method achieves more accurate segmentation performance compared with state-of-the-art methods. The average Jaccard scores are 87.91%, 85.25%, 63.94%, 93.46% and 88.96% for the maxillary sinus, mandibular condyle, mandibular nerve, alveolar bone and teeth, respectively.
Significance: The proposed method was able to accurately segment multiple structures on panoramic radiographs. This method has the potential to be part of the process of automatic pathology diagnosis from dental panoramic radiographs.
." @default.
- W4387483313 created "2023-10-11" @default.
- W4387483313 creator A5006342956 @default.
- W4387483313 creator A5015676600 @default.
- W4387483313 creator A5026253671 @default.
- W4387483313 creator A5026658848 @default.
- W4387483313 creator A5050789305 @default.
- W4387483313 creator A5053648490 @default.
- W4387483313 creator A5063344472 @default.
- W4387483313 creator A5090864700 @default.
- W4387483313 date "2023-10-10" @default.
- W4387483313 modified "2023-10-12" @default.
- W4387483313 title "Coarse-to-fine prior-guided attention network for multi-structure segmentation on dental panoramic radiographs" @default.
- W4387483313 doi "https://doi.org/10.1088/1361-6560/ad0218" @default.
- W4387483313 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37816372" @default.
- W4387483313 hasPublicationYear "2023" @default.
- W4387483313 type Work @default.
- W4387483313 citedByCount "0" @default.
- W4387483313 crossrefType "journal-article" @default.
- W4387483313 hasAuthorship W4387483313A5006342956 @default.
- W4387483313 hasAuthorship W4387483313A5015676600 @default.
- W4387483313 hasAuthorship W4387483313A5026253671 @default.
- W4387483313 hasAuthorship W4387483313A5026658848 @default.
- W4387483313 hasAuthorship W4387483313A5050789305 @default.
- W4387483313 hasAuthorship W4387483313A5053648490 @default.
- W4387483313 hasAuthorship W4387483313A5063344472 @default.
- W4387483313 hasAuthorship W4387483313A5090864700 @default.
- W4387483313 hasConcept C108583219 @default.
- W4387483313 hasConcept C126838900 @default.
- W4387483313 hasConcept C138885662 @default.
- W4387483313 hasConcept C151730666 @default.
- W4387483313 hasConcept C153180895 @default.
- W4387483313 hasConcept C154945302 @default.
- W4387483313 hasConcept C2776401178 @default.
- W4387483313 hasConcept C2779343474 @default.
- W4387483313 hasConcept C31972630 @default.
- W4387483313 hasConcept C36454342 @default.
- W4387483313 hasConcept C41008148 @default.
- W4387483313 hasConcept C41895202 @default.
- W4387483313 hasConcept C71924100 @default.
- W4387483313 hasConcept C81363708 @default.
- W4387483313 hasConcept C86803240 @default.
- W4387483313 hasConcept C89600930 @default.
- W4387483313 hasConceptScore W4387483313C108583219 @default.
- W4387483313 hasConceptScore W4387483313C126838900 @default.
- W4387483313 hasConceptScore W4387483313C138885662 @default.
- W4387483313 hasConceptScore W4387483313C151730666 @default.
- W4387483313 hasConceptScore W4387483313C153180895 @default.
- W4387483313 hasConceptScore W4387483313C154945302 @default.
- W4387483313 hasConceptScore W4387483313C2776401178 @default.
- W4387483313 hasConceptScore W4387483313C2779343474 @default.
- W4387483313 hasConceptScore W4387483313C31972630 @default.
- W4387483313 hasConceptScore W4387483313C36454342 @default.
- W4387483313 hasConceptScore W4387483313C41008148 @default.
- W4387483313 hasConceptScore W4387483313C41895202 @default.
- W4387483313 hasConceptScore W4387483313C71924100 @default.
- W4387483313 hasConceptScore W4387483313C81363708 @default.
- W4387483313 hasConceptScore W4387483313C86803240 @default.
- W4387483313 hasConceptScore W4387483313C89600930 @default.
- W4387483313 hasLocation W43874833131 @default.
- W4387483313 hasLocation W43874833132 @default.
- W4387483313 hasOpenAccess W4387483313 @default.
- W4387483313 hasPrimaryLocation W43874833131 @default.
- W4387483313 hasRelatedWork W2611989081 @default.
- W4387483313 hasRelatedWork W3029198973 @default.
- W4387483313 hasRelatedWork W3133861977 @default.
- W4387483313 hasRelatedWork W3167935049 @default.
- W4387483313 hasRelatedWork W3193565141 @default.
- W4387483313 hasRelatedWork W4226493464 @default.
- W4387483313 hasRelatedWork W4293226380 @default.
- W4387483313 hasRelatedWork W4312417841 @default.
- W4387483313 hasRelatedWork W4315434538 @default.
- W4387483313 hasRelatedWork W4375867731 @default.
- W4387483313 isParatext "false" @default.
- W4387483313 isRetracted "false" @default.
- W4387483313 workType "article" @default.