Publications
Detailed Information
Cephalometric landmark detection via global and local encoders and patch-wise attentions
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Minkyung | - |
dc.contributor.author | Chung, Minyoung | - |
dc.contributor.author | Shin, Yeong-Gil | - |
dc.date.accessioned | 2022-05-04T01:43:17Z | - |
dc.date.available | 2022-05-04T01:43:17Z | - |
dc.date.created | 2021-12-03 | - |
dc.date.issued | 2022-01-22 | - |
dc.identifier.citation | Neurocomputing, Vol.470, pp.182-189 | - |
dc.identifier.issn | 0925-2312 | - |
dc.identifier.uri | https://hdl.handle.net/10371/179352 | - |
dc.description.abstract | Cephalometric landmark detection performs an important role in a diagnostic measurements for orthodontic treatment plans. As manual depiction of landmarks is a time-consuming and tedious task, the development of an automated detection algorithm for daily clinics is in high demand. In this study, we propose a single-passing convolutional neural network that performs an accurate landmark detection in a hierarchical fashion. The proposed network first extracts global contexts by regressing initial positions of all the landmarks. Subsequently, local features are extracted from landmark-centered patches, which are obtained through global regression. The encoded global and local features are concatenated and weighed through a novel patch-wise attention module to weigh the relative importance. The experimental results demonstrate that our proposed local patch-wise attention mechanism performs a significant role in accurate detection. The proposed method outperformed other state-of-the-art methods by improving the successful detection rate by approximately 1 ti 2%. The proposed method suggests that a structured attention, which is developed in a patch-wise fashion, significantly enhances the local feature encoders to further improve the final accuracy. (c) 2021 Elsevier B.V. All rights reserved. | - |
dc.language | 영어 | - |
dc.publisher | Elsevier BV | - |
dc.title | Cephalometric landmark detection via global and local encoders and patch-wise attentions | - |
dc.type | Article | - |
dc.identifier.doi | 10.1016/j.neucom.2021.11.003 | - |
dc.citation.journaltitle | Neurocomputing | - |
dc.identifier.wosid | 000722305600016 | - |
dc.identifier.scopusid | 2-s2.0-85119251334 | - |
dc.citation.endpage | 189 | - |
dc.citation.startpage | 182 | - |
dc.citation.volume | 470 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Shin, Yeong-Gil | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.