Publications
Detailed Information
Tooth instance segmentation from cone-beam CT images through point-based detection and Gaussian disentanglement
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Jusang | - |
dc.contributor.author | Chung, Minyoung | - |
dc.contributor.author | Lee, Minkyung | - |
dc.contributor.author | Shin, Yeong-Gil | - |
dc.date.accessioned | 2022-06-22T00:08:18Z | - |
dc.date.available | 2022-06-22T00:08:18Z | - |
dc.date.created | 2022-05-09 | - |
dc.date.issued | 2022-05 | - |
dc.identifier.citation | Multimedia Tools and Applications, Vol.81 No.13, pp.18327-18342 | - |
dc.identifier.issn | 1380-7501 | - |
dc.identifier.uri | https://hdl.handle.net/10371/182716 | - |
dc.description.abstract | © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.Individual tooth segmentation and identification from cone-beam computed tomography images are preoperative prerequisites for orthodontic treatments. Instance segmentation methods using convolutional neural networks have demonstrated ground-breaking results on individual tooth segmentation tasks, and are used in various medical imaging applications. While point-based detection networks achieve superior results on dental images, it is still a challenging task to distinguish adjacent teeth because of their similar topologies and proximate nature. In this study, we propose a point-based tooth localization network that effectively disentangles each individual tooth based on a Gaussian disentanglement objective function. The proposed network first performs heatmap regression accompanied by box regression for all the anatomical teeth. A novel Gaussian disentanglement penalty is employed by minimizing the sum of the pixel-wise multiplication of the heatmaps for all adjacent teeth pairs. Subsequently, individual tooth segmentation is performed by converting a pixel-wise labeling task to a distance map regression task to minimize false positives in adjacent regions of the teeth. Experimental results demonstrate that the proposed algorithm outperforms state-of-the-art approaches by increasing the average precision of detection by 9.1%, which results in a high performance in terms of individual tooth segmentation. The primary significance of the proposed method is two-fold: (1) the introduction of a point-based tooth detection framework that does not require additional classification and (2) the design of a novel loss function that effectively separates Gaussian distributions based on heatmap responses in the point-based detection framework. | - |
dc.language | 영어 | - |
dc.publisher | Kluwer Academic Publishers | - |
dc.title | Tooth instance segmentation from cone-beam CT images through point-based detection and Gaussian disentanglement | - |
dc.type | Article | - |
dc.identifier.doi | 10.1007/s11042-022-12524-9 | - |
dc.citation.journaltitle | Multimedia Tools and Applications | - |
dc.identifier.wosid | 000766430800007 | - |
dc.identifier.scopusid | 2-s2.0-85126071807 | - |
dc.citation.endpage | 18342 | - |
dc.citation.number | 13 | - |
dc.citation.startpage | 18327 | - |
dc.citation.volume | 81 | - |
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.