Cited 0 times in
An Endodontic Forecasting Model Based on the Analysis of Preoperative Dental Radiographs: A Pilot Study on an Endodontic Predictive Deep Neural Network
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 김선일 | - |
dc.contributor.author | 김의성 | - |
dc.contributor.author | 이채나 | - |
dc.contributor.author | 최윤정 | - |
dc.contributor.author | 이정훈 | - |
dc.contributor.author | 이석준 | - |
dc.date.accessioned | 2023-08-23T00:01:39Z | - |
dc.date.available | 2023-08-23T00:01:39Z | - |
dc.date.issued | 2023-06 | - |
dc.identifier.issn | 0099-2399 | - |
dc.identifier.uri | https://ir.ymlib.yonsei.ac.kr/handle/22282913/196133 | - |
dc.description.abstract | Introduction: This study aimed to evaluate the use of deep convolutional neural network (DCNN) algorithms to detect clinical features and predict the three-year outcome of endodontic treatment on preoperative periapical radiographs. Methods: A database of single-root premolars that received endodontic treatment or retreatment by endodontists with presence of three-year outcome was prepared (n = 598). We constructed a 17-layered DCNN with a self-attention layer (Periapical Radiograph Explanatory System with Self-Attention Network [PRESSAN-17]), and the model was trained, validated, and tested to 1) detect 7 clinical features, that is, full coverage restoration, presence of proximal teeth, coronal defect, root rest, canal visibility, previous root filling, and periapical radiolucency and 2) predict the three-year endodontic prognosis by analyzing preoperative periapical radiographs as an input. During the prognostication test, a conventional DCNN without a self-attention layer (residual neural network [RESNET]-18) was tested for comparison. Accuracy and area under the receiver-operating-characteristic curve were mainly evaluated for performance comparison. Gradient-weighted class activation mapping was used to visualize weighted heatmaps. Results: PRESSAN-17 detected full coverage restoration (area under the receiver-operating-characteristic curve = 0.975), presence of proximal teeth (0.866), coronal defect (0.672), root rest (0.989), previous root filling (0.879), and periapical radiolucency (0.690) significantly, compared to the no-information rate (P < .05). Comparing the mean accuracy of 5-fold validation of 2 models, PRESSAN-17 (67.0%) showed a significant difference to RESNET-18 (63.4%, P < .05). Also, the area under average receiver-operating-characteristic of PRESSAN-17 was 0.638, which was significantly different compared to the no-information rate. Gradient-weighted class activation mapping demonstrated that PRESSAN-17 correctly identified clinical features. Conclusions: Deep convolutional neural networks can detect several clinical features in periapical radiographs accurately. Based on our findings, well-developed artificial intelligence can support clinical decisions related to endodontic treatments in dentists. | - |
dc.description.statementOfResponsibility | restriction | - |
dc.language | English | - |
dc.publisher | Elsevier | - |
dc.relation.isPartOf | JOURNAL OF ENDODONTICS | - |
dc.rights | CC BY-NC-ND 2.0 KR | - |
dc.subject.MESH | Artificial Intelligence* | - |
dc.subject.MESH | Neural Networks, Computer | - |
dc.subject.MESH | Pilot Projects | - |
dc.subject.MESH | Radiography | - |
dc.subject.MESH | Root Canal Therapy* | - |
dc.title | An Endodontic Forecasting Model Based on the Analysis of Preoperative Dental Radiographs: A Pilot Study on an Endodontic Predictive Deep Neural Network | - |
dc.type | Article | - |
dc.contributor.college | College of Dentistry (치과대학) | - |
dc.contributor.department | Dept. of Conservative Dentistry (보존과학교실) | - |
dc.contributor.googleauthor | Junghoon Lee | - |
dc.contributor.googleauthor | Hyunseok Seo | - |
dc.contributor.googleauthor | Yoon Jeong Choi | - |
dc.contributor.googleauthor | Chena Lee | - |
dc.contributor.googleauthor | Sunil Kim | - |
dc.contributor.googleauthor | Ye Sel Lee | - |
dc.contributor.googleauthor | Sukjoon Lee | - |
dc.contributor.googleauthor | Euiseong Kim | - |
dc.identifier.doi | 10.1016/ j.joen.2023.03.015 | - |
dc.contributor.localId | A00556 | - |
dc.contributor.localId | A00833 | - |
dc.contributor.localId | A05388 | - |
dc.contributor.localId | A04139 | - |
dc.relation.journalcode | J01393 | - |
dc.identifier.eissn | 1878-3554 | - |
dc.identifier.pmid | 37019378 | - |
dc.identifier.url | https://www.sciencedirect.com/science/article/pii/S0099239923001784 | - |
dc.subject.keyword | Convolutional neural network | - |
dc.subject.keyword | Grad-CAM | - |
dc.subject.keyword | PRESSAN-17 | - |
dc.subject.keyword | artificial intelligence | - |
dc.subject.keyword | endodontic outcome | - |
dc.subject.keyword | endodontic treatment | - |
dc.contributor.alternativeName | Kim, Sun Il | - |
dc.contributor.affiliatedAuthor | 김선일 | - |
dc.contributor.affiliatedAuthor | 김의성 | - |
dc.contributor.affiliatedAuthor | 이채나 | - |
dc.contributor.affiliatedAuthor | 최윤정 | - |
dc.citation.volume | 49 | - |
dc.citation.number | 6 | - |
dc.citation.startPage | 710 | - |
dc.citation.endPage | 719 | - |
dc.identifier.bibliographicCitation | JOURNAL OF ENDODONTICS, Vol.49(6) : 710-719, 2023-06 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.