0 227

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

 Junghoon Lee  ;  Hyunseok Seo  ;  Yoon Jeong Choi  ;  Chena Lee  ;  Sunil Kim  ;  Ye Sel Lee  ;  Sukjoon Lee  ;  Euiseong Kim 
 JOURNAL OF ENDODONTICS, Vol.49(6) : 710-719, 2023-06 
Journal Title
Issue Date
Artificial Intelligence* ; Neural Networks, Computer ; Pilot Projects ; Radiography ; Root Canal Therapy*
Convolutional neural network ; Grad-CAM ; PRESSAN-17 ; artificial intelligence ; endodontic outcome ; endodontic treatment
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.
Full Text
10.1016/ j.joen.2023.03.015
Appears in Collections:
2. College of Dentistry (치과대학) > Dept. of Conservative Dentistry (보존과학교실) > 1. Journal Papers
2. College of Dentistry (치과대학) > Dept. of Oral and Maxillofacial Radiology (영상치의학교실) > 1. Journal Papers
2. College of Dentistry (치과대학) > Dept. of Orthodontics (교정과학교실) > 1. Journal Papers
Yonsei Authors
Kim, Sun Il(김선일) ORCID logo https://orcid.org/0000-0002-8889-9844
Kim, Eui Seong(김의성) ORCID logo https://orcid.org/0000-0003-2126-4761
Lee, Sukjoon(이석준)
Lee, Junghoon(이정훈)
Lee, Chena(이채나) ORCID logo https://orcid.org/0000-0002-8943-4192
Choi, Yoon Jeong(최윤정) ORCID logo https://orcid.org/0000-0003-0781-8836
사서에게 알리기


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.