Abstract
Fracture of a dental implant (DI) is a rare mechanical complication that is a critical cause of DI failure and explantation. The purpose of this study was to evaluate the reliability and validity of a three different deep convolutional neural network (DCNN) architectures (VGGNet-19, GoogLeNet Inception-v3, and automated DCNN) for the detection and classification of fractured DI using panoramic and periapical radiographic images. A total of 21,398 DIs were reviewed at two dental hospitals, and 251 intact and 194 fractured DI radiographic images were identified and included as the dataset in this study. All three DCNN architectures achieved a fractured DI detection and classification accuracy of over 0.80 AUC. In particular, automated DCNN architecture using periapical images showed the highest and most reliable detection (AUC = 0.984, 95% CI = 0.900–1.000) and classification (AUC = 0.869, 95% CI = 0.778–0.929) accuracy performance compared to fine-tuned and pre-trained VGGNet-19 and GoogLeNet Inception-v3 architectures. The three DCNN architectures showed acceptable accuracy in the detection and classification of fractured DIs, with the best accuracy performance achieved by the automated DCNN architecture using only periapical images.
Highlights
Dental implants (DIs) have shown a high survival and success rate, making them an indispensable and predictable treatment modality for restoring missing teeth [1]
The automated deep convolutional neural network (DCNN) architecture achieved the best accuracy performance using periapical images, with the highest AUC of 0.984, sensitivity of 0.880, specificity of 1.000, and Youden index of 0.880
Our most recent research showed that the automated DCNN architecture was highly accurate (AUC = 0.954, 95% CI = 0.933–0.970) for classifying similar shapes of six different morphological types of DIs based on panoramic and periapical images, and achieves better classification accuracy performance (AUC = 0.961, 95% CI = 0.941–0.976) compared to most of the 25 participating dental professionals, including board-certified periodontists, periodontal residents, and residents not specialized in periodontology [24]
Summary
Dental implants (DIs) have shown a high survival and success rate, making them an indispensable and predictable treatment modality for restoring missing teeth [1]. In a recent systematic review of DI rehabilitation outcomes, the 10-year survival rate was reported as 96.4% (95% CI = 95.2–97.5%), and the overall cumulative survival rate for a follow-up study of 15 years was reported as 82.6%, respectively [1,2]. Various biological (including peri-implant mucositis and peri-implantitis) and mechanical (including chipping, screw loosening and fractures, and ceramic and fixture fractures) complications could increase and require a multiplicity of re-interventions [3]. In a systematic review of long-term results of more than 5 years, the ratio of fracture was reported as 0.18%, and a recent 12-year follow-up study showed a frequency of 0.92% in 19,006 fractured DIs of 5125 patients [6,7]. When DI fracture is undiagnosed or diagnosed late, post-traumatic and inflammatory reactions that induce severe bone loss around DI will inevitably occur [7]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
