Deep learning based dental implant failure prediction from periapical and panoramic films

Abstract

Background: Dental implant failure is a critical condition that can seriously compromise therapeutic efficacy. Insufficient bone volume, unfavorable bone quality, periodontal bone loss, and systemic conditions, including osteopenia/osteoporosis and diabetes mellitus, have been associated with implant failure. Early indicators of potential implant failure could help mitigate the risk of severe complications. This study aimed to develop an effective implant outcome prediction model using dental periapical and panoramic films.Methods: A total of 248 patients (89 with failed implants and 159 with successful implants) were examined.A total of 529 periapical images and 551 panoramic images were collected from the patients for a deep learning-based model. Based on radiographic peri-implant alveolar bone pattern, implant outcome was divided into three categories: implant failure with marginal bone loss, implant failure without marginal bone loss, and implant success. We extracted features using a deep convolutional neural network (CNN) and built a hybrid model to combine periapical and panoramic images. A comparison among three categories of receiver operating characteristic (ROC) curves was performed. The diagnostic accuracy, precision, recall and F1-score of the dataset were assessed.Results: Our model achieved an AUC (area under the ROC curve) of 0.972 for failure with marginal bone loss, 0.947 for failure without marginal bone loss and 0.975 for success. In all conditions, for periapical images alone, the diagnostic accuracy was 78.6%; the precision was 0.84, recall was 0.73, and F1-score was 0.75. For panoramic images alone, the diagnostic accuracy was 78.7%; the precision was 0.87, recall was 0.63, and F1-score was 0.66. Both periapical and panoramic images were used in our novel method, and the prediction accuracy was 87%. The precision was 0.85, recall was 0.88, and F1-score was 0.85. Conclusions:The deep learning model used features from periapical and panoramic images to effectively predict the occurrence of implant failure and might facilitate early clinical intervention for potential dental implant failures.

Automation in Dentistry with Mechanical Drills and Lasers for Implant Osteotomy: A Narrative-Scoping Review

“…In the case of implant dentistry, the focus of these researchers was on the stress concentration of the implant. Another group used deep learning (DL) as a means to predict implant outcome (success or failure) from peripheral and panoramic films [54]. They divided 248 patients (89 with failed implants and 159 with successful implants) into three categories (implant failure with marginal bone loss, implant failure without marginal bone loss, and implant success).…”

Pioneering nanomedicine in orthopedic treatment care: a review of current research and practices

“…One of the key problems connected with the rising popularity of uncemented complete joint arthroplasties is osteointegration failures ( Zhang C. et al, 2023 ; Verma et al, 2023 ). Although prosthetic joints are presently cured to improve osseous ingrowth through surface irregularity, the nanoscale, where cellular relationships take place, stays smooth ( Figure 2 ).…”

“…Pre-processing steps, including cropping and histogram equalization, were applied to periapical and panoramic radiographs to optimize image contrast. Reproduced with permission from Zhang C. et al (2023c) .…”

The Impact of Artificial Intelligence on Dental Implantology: A Narrative Review

“…The integrated model had the best prediction rate as far as five-year implant loss risk was concerned. Another DL model predicting implant loss was developed by Zhang et al based on periapical and panoramic films [ 37 ]. Per-implant alveolar bone loss levels were analyzed, and a prediction accuracy of 87% was obtained.…”