This study evaluated if AI could determine the positional relationship between M3 and IAN based on panoramic radiography regarding whether the two structures were in contact or intimate and whether the IAN was positioned lingually or buccally to M3. AI could determine both positions more accurately than OMFS specialists.
Until now, if M3 and IAN overlap on panoramic radiograph, specialists could use the known predictive signs of IAN injury to determine the positional relationship whether the two structures were in contact or intimate. Umar et al. compared the positional relationship between IAN and M3 through panoramic radiography and CBCT. Loss of the radiopaque line and diversion of the canal on panoramic radiographs resulted in tooth and nerve contact in 100% of the cases on CBCT. Darkening of the roots were associated with contact on CBCT in 76.9% of the cases studied22. However, another study reported that the sensitivities and specificities ranged from 14.6–68.3% and from 85.5–96.9%, respectively, for those three predictive signs1. Datta et al. compared those signs with the clinical findings during surgical removal and found that only 12% of patients with positive radiological signs showed clinical evidence of involvement3. In the present study, we adopted CBCT reading results instead of radiological signs on panoramic radiography to determine the positional relationship so that the AI could determine whether the two structures were in contact or intimate, showing an accuracy of 0.55 to 0.72. Compared to another study1, our deep learning model exhibited similar performance (accuracy 0.87, precision 0.90, recall, 0.96, F1 score 0.93, and AUC 0.82) to determine whether M3 is contacting the IAN or not. This could explain the different model performance depending on the characteristics of the data.
To replace CBCT with analysis of panoramas with AI, information about bucco-lingual positioning was necessary to ensure safe surgical outcomes. It has been reported that the lingual position of the nerve to the tooth has a significantly higher risk of IAN injury compared to other positions23. However, there have been few studies reporting the bucco-lingual relationship using plain radiographs. The vertical tube shift technique is a diagnostic method evaluating the bucco-lingual relationship. Nevertheless, this technique caused patient discomfort and nausea during placement of the film or sensor of the digital intraoral x-ray devices24 and is difficult to use clinically. Since there was no effective method to discern the position, the accuracy of the specialists was low in this study. On the contrary, the AI showed considerably high accuracy ranges from 67.7–80.6% despite the small amount of study data. The course of the IAN predominantly is buccal to the tooth23, and our data revealed a similar situation. However, the total number of cases was small to match the numbers in each group evenly for deep learning. Therefore, training AI with more data could produce more accurate results and be used more widely in clinical settings.
In this study, bucco-lingual determination (Experiment 2) exhibited superior performance for true contact positioning (Experiment 1). The difference in accuracy between the two experiments seems to be a characteristic of the data rather than a special technical difference. There might be a particular advantage for AI to be recognized in bucco-lingual classification, or that some of the contact classification data might have characteristics that are difficult to distinguish.
Panoramic radiography is the most widely used screening test, but image distortion and low resolution of the panoramic images requires possible future examinations with CBCT. It is widely known that CBCT is necessary to confirm subtle changes of the cortical surface. However, the same-side-lingual opposite-side-buccal (SLOB) technique is accepted to determine bucco-lingual positioning25, and it might indicate that modalities with better resolution are not required to evaluate the bucco-lingual relationship. If AI could determine the bucco-lingual relationship between M3 and IAN, it could prove to be very helpful before surgery.
There are several studies that have developed Al algorithms that have been able to outmatch specialists in terms of performance and accuracy. AI assistance improved the performance of radiologists in distinguishing coronavirus disease 2019 from pneumonia of other origins in chest CT26. Moreover, the AI system outperformed radiologists in clinically relevant tasks of breast cancer identification on mammography27. In the present study, the AI exhibited much higher accuracy and performance compared to those of OMFS specialists. To determine the positional relationship between M3 and IAN, we performed preliminary tests to determine the most suitable AI model using VGG19, DenseNet, EfficientNet, and ResNet-50. ResNet showed higher AUC in Experiment 2 and comparable AUC in Experiment 1 (Supplemental Tables 1, 2, and 3). Therefore, it was chosen as the final AI model.
This study has limitations. First, the absolute size of the training dataset was small. Data augmentation by image modification was used to overcome the limitation of a small sized dataset. Nevertheless, as shown in Table 1, there were cases where training did not proceed robustly. Therefore, the performances of the trained models highly depend on the train-test split. This unsoundness of the trained model, which hinders the clinical utility of AI models for primary determination in practice, can be alleviated by collecting more data and using them for training. In addition, this study is meaningful in that the AI model performed better than experts even under these adverse conditions. Second, there was no external dataset from multiple dental centers for reproducibility in general utility. We plan to study large datasets including internal and external data to overcome limitations in future studies.