Improving Dental Implant Outcomes: CNN-Based System Accurately Measures Degree of Peri-Implantitis Damage on Periapical Film

Phantom study for CT artifacts of dental titanium implants and zirconia upper structures: the effects of occlusal plane angle setting and SEMAR algorithm

OBJECTIVES

The single-energy metal artifact reduction (SEMAR) algorithm effectively reduces metal artifacts in computed tomography (CT). The study aimed to evaluate the effect of the occlusal plane angle on metal artifacts caused by dental implants and zirconia upper structures, and the effectiveness of SEMAR for CT prognostic evaluation.

METHODS

Part of a bovine rib was used as the mandibular implant phantom. First, the phantom immersed in a water tank was scanned using CT to obtain the control image under certain conditions. Subsequently, three titanium implant bodies were implanted in a straight line into the phantom, and a zirconia superstructure was attached. CT scans were performed. The CT-reconstructed images were obtained with and without SEMAR processing. Twelve regions of interest (ROIs) were set at the same site on each sagittal image, and the CT values were measured at all the ROIs. The CT values of the ROIs in the control images and those of the ROIs with and without SEMAR were compared.

RESULTS

The variations in the occlusal plane angle during CT imaging negligibly affected the number of regions in which metal artifacts appeared. SEMAR improved the CT value of the trabecular bone, which was affected by metal artifacts.

CONCLUSION

This study showed that the occlusal plane angle occasionally did not affect the area of metal artifacts caused by dental implants or zirconia upper structures. Other results indicate that SEMAR is effective for accurately evaluating the alveolar bone around the implant body by reducing metal artifacts.

Deep Learning-Based Recognition of Periodontitis and Dental Caries in Dental X-ray Images

Dental X-ray images are important and useful for dentists to diagnose dental diseases. Utilizing deep learning in dental X-ray images can help dentists quickly and accurately identify common dental diseases such as periodontitis and dental caries. This paper applies image processing and deep learning technologies to dental X-ray images to propose a simultaneous recognition method for periodontitis and dental caries. The single-tooth X-ray image is detected by the YOLOv7 object detection technique and cropped from the periapical X-ray image. Then, it is processed through contrast-limited adaptive histogram equalization to enhance the local contrast, and bilateral filtering to eliminate noise while preserving the edge. The deep learning architecture for classification comprises a pre-trained EfficientNet-B0 and fully connected layers that output two labels by the sigmoid activation function for the classification task. The average precision of tooth detection using YOLOv7 is 97.1%. For the recognition of periodontitis, the area under the curve (AUC) of the receiver operating characteristic (ROC) curve is 98.67%, and the AUC of the precision-recall (PR) curve is 98.38%. For the recognition of dental caries, the AUC of the ROC curve is 98.31%, and the AUC of the PR curve is 97.55%. Different from the conventional deep learning-based methods for a single disease such as periodontitis or dental caries, the proposed approach can provide the recognition of both periodontitis and dental caries simultaneously. This recognition method presents good performance in the identification of periodontitis and dental caries, thus facilitating dental diagnosis.