In this study, the efficacy of the automated deep convolutional neural network (DCNN) was evaluated for the classification of dental implant systems (DISs) and the accuracy of the performance was compared against that of dental professionals using dental radiographic images collected from three dental hospitals. A total of 11,980 panoramic and periapical radiographic images with six different types of DISs were divided into training (n = 9584) and testing (n = 2396) datasets. To compare the accuracy of the trained automated DCNN with dental professionals (including six board-certified periodontists, eight periodontology residents, and 11 residents not specialized in periodontology), 180 images were randomly selected from the test dataset. The accuracy of the automated DCNN based on the AUC, Youden index, sensitivity, and specificity, were 0.954, 0.808, 0.955, and 0.853, respectively. The automated DCNN outperformed most of the participating dental professionals, including board-certified periodontists, periodontal residents, and residents not specialized in periodontology. The automated DCNN was highly effective in classifying similar shapes of different types of DISs based on dental radiographic images. Further studies are necessary to determine the efficacy and feasibility of applying an automated DCNN in clinical practice.

Lee JB, et al. J Periodontal Implant Sci. 2020 Jun;50(3):146-158. https://doi.org/10.5051/jpis.2020.50.3.146

Lee JH, et al. J Periodontal Implant Sci. 2022 Jun;52(3):220-229. https://doi.org/10.5051/jpis.2104080204

The aim of this study was to analyze the correlation between the dental plaque indices measured using quantitative light-induced fluorescence-digital (QLF-D) and conventional clinical indices that assess gingival status. From among the patients who visited Ewha Womans University Mokdong Hospital, 33 adults in their 20s who had relatively even teeth were selected for full-mouth QLF-D imaging. The images were used to analyze the QLF-D score and the QLF-D ΔR score. As clinical indices, the gingival index (GI), bleeding on probing (BOP), probing pocket depth (PPD), and patient hygiene performance (PHP) index were measured. The correlations between the QLF-D score and QLF-D ΔR score and each clinical index were analyzed. Analyses were performed comparing the indices of maxillary and mandibular teeth, the teeth on right and left sides of the mouth, anterior and posterior teeth, and buccal and lingual surfaces of each tooth. Pearson’s correlation analysis was conducted (p < 0.05). The mean full-mouth QLF-D score was highly correlated with the GI, BOP, PPD, PHP index (p < 0.01). The mean full-mouth QLF-D score showed the highest correlation with GI (r = 0.749) and the lowest correlation with PPD (r = 0.683). The correlations between the QLF-D score were higher in the mandible than in the maxilla and in the anterior teeth than in the posterior teeth, while no significant differences were seen between the buccal and lingual surfaces of tooth. This study concluded that the correlations between the plaque indices measured for each tooth surface area using QLF-D and the clinical indices assessed were significantly high, and it allowed objective determination of the gingival status. Therefore, the plaque index measured using QLF-D may be used as an alternative to supplement the shortcomings of conventional clinical indices for educating patients about plaque control and continued patient oral care.

Kim YM, et al. J Periodontal Implant Sci. 2022 Jun;52:e22. https://doi.org/10.5051/jpis.2200960048