Establishing a novel deep learning model for detecting peri-implantitis.

BACKGROUND/PURPOSE: The diagnosis of peri-implantitis using periapical radiographs is crucial. Recently, artificial intelligence may apply in radiographic image analysis effectively. The aim of this study was to differentiate the degree of marginal bone loss of an implant, and also to classify the severity of peri-implantitis using a deep learning model. MATERIALS AND METHODS: A dataset of 800 periapical radiographic images were divided into training (n = 600), validation (n = 100), and test (n = 100) datasets with implants used for deep learning. An object detection algorithm (YOLOv7) was used to identify peri-implantitis. The classification performance of this model was evaluated using metrics, including the specificity, precision, recall, and F1 score. RESULTS: Considering the classification performance, the specificity was 100%, precision was 100%, recall was 94.44%, and F1 score was 97.10%. CONCLUSION: Results of this study suggested that implants can be identified from periapical radiographic images using deep learning-based object detection. This identification system could help dentists and patients suffering from implant problems. However, more images of other implant systems are needed to increase the learning performance to apply this system in clinical practice.

Visualizing profitability: A heatmap approach to evaluate Bitcoin futures trading using VMA trading rules.

Given that technical trading charts are publicly available on popular financial websites such as Bloomberg and MarketWatch, it stands to reason that the same technical trading approaches may be applied to cryptocurrency markets. One of these trading strategies is the variable length moving average (VMA), whose flexibility benefit has not been fully explored in prior research. To fill this gap, we evaluate Bitcoin futures using VMA trading rules and provide the results in a heatmap diagram. This approach allows investors to choose the most effective VMA rules, potentially leading to profits. Furthermore, our approach may shed new light on previously unexplored investment thinking and practices that have the potential to improve investment outcomes.

Using Heatmap Visualization to assess the performance of the DJ30 and NASDAQ100 Indices under diverse VMA trading rules.

We investigate whether using various VMA trading rules would improve investment performance due to the flexibility of VMA trading rules and the aid of Heatmap Visualization. Previously, investors frequently chose the best performance derived from limited VMA trading rules. However, our new design, which can display all results using Heatmap Visualization, shows that the NASDAQ100 index outperforms the DJ30 index and that weekly data outperforms daily data when measured by annualized return. These findings may be useful to those who trade index ETFs tracking the DJ30 and NASDAQ100 indices, as well as investors making investment decisions, and may contribute to the existing literature by evaluating the outcomes of VMA trading rules and providing insights for index ETF investors using a heatmap matrix, which is rarely explored and presented in the relevant literature.