Clinical trials are the key step in verifying the effectiveness, safety and usability of novel oral medical devices. With improvements in invention capability, the number of clinical trials of medical devices has steadily increased domestically, indicating the need for new requirements for quality management. Here, on the basis of summarizing the characteristics of clinical trials for oral medical devices in China, we proposed a whole-process quality-control model for good clinical practice (WQGCP). This model clarified the management specifications for oral medical device clinical trials in the new era. It indicates that the clinical trial design is the breakthrough point, while whole-process risk control is the key point. This suggests the need for the establishment of a quality management cooperation system, evaluation and postevaluation systems and the training of high-level personnel who conduct clinical trials. It also provides suggestions to promote the participation of oral clinicians in high-quality research and invention of novel clinical medical devices with the aim of accelerating the development of oral medical devices in China.
- Article type
- Year
- Co-author
Open Access
Expert Forum
Issue
Open Access
Clinical Study
Issue
To study the effect of artificial intelligence in the pathological diagnosis of periapical cysts and to explore the application of artificial intelligence in the field of oral pathology.
Pathological images of eighty-seven periapical cysts were selected as subjects to read, and a neural network with a U-net structure was constructed. The 87 HE images and labeled images of periapical cysts were divided into a training set (72 images) and a test set (15 images), which were used in the training model and test model, respectively. Finally, the target level index F1 score, pixel level index Dice coefficient and receiver operating characteristic (ROC) curve were used to evaluate the ability of the U-net model to recognize periapical cyst epithelium.
The F1 score of the U-net network model for recognizing periapical cyst epithelium was 0.75, and the Dice index and the areas under the ROC curve were 0.685 and 0.878, respectively.
The U-net network model constructed by artificial intelligence has a good segmentation result in identifying periapical cyst epithelium, which can be preliminarily applied in the pathological diagnosis of periapical cysts and is expected to be gradually popularized in clinical practice after further verification with large samples.
京公网安备11010802044758号