Can AI be used to detect periapical radiolucencies?

Investigators have examined whether artificial intelligence may help dentists detect periapical radiolucencies on imaging, according to a systematic review and meta-analysis published in the Journal of Dentistry.

Previous research has found inconsistencies in the accuracy of diagnosing periapical radiolucencies.

In the study, the investigators used the PubMed/MEDLINE, ScienceDirect and Institute of Electrical and Electronics Engineers Xplore databases to analyze the data of 24 articles focused on periapical radiolucency detection. They noted that 23 of the studies utilized a convolutional neural network to assist in diagnosing the radiolucencies.

Among the four articles included in the meta-analysis, AI demonstrated a pooled sensitivity of 0.94 and specificity of 0.96 — representing the potential to support dentists in periapical radiolucency detection.

However, the investigators emphasized that more diverse studies, such as prospective, real-life randomized controlled trials, may be needed to further understand the benefit of using AI for this application.

Read more: Journal of Dentistry

The article presented here is intended to inform you about the broader media perspective on dentistry, regardless of its alignment with the ADA's stance. It is important to note that publication of an article does not imply the ADA's endorsement, agreement, or promotion of its content.