Improving dental diagnoses with novel AI model

An artificial intelligence model may be effective at automating the detection of dental pathologies on panoramic radiographs.

In a study published in Diagnostics, the researchers developed and validated a novel AI model to identify dental conditions — including periapical lesions, impacted teeth, root fragments, prosthetic restorations and orthodontic devices — and, in particular, at-risk teeth prior to radiotherapy among patients with head and neck cancer.

After using 1,628 annotated panoramic radiographs to train a YOLOv8 model, the researchers found that the AI model was capable of identifying implants, endodontic treatments and surgical devices. Conversely, the model performed poorer during external validation with 180 panoramic radiographs.

The researchers emphasized that the novel AI model should undergo refinement to enhance its generalizability and improve its diagnostic capabilities.

Read more: Diagnostics

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.