- Austria / Österreich
- Bosnia and Herzegovina / Босна и Херцеговина
- Bulgaria / България
- Croatia / Hrvatska
- Czech Republic & Slovakia / Česká republika & Slovensko
- Finland / Suomi
- France / France
- Germany / Deutschland
- Greece / ΕΛΛΑΔΑ
- Italy / Italia
- Netherlands / Nederland
- Nordic / Nordic
- Poland / Polska
- Portugal / Portugal
- Romania & Moldova / România & Moldova
- Slovenia / Slovenija
- Serbia & Montenegro / Србија и Црна Гора
- Spain / España
- Sweden / Sverige
- Switzerland / Schweiz
- Turkey / Türkiye
- UK & Ireland / UK & Ireland
COPENHAGEN, Denmark: Researchers in Turkey have examined the extent to which deep learning artificial intelligence (AI) algorithms are able to identify periodontal status from two-dimensional dental bitewing radiographs. According to the research, which was presented at EuroPerio10 in Copenhagen on 16 June, the AI system is capable of identifying periodontal pathologies that may be missed by dentists.
Previous studies have examined the capability of AI to detect caries, root fractures and apical lesions, but only limited research has examined the use of the technology in the field of periodontology, according to a EuroPerio10 press release.
The study was conducted by researchers at Eskisehir Osmangazi University in Eskisehir in Turkey, and it evaluated the ability of deep learning, a type of AI, to determine periodontal status in bitewing radiographs. A total of 434 bitewing radiographs were used from patients with periodontitis, and the images were examined by a convolutional neural network and by an experienced clinician for total alveolar bone loss, horizontal and vertical bone loss, furcation defects, and calculus around maxillary and mandibular teeth.
Compared with the clinician’s assessment, the AI scored highly in both sensitivity and precision in identifying total alveolar bone loss and horizontal bone loss but was not able to identify vertical bone loss. The weighted averages of its sensitivity and precision in identifying dental calculus and furcation defects, in comparison with the clinician, were 0.82 and 0.66, respectively.
Dr Muhammet Burak Yavuz of the university’s Department of Periodontology presented the findings during the EuroPerio10 session “Periodontal diagnosis and disease progression”, and he commented that, although further research is needed, the study results show that AI systems could be used to assess periodontal health.
Dr Yavuz commented in the press release: “Our study shows the potential for artificial intelligence to automatically identify periodontal pathologies that might otherwise be missed. This could reduce radiation exposure by avoiding repeat assessments, prevent the silent progression of periodontal disease, and enable earlier treatment.” He added that the results illustrate “that AI is able to pick up many types of defects from 2D images which could aid in the diagnosis of periodontitis”.
“This study provides a glimpse into the future of dentistry, where AI automatically evaluates images and assists dental professionals to diagnose and treat disease earlier,” Dr Yavuz concluded.