Artificial Intelligence in Dental Radiographic Diagnosis: Systematic review
Session
Dental Science
Description
Artificial intelligence (AI), particularly machine learning and deep learning algorithms, is playing an increasingly important role in dental radiographic diagnosis. This systematic review explores the diagnostic accuracy and clinical applicability of AI in analyzing dental radiographs. Through an extensive search of major scientific databases, 47 studies were selected, evaluating the performance of AI systems in identifying dental conditions such as caries, periapical lesions, and bone loss. The models—mainly based on convolutional neural networks (CNNs)—achieved diagnostic accuracy ranging from 82.4% to 96.1%. However, the lack of standardization and methodological variability limit the generalizability of the findings. Moreover, few studies addressed real-time implementation challenges or the user interface in clinical settings. In conclusion, AI demonstrates significant potential to enhance diagnostic decision-making in dentistry, but further studies are needed to support safe and effective integration into clinical practice.
Keywords:
Artificial intelligence, dental radiography, diagnostic accuracy, systematic review, dental diagnosis, radiology
Proceedings Editor
Edmond Hajrizi
ISBN
978-9951-982-41-2
Location
UBT Lipjan, Kosovo
Start Date
25-10-2025 9:00 AM
End Date
26-10-2025 6:00 PM
DOI
10.33107/ubt-ic.2025.114
Recommended Citation
Karakashi, Adea and Hamiti, Vjosa, "Artificial Intelligence in Dental Radiographic Diagnosis: Systematic review" (2025). UBT International Conference. 1.
https://knowledgecenter.ubt-uni.net/conference/2025UBTIC/DS/1
Artificial Intelligence in Dental Radiographic Diagnosis: Systematic review
UBT Lipjan, Kosovo
Artificial intelligence (AI), particularly machine learning and deep learning algorithms, is playing an increasingly important role in dental radiographic diagnosis. This systematic review explores the diagnostic accuracy and clinical applicability of AI in analyzing dental radiographs. Through an extensive search of major scientific databases, 47 studies were selected, evaluating the performance of AI systems in identifying dental conditions such as caries, periapical lesions, and bone loss. The models—mainly based on convolutional neural networks (CNNs)—achieved diagnostic accuracy ranging from 82.4% to 96.1%. However, the lack of standardization and methodological variability limit the generalizability of the findings. Moreover, few studies addressed real-time implementation challenges or the user interface in clinical settings. In conclusion, AI demonstrates significant potential to enhance diagnostic decision-making in dentistry, but further studies are needed to support safe and effective integration into clinical practice.