Albano D, Galiano V, Basile M et al. Artificial intelligence for radiographic imaging detection of caries lesions: a systematic review. BMC Oral Health 2024; 24: 274.

AI-based models have demonstrated good diagnostic performance, potentially being an important aid in carious lesion detection.

This systematic review evaluated the diagnostic performance of artificial intelligence (AI) models designed for the detection of caries lesions (CL). An electronic literature search was conducted for retrospective, prospective and cross-sectional studies published until January 2023. Twenty articles were evaluated. Five studies were performed on periapical radiographs, nine on bitewings, and six on orthopantomography. The number of imaging examinations included ranged from 15 to 2,900. Four studies investigated ANN models, 15 CNN models, and 2 DCNN models. Twelve were retrospective studies, six cross-sectional and two prospective. The following diagnostic performance was achieved in detecting CL: sensitivity from 0.44 to 0.86, specificity from 0.85 to 0.98, precision from 0.50 to 0.94, Positive Predictive Value 0.86, Negative Predictive Value 0.95, accuracy from 0.73 to 0.98, area under the curve from 0.84 to 0.98, intersection over union of 0.3-0.4 and 0.78, Dice coefficient 0.66 and 0.88, F1-score from 0.64 to 0.92. Most studies exhibited a low risk of bias.