Evaluating Deep Learning AI for Periapical Lesion Detection Across Panoramic, Periapical, and CBCT Radiographs: A Systematic Review

Introduction Early detection of periapical lesions is critical for timely clinical intervention. Artificial Intelligence (AI) technology, particularly deep learning models, offers a promising approach for identifying such lesions. This study systematically reviews the application of deep learning in detecting periapical lesions across three radiographic modalities: periapical radiography, panoramic radiography, and Cone-Beam Computed Tomography (CBCT). Methods This study employs a systematic literature review methodology, adhering to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines to ensure methodological rigor and transparency. Results The results of this study demonstrate that integrating Artificial Intelligence (AI) with periapical, panoramic, and Cone-Beam Computed Tomography (CBCT) enhances diagnostic accuracy and efficiency in the detection of periapical lesions. Discussion The integration of artificial intelligence with panoramic, periapical, and Cone Beam Computed Tomography (CBCT) imaging modalities significantly enhances the diagnostic accuracy and operational efficiency in identifying periapical lesions. Conclusion This study found that Artificial Intelligence (AI) performs better at evaluating mandibular periapical lesions than at evaluating maxillary periapical lesions. Furthermore, periapical radiography is more sensitive than panoramic radiography for detecting smaller periapical lesions, whereas Cone-Beam Computed Tomography (CBCT) provides the highest diagnostic accuracy for both periapical and odontogenic cystic lesions. The integration of AI with radiographic technologies shows significant potential to enhance diagnostic precision, optimize treatment planning, and improve patient outcomes in endodontic practice.