The Leeuwenhoek paradox in dental artificial intelligence: A narrative review of artificial intelligence-detected subclinical periapical changes and human-labeled false positives.

This narrative review explores the "Leeuwenhoek Paradox," a metaphorical and conceptual challenge that arises when artificial intelligence (AI) detects subtle periapical radiological changes that are not visible to human observers. Drawing on evidence from studies using two-dimensional and cone-beam computed tomography (CBCT) imaging, this review critically examined the limitations of human-centered reference standards and recurrent discrepancies in AI-based periapical detection. The literature shows that AI systems frequently detect more periapical alterations than human experts. These findings may reflect early bone changes, as indicated by CBCT-based analyses of bone density and longitudinal observations. The paradox arises because AI identifies subclinical radiographic changes (AI-SRCs) that fall below the threshold of human visual perception, leading to their classification as false positives by humans owing to the limitations of human vision. Framed within the Leeuwenhoek Paradox, this article highlighted the constraints of equating diagnostic truth exclusively with human visual perception. Finally, the review outlined conceptual pathways for validating AISRCs, including longitudinal clinical studies, standardized visualization tools such as heatmaps, and the definition of new diagnostic thresholds, with the aim of supporting the safe integration of AI into dental diagnostics while mitigating the risks of overdiagnosis.