DentalGEN: a large-scale controllable generative AI framework for automated dental crown restoration

Abstract

Dental crown restoration addresses a global public health burden, yet is constrained by a slow, variable, and labor-intensive manual design process that limits access to high-quality treatment. Here we introduce DentalGEN, a large-scale controllable generative artificial intelligence framework for automated dental crown restoration. DentalGEN is the first framework capable of designing a patient-specific crown while simultaneously satisfying morphological, functional, and aesthetic criteria. Its core is a novel multi-view diffusion model that leverages explicit control mechanisms to incorporate clinical constraints directly within the generative process. This approach enables the integrated synthesis of view-consistent geometry and texture, achieving a level of precision and integration unattainable with prior automated methods. Evaluated on the largest reported multi-center dataset, DentalGEN’s designs achieved clinical scores statistically equivalent to those of human experts in blinded assessments, while outperforming state-of-the-art methods by 70% in Hausdorff Distance. Furthermore, a clinical proof-of-concept study demonstrated the feasibility of integrating DentalGEN into a supervised scan-design-manufacture paradigm, reducing active design time by over 90%. DentalGEN represents a crucial step in bridging the translational gap for generative AI in dental restoration, paving the way for more accessible, accurate, and efficient dental care.