桥接(联网)
生成语法
生成模型
计算机科学
人工智能
过程(计算)
牙冠(牙科)
机器学习
监督学习
芯(光纤)
豪斯多夫距离
工程制图
生成设计
作者
Jiamin Wu,Ying Liu,Yanning Chen,Yuqiang Zhang,Jiaying Gu,Yuan Liu,Mengxun Li,Wenping Wang,Yuanfei Fu,Zhiming Cui,James Kit Hon Tsoi,Dinggang G. Shen
标识
DOI:10.1038/s41746-026-03236-7
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI