Related Experiment Video
Updated: Jan 9, 2026
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
Artificial Intelligence Versus Conventional Methods in Digital Smile Designing: An Accuracy Study
Marwa AbdelHafez1, AbdelRahman Afia2, Omar Shaalan3
1Division of Conservative Dentistry, School of Dentistry, Newgiza University, Giza, Egypt.
Objectives:
Concerns exist that artificial intelligence tools prioritize marketing over actual patients' needs. This study evaluates the accuracy and acceptance of digital smile designs created using artificial intelligence software compared to conventional methods.
Materials And Methods:
Ten cases requiring esthetic rehabilitation were included. Each case received two smile designs: one created using artificial intelligence software (Smilefy) and another using a conventional method (exoCAD). Both designs were converted into Standard Tessellation Language and superimposed to measure error differences using Geomagic software. Satisfaction levels were assessed for both patients and dentists on a visual analogue scale from 0 to 10. Error differences were analyzed using one-way ANOVA, while satisfaction scores were compared using a paired t test.
Results:
Smilefy showed an average error difference of 0.29 ± 0.095 mm. No significant differences were found in primary or tertiary anatomy or overall dentist satisfaction (p > 0.05). However, exoCAD was preferred for secondary anatomy (p < 0.05). Patient satisfaction did not differ significantly between the two methods (p > 0.05).
Conclusions:
Smilefy demonstrated acceptable accuracy in smile design. Dentists were generally satisfied except with secondary anatomy, while patients were satisfied with both methods. Smilefy shows promise but requires further refinement to meet both dentist and patient expectations.
Clinical Significance:
Artificial intelligence significantly enhances smile designing by automating tasks like anatomical landmark detection, image adjustment, face classification, and teeth segmentation. It enables rapid, personalized smile design evaluations with improved accuracy and efficiency. Moreover, it also generates virtual treatment simulations that support collaborative decision-making between dentists and patients. This automation reduces human error, suggests optimal treatment plans, and even predicts treatment longevity for better, cost-effective outcomes.
