Received by the Editorial Office: August 09, 2026
Accepted for publication: September 14, 2026
Published online: September 30, 2026
UDC: 616.314-089.28:004.8
DOI: 10.70113/1815-9443.2026.68.68.006
DIGITAL ANALYSIS OF TOOTH COLOR IN PROSTHODONTIC DENTISTRY
Nysanova B.Zh.¹, Zhaishieva Sh.A.¹, Imasheva A. S.¹, Onaibekova N.M.¹,
Taupyk N.¹, Zholshibekov A.K.¹
¹Asfendiyarov Kazakh National Medical University,
Almaty, Kazakhstan
Introduction. Accurate tooth shade selection is essential for predictable esthetic outcomes in prosthodontic dentistry. Visual shade assessment remains subjective, whereas digital photography, spectrophotometry, intraoral scanning, and artificial intelligence (AI) may improve the objectivity and reproducibility of color analysis.
Objective. To evaluate contemporary digital methods for tooth color determination and the potential of AI for analyzing and predicting the shade of teeth and prosthodontic restorations.
Materials and Methods. An analytical review of PubMed/MEDLINE literature on digital photography, spectrophotometry, intraoral scanning, computer vision, machine learning, and AI-based color analysis was performed. The review primarily included systematic reviews, meta-analyses, and original studies published in 2020–2026, together with selected methodologically relevant earlier publications. A clinical illustration of a 34-year-old patient was also included: standardized RAW photography, color calibration, convolutional-neural-network image segmentation, CIELAB color coordinates, and ΔE calculations were used for shade selection of an all-ceramic crown.
Results. Digital methods enable more objective quantitative color registration, while AI algorithms can automate image segmentation, color-feature analysis, and restorative shade prediction. In the clinical illustration, digital analysis identified 2M2 as the closest match to the intact reference tooth (ΔE=0.82 versus ΔE=2.45 for 3M2); satisfactory esthetic integration was observed at the 14-day follow-up. Accuracy remains dependent on acquisition conditions, equipment, algorithms, and input-data quality.
Discussion. The available evidence supports the potential of AI as a decision-support tool for dental shade selection; however, heterogeneity in acquisition protocols, devices, algorithms, and training datasets limits direct generalization. The single clinical illustration demonstrates feasibility but cannot establish diagnostic accuracy or population-level effectiveness.
Conclusion. AI is a promising adjunct for digital color analysis in prosthodontics, but it should be integrated with standardized digital acquisition, objective measurement methods, and CAD/CAM workflows. Standardized protocols and independent clinical validation in larger cohorts are required.
Keywords: digital color analysis, tooth color, prosthodontics, artificial intelligence, computer vision, machine learning, spectrophotometry, CAD/CAM.
