Advanced search
Start date

Applying artificial intelligence algorithms for color prediction of CAD/CAM materials with varying thicknesses, over colored backgrounds, and under different illuminants

Grant number: 23/15441-4
Support Opportunities:Scholarships abroad - Research Internship - Doctorate
Effective date (Start): April 12, 2024
Effective date (End): November 01, 2024
Field of knowledge:Health Sciences - Dentistry - Dental Materials
Principal Investigator:José Maurício dos Santos Nunes Reis
Grantee:Bruno Arruda Mascaro
Supervisor: Maria Del Mar Perez Gomez
Host Institution: Faculdade de Odontologia (FOAr). Universidade Estadual Paulista (UNESP). Campus de Araraquara. Araraquara , SP, Brazil
Research place: Universidad de Granada (UGR), Spain  
Associated to the scholarship:22/12431-5 - Influence of substrate, simulated gastric juice, dentifrice, and illuminant on optical properties and surface analysis of CAD/CAM materials, BP.DR


Objectives: The study aims to assess the predictability of color coordinates of resin composite, hybrid ceramic, and porcelain CAD/CAM restorative materials to estimate their final color based on their thickness, over colored backgrounds, and under different illuminants. Material and Methods: Disk-shaped samples (n=36/material) with thicknesses (n=12) of 0.5, 1.0, and 1.5 mm will be fabricated with A2 shade and high translucency level (HT) CAD/CAM blocks of Lava Ultimate (LU), Grandio Blocs (GB), VITA Enamic (VE), and VITABLOCS Mark II (VM). After polishing (600, 1200, 1500, and 2000-grit SiC abrasive papers), a non-contact spectroradiometer with CIE 45º/0º illuminating/measuring geometry will be used to measure the spectral reflectance of samples. Measurements will be taken over a standardized black background and nine fabricated backgrounds: ND1-ND9 (IPS Natural Die Material). Artificial intelligence (AI) algorithms will be used as a predictive method to reconstruct spectral data and CIE-L*, a*, and b* color coordinates as a function of sample thicknesses. The reflectance spectrum data will be converted to CIEL* CIEa*, and CIEb* coordinates to calculate color differences (”E00) between the measured and predicted values. Color differences will be obtained for each material thickness over each ND-colored background and under illuminants CIE D65, A, F2, and nine white LEDs. Root mean square error (RMSE), goodness-of-fit coefficient (GFC), correlation coefficient (R2) as well as ”E00 with corresponding 50:50% acceptability and perceptibly thresholds (AT00 and PT00) for dentistry will be used as performance assessment of the method. From these methods, the data will be analyzed to verify the effects of the studied variables.

News published in Agência FAPESP Newsletter about the scholarship:
Articles published in other media outlets (0 total):
More itemsLess items

Please report errors in scientific publications list using this form.