ArticleJournal of esthetic and restorative dentistry : official publication of the American Academy of Esthetic Dentistry ... [et al.]2026
Photo-Based Color Analysis in Restorative Dentistry: The Role of Artificial Intelligence Algorithms.
Article in Journal of esthetic and restorative dentistry : official publication of the American Academy of Esthetic Dentistry ... [et al.], 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 1 paper.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
1 citing paper in PubMed.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
objectiveThis study aimed to develop and evaluate deep learning-based models for estimating CIELAB tooth color coordinates from standardized extraoral photographs, using in vivo spectrophotometric measurements as the reference standard, to provide practical and validating support for clinical shade selection in restorative dentistry. MATERIALS AND
methodsA total of 1031 labeled and cropped tooth images were obtained from high-resolution extraoral photographs of 102 participants. In vivo CIELAB color coordinates (L*, a*, b*, C*, h°) were recorded from the maxillary anterior teeth using the VITA Easyshade V spectrophotometer. Five convolutional neural network (CNN) architectures (CustomCNN, ResNet18, EfficientNetB0, DenseNet121, and MobileNetV2) were trained using two types of input: preprocessed tooth photographs (cropped, resized, and normalized) and their corresponding anatomical positions (one-hot encoded). The performance of this combined-input model was evaluated using mean absolute error (MAE), coefficient of determination (R
resultsAmong the models tested, MobileNetV2 achieved the best performance, with a MAE of 0.0593 and accuracy exceeding 94% when estimated CIELAB color coordinates from extraoral photographs were compared with in vivo spectrophotometric measurements (reference standard) using the ΔE ≤ 2 clinical threshold. No significant differences were found between MobileNetV2, DenseNet121, and ResNet18, and all three models significantly outperformed EfficientNetB0 and CustomCNN (p < 0.001). Estimation accuracy was highest for C*(chroma) and h°(hue) values, while slightly lower performance was observed for L*(lightness) and b* values. Anterior teeth exhibited higher accuracy than posterior teeth, likely due to more favorable image quality and light exposure.
conclusionAI-based models, particularly MobileNetV2, demonstrated high agreement with spectrophotometric reference measurements in estimating CIELAB tooth color coordinates from standardized extraoral photographs. These findings suggest their potential to support consistent and practical shade selection in esthetic restorative dentistry. CLINICAL SIGNIFICANCE: These results suggest that AI models have the potential to be applied in clinical shade selection procedures, providing a supportive approach that may contribute to improved consistency and assist decision-making in esthetic dentistry.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.