Efitli, Esra; Karcioglu, Abdullah Ammar; Ozdogan, Alper; Karatas, Furkan; Senocak, Tuba

Tooth color selection is a crucial step in prosthetic dental treatments. However, the process often suffers from subjectivity, environmental light variability, and the high cost or lack of standardization in instrumental methods. This study aims to develop a consistent and reliable tooth color prediction model using machine learning (ML) techniques, even under different clinical lights. In-vivo intraoral images of anterior teeth were collected from volunteer patients under five different clinical light sources. The teeth were annotated, segmented, and matched with corresponding color labels. LAB color space was used, and the CLAHE (Contrast Limited Adaptive Histogram Equalization) technique was applied to the L-channel to reduce light-induced glare. To address class imbalance, data augmentation was performed, resulting in a balanced dataset of 16,640 images. The dataset was split into 80% training and 20% testing subsets. Five ML algorithms—Random Forest (RF), K-Nearest Neighbors (KNN), Logistic Regression, Decision Tree, and XGBoost—were evaluated. As a result of experimental studies, RF and XGBoost obtained the highest performance, both achieving an accuracy of 97% in predicting tooth color across different lighting scenarios. These results demonstrate the robustness of the approach under variable lighting conditions. This study demonstrates that ML algorithms combined with image enhancement techniques such as CLAHE can provide accurate and light-independent tooth color predictions. The proposed method offers a practical and low-cost tool to support clinical decision-making in prosthetic dentistry, potentially enhancing standardization and efficiency in color matching processes.

Karcioglu, Abdullah Ammar; Efitli, Esra; Simsek, Emrah; Ozdogan, Alper; Karatas, Furkan; Senocak, Tuba

The aesthetic understanding has found its place in dental clinics and prosthetic dental treatment. Determining the appropriate prosthetic tooth color between the clinician, patient and technician is a difficult process due to metamerism. Metamerism, known as the different perception of the color of an object under different light sources, is caused by the lighting differences between the laboratory and the dental clinic. The traditional trial-error color determination method, coupled with the high cost of instrumental color value determination, has prompted the need for alternative technologies. The integration of AI technologies into dental practices aims to minimize errors in tooth shade assessment, reduce equipment usage, eliminate the impact of clinic lighting on color detection, and decrease costs for patients, dentists, and laboratories. In this study, a machine learning (ML) based approach that can correctly detect tooth shade even under different clinical lights has been developed. A dataset consisting of 580 dental images taken under four different clinical lights and with five repetitions was created using the Vita color shade guide. Experimental studies were performed using the HSV color space, 6 different ML algorithms and color histograms. As a result, 97.93% accuracy rate was achieved by using cross-validation (cv = 5) in the classification of 29 color values ​​independent of clinical lights. It has been shown that the tooth colors can be determined with high accuracy using ML algorithms and metamerism can be prevented.

Ateş, Gamze Bölükbaşı; Ak, Ayşe; Garipcan, Bora; Gülsoy, Murat

Photobiomodulation (PBM) and photodynamic therapy (PDT) share similar mechanisms but have opposite aims. Increased levels of reactive oxygen species (ROS) in the target tissue in response to light combined photosensitizer (PS) application may lead to cell proliferation or oxidative damage depending on the ROS amount. The purpose of the present study is to investigate the effect of indocyanine green (ICG)-mediated PBM on osteoblast cells by measuring cell viability, proliferation, alkaline phosphatase (ALP) activity, mineralization, and gene expressions of three phenotypic osteoblast markers. A diode laser irradiating at 809 nm (10 W output power, 50 mW/cm2 power density) was used at 0.5, 1, and 2 J/cm2 energy densities (10, 20, and 40 s respectively) was applied following ICG incubation. No inhibitory effect was observed in cell viability and proliferation according to the (4,5-dimethylthiazol-2-yl)-2,5-diphenyl tetrazolium bromide (MTT) and Alamar Blue assays. ICG-mediated PBM did not alter cell viability but increased ALP activity and enhanced mineralization of existing osteoblasts. These results were also confirmed by real-time polymerase chain reaction (RT-PCR) analysis of osteoblastic markers. PS can be combined to PBM not only to damage the malignant cells as aimed in PDT studies, but also to promote cellular activity. The findings of this in vitro study may contribute to in vivo studies and ICG-mediated PBM can have promising outcomes in bone healing and regeneration therapies in future.

Ateş, Gamze Bölükbaşı; Ak, Ayşe; Garipcan, Bora; Gülsoy, Murat

Photobiomodulation (PBM) and photodynamic therapy (PDT) are two major methods, which use light in medicine and dentistry. PBM uses low-level laser light to induce cell proliferation and activity. In contrast, PDT use laser light combined with a photosensitizer (PS) to cause cell death. Due to similar, not fully understood mechanisms and biphasic response of light, unexpected and complex outcomes may be observed. In the present study, the effect of 635 nm laser light, with power density 50 mW/cm2, at three different energy densities (0.5, 1, and 2 J/cm2 which last 10, 20, and 40 s, respectively) mediated by methylene blue (MB) on the human osteoblast cell line (ATCC-CRL-11372, Rockville, MD, USA) was investigated. Cell viability (MTT assay and acridine orange/propidium iodide staining) and proliferation (Alamar Blue assay) were assessed at 24, 48, and 72 h post irradiation. Alkaline phosphatase (ALP) activity, mineralization (Alizarin Red staining) and gene expressions (RT-PCR analysis) were analyzed at 7th and 14th days after treatment. Five groups were formed as the control group (no MB, no irradiation), MB (only 0.05 μM MB), MB + 0.5 J/cm2, MB + 1 J/cm2, and MB + 2 J/cm2. Cell viability was decreased at 72 h (ANOVA; p < 0.05) for MB + 0.5 J/cm2, MB + 1 J/cm2, and MB + 2 J/cm2 groups. Although proliferation does not seem to be effected by MB-mediated laser application, osteo-anabolic activity is altered. ALP activity was significantly increased at day 7 (ANOVA; p < 0.05) for MB-combined laser groups; on the other hand, mineralization was significantly decreased (ANOVA; p < 0.05) in all treatment groups. Alkaline phosphatase and collagen-I expressions were upregulated in MB + 2 J/cm2 group at 7th and 14th days, respectively. These results may contribute to the low-dose PDT researches and understanding PBM effects on osteoblast behavior but further studies are needed since inappropriate conditions may lead to undesirable results for both therapies.

Bölükbaşı Ateş, Gamze; Ak Can, Ayşe; Gülsoy, Murat

Photobiomodulation (PBM) describes light-induced photochemical reactions achieved by the application of red or near infrared lasers/LED light with low energy densities. This noninvasive and painless method has been used in some clinical areas but controversial outcomes demand a skeptical look for its promising and potential effects. In this detailed in vitro study, the osteoblast cells were irradiated with 635 and 809 nm diode lasers at energy densities of 0.5, 1, and 2 J/cm2. Cell viability, proliferation, bone formation, and osteoblast differentiation were evaluated by methylthiazole tetrazolium (MTT) assay, Alamar Blue assay, acridine orange/propidium iodide staining, alkaline phosphatase (ALP) activity, Alizarin red staining, and reverse-transcription polymerase chain reaction (RT-PCR) to test the expression of collagen type I, ALPL, and osteocalcin. The results indicate that studied energy doses have a transient effect (48 h after laser irradiation) on the osteoblast viability and proliferation. Similarly, laser irradiation did not appear to have any effect on ALP activity. These results were confirmed by RT-PCR analysis of osteoblast markers. This study suggests that several irradiation parameters and variations in the methods should be clearly established in the laboratory before laser treatment becomes a postulated application for bone tissue regeneration in clinical level.