Background/Objectives: The integration of digital imaging technologies in dentistry has revolutionized diagnostic and treatment practices, with panoramic radiographs playing a crucial role in detecting impacted teeth. Manual interpretation of these images is time consuming and error prone, highlighting the need for automated, accurate solutions. This study proposes an artificial intelligence (AI)-based model for detecting impacted teeth in panoramic radiographs, aiming to enhance accuracy and reliability. Methods: The proposed model combines YOLO (You Only Look Once) and RT-DETR (Real-Time Detection Transformer) models to leverage their strengths in real-time object detection and learning long-range dependencies, respectively. The integration is further optimized with the Weighted Boxes Fusion (WBF) algorithm, where WBF parameters are tuned using Bayesian optimization. A dataset of 407 labeled panoramic radiographs was used to evaluate the model’s performance. Results: The model achieved a mean average precision (mAP) of 98.3% and an F1 score of 96%, significantly outperforming individual models and other combinations. The results were expressed through key performance metrics, such as mAP and F1 scores, which highlight the model’s balance between precision and recall. Visual and numerical analyses demonstrated superior performance, with enhanced sensitivity and minimized false positive rates. Conclusions: This study presents a scalable and reliable AI-based solution for detecting impacted teeth in panoramic radiographs, offering substantial improvements in diagnostic accuracy and efficiency. The proposed model has potential for widespread application in clinical dentistry, reducing manual workload and error rates. Future research will focus on expanding the dataset and further refining the model’s generalizability.

Background: Dental disorders are one of the most important health problems, affecting billions of people all over the world. Early diagnosis is important for effective treatment planning. Precise dental disease segmentation requires reliable tooth numbering, which may be prone to errors if performed manually. These steps can be automated using artificial intelligence, which may provide fast and accurate results. Among the AI methodologies, deep learning has recently shown excellent performance in dental image processing, allowing effective tooth segmentation and numbering. Methods: This paper proposes the Squeeze and Excitation Inception Block-based Encoder–Decoder (SE-IB-ED) network for teeth segmentation in panoramic X-ray images. It combines the InceptionV3 model for encoding with a custom decoder for feature integration and segmentation, using pointwise convolution and an attention mechanism. A dataset of 313 panoramic radiographs from private clinics was annotated using the Fédération Dentaire Internationale (FDI) system. PSPL and SAM augmented the annotation precision and effectiveness, with SAM automating teeth labeling and subsequently applying manual corrections. Results: The proposed SE-IB-ED network was trained and tested using 80% training and 20% testing of the dataset, respectively. Data augmentation techniques were employed during training. It outperformed the state-of-the-art models with a very high F1-score of 92.65%, mIoU of 86.38%, and 92.84% in terms of accuracy, precision of 92.49%, and recall of 99.92% in the segmentation of teeth. Conclusions: According to the results obtained, the proposed method has great potential for the accurate segmentation of all teeth regions and backgrounds in panoramic X-ray images.

Accurate detection of impacted teeth in panoramic radiographs is critical for effective diagnosis and treatment planning in dentistry. Traditional segmentation methods often face challenges in achieving accurate detection due to the anatomical complexity and variability of dental structures. This study aims to address these limitations by performing a comprehensive comparative analysis of four advanced pixel-based segmentation models - U-Net, FPN, PSPNet and LinkNet - integrated with ten different backbone architectures. Using a meticulously annotated dataset of 407 high-resolution panoramic radiographs, the models were rigorously trained and evaluated using robust performance metrics, including accuracy, precision, recall, F1 score, and Intersection over Union (IoU). Among the configurations tested, the U-Net model with an EfficientNetB7 backbone achieved the highest performance, with an average IoU score of 85.29%, demonstrating superior accuracy and reliability. The main contributions of this study are the in-depth comparison of state-of-the-art segmentation models, the identification of the most effective architectures tailored for dental radiograph segmentation, and new insights into the advantages of pixel-based approaches over region-based methods commonly used in previous studies. These findings highlight the strengths and limitations of each model, providing practical guidance for researchers and clinicians in selecting appropriate solutions for impacted teeth detection. In addition, the study highlights the potential for future advances through hybrid approaches and customized model designs to further improve detection accuracy and clinical applicability. As a result, this research demonstrates the transformative potential of integrating artificial intelligence into dental diagnostics, paving the way for more accurate, efficient and scalable solutions to improve clinical decision-making.

Gömülü diş tespiti, diş hekimliği uygulamalarında önemli bir adımdır ve doğru bir tespit süreci, tedavi planlaması ve teşhislerde büyük önem taşır. Geleneksel yöntemlerin sınırlamaları ve hata olasılıkları göz önüne alındığında, derin öğrenme modelleri gibi yapay zekâ temelli yaklaşımların kullanılması giderek daha yaygın hale gelmektedir. Bu çalışmada panoramik gömülü diş görüntülerinde derin öğrenme modellerinin performansı incelenmiştir Yedi farklı modelin (VGG16-Unet, VGG19-Unet, MobileNetV2, Unet-v1, Unet-v2, Unet-v3 ve Unet-v4) performansı değerlendirilmiştir. VGG16-Unet modelinin AUC (eğri altındaki alan) değeri %94.87 ile diğer modellere kıyasla daha yüksek bulunmuştur. Bu çalışma, diş hekimliği alanında daha doğru ve hassas segmentasyon yöntemleri geliştirilmesine katkı sağlayarak, diş tespiti ve tedavi planlaması süreçlerinde daha güvenilir sonuçlar elde edilmesini desteklemektedir.