Improving resolution of panoramic radiographs: super-resolution concept.

OBJECTIVES: Dental imaging plays a key role in the diagnosis and treatment of dental conditions, yet limitations regarding the quality and resolution of dental radiographs sometimes hinder precise analysis. Super-resolution with deep learning refers to a set of techniques used to enhance the resolution of images beyond their original size or quality using deep neural networks instead of traditional image interpolation methods which often result in blurred or pixelated images when attempting to increase resolution. Leveraging advancements in technology, this study aims to enhance the resolution of dental panoramic radiographs, thereby enabling more accurate diagnoses and treatment planning. METHODS: About 1714 panoramic radiographs from 3 different open datasets are used for training (n = 1364) and testing (n = 350). The state of the art 4 different models is explored, namely Super-Resolution Convolutional Neural Network (SRCNN), Efficient Sub-Pixel Convolutional Neural Network, Super-Resolution Generative Adversarial Network, and Autoencoder. Performances in reconstructing high-resolution dental images from low-resolution inputs with different scales (s = 2, 4, 8) are evaluated by 2 well-accepted metrics Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR). RESULTS: SSIM spans between 0.82 and 0.98 while PSNR are between 28.7 and 40.2 among all scales and models. SRCNN provides the best performance. Additionally, it is observed that performance decreased when images are scaled with higher values. CONCLUSION: The findings highlight the potential of super-resolution concepts to significantly improve the quality and detail of dental panoramic radiographs, thereby contributing to enhanced interpretability.

Evaluation of root canal filling length on periapical radiograph using artificial intelligence.

OBJECTIVES: This work proposes a novel method to evaluate root canal filling (RCF) success using artificial intelligence (AI) and image analysis techniques. METHODS: 1121 teeth with root canal treatment in 597 periapical radiographs (PARs) were anonymized and manually labeled. First, RCFs were segmented using 5 different state-of-the-art deep learning models based on convolutional neural networks. Their performances were compared based on the intersection over union (IoU), dice score and accuracy. Additionally, fivefold cross validation was applied for the best-performing model and their outputs were later used for further analysis. Secondly, images were processed via a graphical user interface (GUI) that allows dental clinicians to mark the apex of the tooth, which was used to find the distance between the apex of the tooth and the nearest RCF prediction of the deep learning model towards it. The distance can show whether the RCF is normal, short or long. RESULTS: Model performances were evaluated by well-known evaluation metrics for segmentation such as IoU, Dice score and accuracy. CNN-based models can achieve an accuracy of 88%, an IoU of 79% and Dice score of 88% in segmenting root canal fillings. CONCLUSIONS: Our study demonstrates that AI-based solutions present accurate and reliable performance for root canal filling evaluation.

The role of deep learning for periapical lesion detection on panoramic radiographs.

OBJECTIVE: This work aimed to detect automatically periapical lesion on panoramic radiographs (PRs) using deep learning. METHODS: 454 objects in 357 PRs were anonymized and manually labeled. They are then pre-processed to improve image quality and enhancement purposes. The data were randomly assigned into the training, validation, and test folders with ratios of 0.8, 0.1, and 0.1, respectively. The state-of-art 10 different deep learning-based detection frameworks including various backbones were applied to periapical lesion detection problem. Model performances were evaluated by mean average precision, accuracy, precision, recall, F1 score, precision-recall curves, area under curve and several other Common Objects in Context detection evaluation metrics. RESULTS: Deep learning-based detection frameworks were generally successful in detecting periapical lesions on PRs. Detection performance, mean average precision, varied between 0.832 and 0.953 while accuracy was between 0.673 and 0.812 for all models. F1 score was between 0.8 and 0.895. RetinaNet performed the best detection performance, similarly Adaptive Training Sample Selection provided F1 score of 0.895 as highest value. Testing with external data supported our findings. CONCLUSION: This work showed that deep learning models can reliably detect periapical lesions on PRs. Artificial intelligence-based on deep learning tools are revolutionizing dental healthcare and can help both clinicians and dental healthcare system.

Automated detection of dental restorations using deep learning on panoramic radiographs.

OBJECTIVES: Automatically detecting dental conditions using Artificial intelligence (AI) and reporting it visually are now a need for treatment planning and dental health management. This work presents a comprehensive computer-aided detection system to detect dental restorations. METHODS: The state-of-art ten different deep-learning detection models were used including R-CNN, Faster R-CNN, SSD, YOLOv3, and RetinaNet as detectors. ResNet-50, ResNet-101, XCeption-101, VGG16, and DarkNet53 were integrated as backbone and feature extractor in addition to efficient approaches such Side-Aware Boundary Localization, cascaded structures and simple model frameworks like Libra and Dynamic.Total 684 objects in panoramic radiographs were used to detect available three classes, namely, dental restorations, denture and implant.Each model was evaluated by mean average precision (mAP), average recall (AR), and precision-recall curve using Common Objects in Context (COCO) detection evaluation metrics. RESULTS: mAP varied between 0.755 and 0.973 for ten models explored while AR ranges between 0.605 and 0.771. Faster R-CNN RegnetX provided the best detection performance with mAP of 0.973 and AR of 0.771. Area under precision-recall curve was 0.952. Precision-recall curve indicated that errors were mainly dominated by localization confusions. CONCLUSIONS: Results showed that the proposed AI-based computer-aided system had great potential with reliable, accurate performance detecting dental restorations, denture and implant in panoramic radiographs. As training models with more data and standardization in reporting, AI-based solutions will be implemented to dental clinics for daily use soon.

Unusual radiographic images of radiopaque contrast media incidentally observed in intracranial region: two case reports.

The oil-based contrast medium has extremely slow clearance rate from cerebrospinal fluid. The medium known as myodil or pantopaque or iopenydylate was firstly introduced in 1944 to be used in myelography, cisternography and ventriculography. It was commonly used until 1980s but was later replaced by water-soluble mediums in 1990s because of its complication and sequelae. Although rare, images of the remnants may still be encountered on radiograms since its remnants may be seen after six decades. In this article, incidental radiopaque images in panoramic radiography and cone-beam computed tomography (CBCT) were presented in two patients whose myelography was taken before herniated discs' operation. Unusual incidental radiopacities in intracranial region were observed on panoramic radiography image of a male and CBCT image of a female, both of whom underwent myelography more than 30 years ago. Dentomaxillofacial radiologists should be aware of this radiographic appearance, should be able to differentiate it from possible pathologies.