Journal of Dental Medicine

Background and Aims: Third molar teeth extraction is one of the common treatments procedure in dentistry. The proximity of mandibular third molar teeth to the inferior alveolar nerve canal may make the surgery challenging and cause adverse complications. The purpose of this study was to determine the accuracy of diagnostic and evaluation of panoramic radiography findings in two classification methods (Rood-Shehab and Tanaka) according to CBCT in mandibular third molar extraction surgery.
Materials and Methods: This cross-sectional analytical study was conducted on 65 patients of a private radiology clinic in Qom who had simultaneous panoramic and CBCT radiography. Panoramic and CBCT radiographs were imported into Scanora and Ondemand softwares, respectively. The relation of the mandibular third molar with the inferior alveolar nerve was evaluated according to Tanaka's classification and Rood-Shehab radiographic signs and compared with CBCT radiographs. Finally, the obtained data were analyzed by chi-square test, ROC curve and SPSS software version 24. The significant level was considered at P<0.05.
Results: Out of 65 samples, 23.1% were men and 76.9% were women. The mean age of participants was 26.9±8.77. There was a significant relation between the Tanaka's classification of panoramic radiographs and proximity to the nerve in CBCT radiographs (P=0.011). This relationship was significant when the number of radiographic signs of the Rood-Shehab classification increased (P=0.044). Root darkening and diversion of mandibular nerve canal signs of Rood-Shehab classification showed more diagnostic accuracy in the nerve canal contact determination than that of other signs.
Conclusion: The probability of contact of third molar root with the inferior alveolar nerve canal increases with increasing in the number of Rood-Shehab radiographic signs. The root darkening sign was more accurate and followed by mandibular canal diversion sign. Tanaka’s classification can be used in differentiating cases without contact to the nerve canal.

Background and Aims: Dental caries is one of the most prevalent chronic oral diseases worldwide. Timely and accurate diagnosis of dental caries plays a crucial role in preventing lesion progression and reducing complications. This study aimed to systematically review the studies on dental caries detection using machine learning algorithms applied to periapical radiographs.
Materials and Methods: A comprehensive search was conducted in PubMed, Scopus, Web of Science, IEEE Xplore, and Google Scholar databases up to the end of 2024. Inclusion criteria comprised studies using machine learning algorithms for detecting dental caries in periapical or intraoral radiographs. The quality of studies was assessed using the QUADAS-2 tool.
Results: From 825 initial articles, 13 studies met the inclusion criteria. All studies used Convolutional Neural Networks (CNNs) with various architectures including ResNet, VGG, Inception, DenseNet, and YOLO. ResNet-based models and their hybrid variants showed the best performance with diagnostic accuracy ranging from 82% to 98%. Comparison with human experts in 6 studies revealed that deep learning algorithms demonstrated similar or superior performance.
Conclusion: From the results, deep learning especially convolutional neural networks, had significant potential for improving dental caries detection in periapical radiographs. However, challenges such as limited high-quality training data and generalizability issues need further investigation.

Background and Aims: In recent years, the use of artificial intelligence (AI) has become increasingly common in dentistry because it facilitates the process of diagnosis and clinical decision-making. It is necessary for dentists to be aware of the advantages and disadvantages of artificial intelligence before implementing it. The present study aimed to comprehensively review the various applications of artificial intelligence in the diagnosis of dental diseases along with its challenges and disadvantages.
Materials and Methods: For this review article, a complete search was conducted on the PubMed and Google Scholar databases and studies published in recent years as well as studies published in 2024 were collected using the keywords "artificial intelligence," "dentistry," "diagnosis." Finally, the relevant articles were selected and evaluated, focusing on artificial intelligence in dentistry and the diagnosis of dental diseases.
Results: Advances in artificial intelligence in dental imaging, particularly through machine learning (ML) and artificial neural networks (ANN), have dramatically transformed the way dental disease is diagnosed. These technologies help dentists to analyze complex information and produce more accurate results by using algorithms that allow systems to learn and respond to data. The most recent development in this area is deep learning (DL), which uses multiple layers of neural networks to process unlabeled data and predict outcomes. These techniques are used in various fields such as diagnostic imaging, periodontology, dental caries detection, and osteoporosis screening, which help to improve the quality of dental services. Despite the benefits of AI in clinical dentistry, three controversial challenges remain and need to be addressed: ease of use, return on investment, and evidence of performance, or reliability.
Conclusion: Based on the results, the most important advantage of AI is the diagnosis of dental diseases. AI has great potential to reduce the pressure on health systems by automating routine tasks and improving patient care. However, this technology can never replace human expertise and must be guided by ethical principles. Ultimately, AI is recognized as a valuable tool in dentistry and the final decision-making always remains with the dentist.