The diagnostic performance of impacted third molars in the mandible: A review of deep learning on panoramic radiographs

Background

Mandibular third molar is prone to impaction, resulting in its inability to erupt into the oral cavity. The radiographic examination is required to support the odontectomy of impacted teeth. The use of computer-aided diagnosis based on deep learning is emerging in the field of medical and dentistry with the advancement of artificial intelligence (AI) technology. This review describes the performance and prospects of deep learning for the detection, classification, and evaluation of third molar-mandibular canal relationships on panoramic radiographs.

Methods

This work was conducted using three databases: PubMed, Google Scholar, and Science Direct. Following the literature selection, 49 articles were reviewed, with the 12 main articles discussed in this review.

Results

Several models of deep learning are currently used for segmentation and classification of third molar impaction with or without the combination of other techniques. Deep learning has demonstrated significant diagnostic performance in identifying mandibular impacted third molars (ITM) on panoramic radiographs, with an accuracy range of 78.91% to 90.23%. Meanwhile, the accuracy of deep learning in determining the relationship between ITM and the mandibular canal (MC) ranges from 72.32% to 99%.

Conclusion

Deep learning-based AI with high performance for the detection, classification, and evaluation of the relationship of ITM to the MC using panoramic radiographs has been developed over the past decade. However, deep learning must be improved using large datasets, and the evaluation of diagnostic performance for deep learning models should be aligned with medical diagnostic test protocols. Future studies involving collaboration among oral radiologists, clinicians, and computer scientists are required to identify appropriate AI development models that are accurate, efficient, and applicable to clinical services.

Artificial intelligence in detecting dentomaxillofacial fractures in diagnostic imaging: a scoping review protocol

INTRODUCTION

The dentomaxillofacial (DMF) area, which includes the teeth, maxilla, mandible, zygomaticum, orbits and midface, plays a crucial role in the maintenance of the physiological functions despite its susceptibility to fractures, which are mostly caused by mechanical trauma. As a diagnostic tool, radiographic imaging helps clinicians establish a diagnosis and determine a treatment plan; however, the presence of human factors in image interpretation can result in missed detection of fractures. Therefore, an artificial intelligence (AI) computing system with the potential to help detect abnormalities on radiographic images is currently being developed. This scoping review summarises the literature and assesses the current status of AI in DMF fracture detection in diagnostic imaging.

METHODS AND ANALYSIS

This proposed scoping review will be conducted using the framework of Arksey and O'Malley, with each step incorporating the recommendations of Levac et al. By using relevant keywords based on the research questions. PubMed, Science Direct, Scopus, Cochrane Library, Springerlink, Institute of Electrical and Electronics Engineers, and ProQuest will be the databases used in this study. The included studies are published in English between 1 January 2000 and 30 June 2023. Two independent reviewers will screen titles and abstracts, followed by full-text screening and data extraction, which will comprise three components: research study characteristics, comparator and AI characteristics.

ETHICS AND DISSEMINATION

This study does not require ethical approval because it analyses primary research articles. The research findings will be distributed through international conferences and peer-reviewed publications.

Analysis of mandible trabecular structure using digital periapical radiographs to assess low bone quality in postmenopausal women

PURPOSE

To analyze the quality of mandibular trabecular structure in postmenopausal women using periapical radiographs. Postmenopausal women are subjected to low bone quality; hence, early detection methods are needed. In addition to bone mineral density (BMD), trabecular architecture must be assessed to determine bone quality. The mandible represents bone quality and allows the assessment of trabecular structure from periapical radiographs.

MATERIAL AND METHODS

Lumbar (BMDL) and femoral BMD (BMDF) examinations were performed using dual-energy X-ray absorptiometry (DXA) in 31 postmenopausal women and divided into normal, osteopenia, and osteoporotic groups. Periapical radiographs were taken at both posterior sites of the mandible. The region of interest was taken 2 mm from the apical root of the first molar. Trabecular parameters consisting of trabecular thickness (Tb.Th) and bone percentage (BA/TA) were measured using BoneJ.

RESULTS

Both trabecular parameters were significantly correlated with BMDF [BA/TA ​​(r = 0.3796; p < 0.05) and Tb.Th (r = 0.508; p < 0.05)]. BA/TA and Tb.Th were significantly different between the osteoporosis and normal groups (p < 0.05) contrast to osteopenia and normal groups (p > 0.05).

CONCLUSION

Changes in mandibular trabeculae structure in postmenopausal women can be assessed using periapical radiographs.