Performance of artificial intelligence using oral and maxillofacial CBCT images: A systematic review and meta-analysis.

Background: Artificial intelligence (AI) has the potential to enhance health care efficiency and diagnostic accuracy. Aim: The present study aimed to determine the current performance of AI using cone-beam computed tomography (CBCT) images for detection and segmentation. Materials and Methods: A systematic search for scholarly articles written in English was conducted on June 24, 2021, in PubMed, Web of Science, and Google Scholar. Inclusion criteria were peer-reviewed articles that evaluated AI systems using CBCT images for detection and segmentation purposes and achieved reported outcomes in terms of precision and recall, accuracy, based on DICE index and Dice similarity coefficient (DSC). The Cochrane tool for assessing the risk of bias was used to evaluate the studies that were included in this meta-analysis. A random-effects model was used to calculate the pooled effect size. Results: Thirteen studies were included for review and analysis. The pooled performance that measures the included AI models is 0.85 (95%CI: 0.73,0.92) for DICE index/DSC, 0.88 (0.77,0.94) for precision, 0.93 (0.84, 0.97) for recall, and 0.83 (0.68, 0.91) for accuracy percentage. Conclusion: Some limitations are identified in our meta-analysis such as heterogenicity of studies, risk of bias and lack of ground truth. The application of AI for detection and segmentation using CBCT images is comparable to services offered by trained dentists and can potentially expedite and enhance the interpretive process. Implementing AI into clinical dentistry can analyze a large number of CBCT studies and flag the ones with significant findings, thus increasing efficiency. The study protocol was registered in PROSPERO, the international registry for systematic reviews (ID number CRD42021285095).

Comparison of Airway Measurements in Rheumatoid Arthritis and Non-rheumatoid Patients using Lateral Cephalometric Radiographs.

OBJECTIVE: The aim of this study was to investigate the potential relationship between the volumetric area of the upper airway and rheumatoid arthritis (RA) by comparing upper airway measurements between patients with and without RA. METHODS: This case-control study compared upper airway measurements between patients with and without RA using lateral cephalometric radiographs. Two distinct measurements were made: the area of the upper airway, which is defined as "the area extending from the point of the retro-palatal region to the base of the epiglottis," and the distance of the upper airway, which is defined as "the distance between the anterior border of the third cervical vertebra (C3) and the anterior border of the soft tissue of the neck". A single examiner performed all measurements, and the intra-examiner reliability was assessed. RESULTS: Sixty-one RA patients and 95 non-RA patients were included in the case and control groups, respectively. RA patients were significantly older in age and with higher BMI values. Patients with or without RA had Angle Class II as the most prevalent orthodontic classification. The upper airway was slightly narrower in RA patients, resulting in a smaller area, and the length of the upper airway was significantly longer in RA patients. CONCLUSION: Patients with RA have narrower upper airways as measured on lateral cephalometric radiographs. This may partially explain the high prevalence of obstructive sleep apnea among patients with RA. Focusing on airways measurements when cephalometric radiographs are taken for patients with RA could give some idea about which patient is likely to have OSA.

Degenerative Joint Disease of the Upper Cervical Spines: A Cone Beam Computed Tomography Study.

OBJECTIVES: To investigate the prevalence, imaging features, and predictors (age and gender) of upper cervical spine degenerative joint disease (DJD). METHODS: Two oral radiologists retrospectively reviewed the cone-beam computed tomography (CBCT) examinations conducted at a university-based imaging center over 1 year. They recorded the imaging findings related to the upper cervical spine (C1C2) and collected patient demographic data. Then the data of the patients with and without DJD findings in the upper cervical spine were compared. RESULTS: The prevalence of upper cervical DJD was 45.6%. There were no gender-based differences in upper cervical DJD. The prevalence of upper cervical DJD increased steadily with age. There was a statistically significantly difference in the prevalence of upper cervical DJD at all the age ranges. CONCLUSIONS: DJD of the upper cervical spine is a relatively common incidental finding frequently captured in CBCT scans acquired for dental purposes.

The prevalence and causes of wrong tooth extraction.

BACKGROUND: Dental extraction is a common procedure that is subject to complications and errors including extraction of the wrong tooth. This study aimed to determine the prevalence and identify the causes of wrong tooth extractions and explore the attitude of dentists after extraction of a wrong tooth. METHODS: A questionnaire was adapted to fit the needs of this project and was distributed among all the dentists in four teaching dental clinics. The questionnaire was available in both the English and Arabic languages. RESULTS: Of the 486 questionnaires, 186 questionnaires were returned (response rate of 37%) and used for the analysis. The prevalence of wrong tooth extraction was 21.1%. The three most common reasons for extracting a wrong tooth were miscommunication (31.6%), inadequate referral (28.9%), and exhaustion of an overworked dentist (28.9%). Surprisingly, only 50% informed the patient and documented the incident in the patient's chart. Few dentists apologized to their patients or offered any kind of solution or compensation. CONCLUSION: Wrong tooth extraction is a prevalent yet preventable problem. Most of the common causes of this problem appear to be more system rather than individual related. There is a pressing need to implement the universal protocol for the prevention of wrong site, wrong procedure, and wrong person surgery.

A comparative study of the diagnostic capabilities of 2D plain radiograph and 3D cone beam CT sialography.

OBJECTIVE: The aim of this study was to compare the diagnostic capabilities of two-dimensional sialography with a novel three-dimensional technique using cone beam CT (CBCT). METHODS: 47 subjects underwent parotid or submandibular gland sialography over a 2 year period using both plain imaging and CBCT. Both image sets were anonymized and independently reviewed by three certified oral and maxillofacial radiologists blinded to the clinical data. McNemar's χ(2) test was used to determine differences between the two modalities for feature visualization and interpretation. RESULTS: CBCT outperformed plain imaging with respect to visualization of the gland parenchyma (p < 0.001) and identification of sialoliths (p = 0.02). Plain imaging outperformed CBCT for the identification of strictures (p = 0.04); however, the negative per cent agreement ("specificity") between the two imaging modalities was 100%. Although both imaging modalities performed equally in identifying normal and abnormal sialographic examinations, CBCT demonstrated a high negative per cent agreement for normal glands and a high positive per cent agreement ("sensitivity") for abnormal glands with inflammatory changes. CONCLUSION: CBCT sialography allowed better visualization of gland parenchyma and identification of sialoliths. The high negative per cent agreement for strictures suggests that, if strictures are identified on CBCT images, then obstruction can be ruled in. Relative to plain images, the high negative per cent agreement for normal glands suggests that, if an abnormal finding is detected on CBCT images, then disease can be ruled in, and the high positive per cent agreement for glands with inflammatory changes suggests that inflammation can be ruled out if these changes are not seen on CBCT images.

Optimization of exposure parameters for cone beam computed tomography sialography.

OBJECTIVES: The assessment of image quality is a crucial step in the development of a new imaging protocol. Having proposed and reported on a preliminary protocol for sialography using cone beam CT (CBCT), the purpose of this study was to further optimize this protocol by maximizing the image signal difference-to-noise ratio (SDNR) and to relate these new data to previously published dosimetric data for CBCT sialography. METHODS: An imaging phantom was constructed using samples with different concentrations of iodine and a water-immersed mandible. The CB MercuRay (Hitachi Medical Systems, Tokyo, Japan) was used to image the phantom using different peak kilovoltage (kVp) and milliamperage (mA) settings. SDNR was then calculated using the raw images based on mean pixel values (MPV) measured in selected regions of interest (ROI). Finally, a figure of merit (FOM) was calculated to examine the trade-off between image SDNR and effective radiation dose. RESULTS: The SDNR demonstrated an expected increase as the kVp increased from 60 to 120. Also, images made with the higher mA setting (15) had greater SDNR. The iodine concentration also influenced the image quality such that SDNR increased with increased amounts of iodine. The calculated FOM was greatest for the technique using 80 kVp, with equivalent results for 10 mA and 15 mA. CONCLUSION: An optimized protocol for CBCT sialography using CB MercuRay entails a 6 inch field of view with 80 kVp and 10 mA.

Central giant cell granuloma of the mandibular condyle: a case report and review of the literature.

Central giant cell granuloma (CGCG) is a benign intraosseous lesion. The true nature of this lesion is controversial and remains unknown; the three competing theories are that it could be a reactive lesion, a developmental anomaly or a benign neoplasm. Furthermore, the actual aetiology of CGCG is still unclear, although inflammation, haemorrhage and local trauma have all been suggested; it has also been hypothesized that CGCG may have a genetic aetiology. Lesions central to the mandibular condylar head are very rare, with only three documented cases in the English language literature, none of which elaborates on the CT features. In this case report, a 31-year-old male patient complaining of a left pre-auricular mass underwent radiographic investigation. CT images revealed a lesion central to the mandibular condyle and demonstrated features that were highly suggestive of CGCG. The patient underwent surgical curettage, and the subsequent histopathological examination confirmed the diagnosis of CGCG. 3 years after the procedure the patient presented with a recurrence and underwent complete resection of the mandibular condyle with immediate reconstruction. This report presents CT characteristics of a rare occurrence of CGCG of the mandibular condyle, compares it with other published cases and poses the question of the role of radiology in predicting the degree of aggressive behaviour of these lesions before surgery.