Background: Acceleration of mass vaccination strategies is the only pathway to overcome the COVID-19 pandemic. Healthcare professionals and students have a key role in shaping public opinion about vaccines. This study aimed to evaluate the attitudes of dental students globally towards COVID-19 vaccines and explore the potential drivers for students’ acceptance levels. Methods: A global cross-sectional study was carried out in February 2021 using an online questionnaire. The study was liaised by the scientific committee of the International Association of Dental Students (IADS), and data were collected through the national and local coordinators of IADS member organizations. The dependent variable was the willingness to take the COVID-19 vaccine, and the independent variables included demographic characteristics, COVID-19-related experience, and the drivers of COVID-19 vaccine-related attitude suggested by the WHO SAGE. Results: A total of 6639 students from 22 countries, representing all world regions, responded to the questionnaire properly. Their mean age was 22.1 ± 2.8 (17–40) years, and the majority were females (70.5%), in clinical years (66.8%), and from upper-middle-income economies (45.7%). In general, 22.5% of dental students worldwide were hesitant, and 13.9% rejected COVID-19 vaccines. The students in low- and lower-middle-income (LLMI) economies had significantly higher levels of vaccine hesitancy compared to their peers in upper-middle- and high-income (UMHI) economies (30.4% vs. 19.8%; p < 0.01). Conclusions: The global acceptance level of dental students for COVID-19 vaccines was suboptimal, and their worrisome level of vaccine hesitancy was influenced by the socioeconomic context where the dental students live and study. The media and social media, public figures, insufficient knowledge about vaccines, and mistrust of governments and the pharmaceutical industry were barriers to vaccination. The findings of this study call for further implementation of epidemiology (infectious diseases) education within undergraduate dental curricula.

Segmentation of anatomical structures on dento-maxillo-facial (DMF) computed tomography (CT) or cone beam computed tomography (CBCT) scans is increasingly needed in digital dentistry. The main aim of this research was to propose and evaluate a novel open source tool called DentalSegmentator for fully automatic segmentation of five anatomical structures on DMF CT and CBCT scans: maxilla/upper skull, mandible, upper teeth, lower teeth, and the mandibular canal. A retrospective sample of 470 CT and CBCT scans was used as a training/validation set. The performance and generalizability of the tool was evaluated by comparing segmentations provided by experts and automatic segmentations in two hold-out test datasets: an internal dataset of 133 CT and CBCT scans acquired before orthognathic surgery and an external dataset of 123 CBCT scans randomly sampled from routine examinations in 5 institutions. The mean overall results in the internal test dataset (n = 133) were a Dice similarity coefficient (DSC) of 92.2 ± 6.3 % and a normalised surface distance (NSD) of 98.2 ± 2.2 %. The mean overall results on the external test dataset (n = 123) were a DSC of 94.2 ± 7.4 % and a NSD of 98.4 ± 3.6 %. The results obtained from this highly diverse dataset demonstrate that this tool can provide fully automatic and robust multiclass segmentation for DMF CT and CBCT scans. To encourage the clinical deployment of DentalSegmentator, the pre-trained nnU-Net model has been made publicly available along with an extension for the 3D Slicer software. DentalSegmentator open source 3D Slicer extension provides a free, robust, and easy-to-use approach to obtaining patient-specific three-dimensional models from CT and CBCT scans. These models serve various purposes in a digital dentistry workflow, such as visualization, treatment planning, intervention, and follow-up.

This study aims to evaluate the diagnostic accuracy of artificial intelligence in detecting apical pathosis on periapical radiographs. A total of twenty anonymized periapical radiographs were retrieved from the database of Poznan University of Medical Sciences. These radiographs displayed a sequence of 60 visible teeth. The evaluation of the radiographs was conducted using two methods (manual and automatic), and the results obtained from each technique were afterward compared. For the ground-truth method, one oral and maxillofacial radiology expert with more than ten years of experience and one trainee in oral and maxillofacial radiology evaluated the radiographs by classifying teeth as healthy and unhealthy. A tooth was considered unhealthy when periapical periodontitis related to this tooth had been detected on the radiograph. At the same time, a tooth was classified as healthy when no periapical radiolucency was detected on the periapical radiographs. Then, the same radiographs were evaluated by artificial intelligence, Diagnocat (Diagnocat Ltd., San Francisco, CA, USA). Diagnocat (Diagnocat Ltd., San Francisco, CA, USA) correctly identified periapical lesions on periapical radiographs with a sensitivity of 92.30% and identified healthy teeth with a specificity of 97.87%. The recorded accuracy and F1 score were 96.66% and 0.92, respectively. The artificial intelligence algorithm misdiagnosed one unhealthy tooth (false negative) and over-diagnosed one healthy tooth (false positive) compared to the ground-truth results. Diagnocat (Diagnocat Ltd., San Francisco, CA, USA) showed an optimum accuracy for detecting periapical periodontitis on periapical radiographs. However, more research is needed to assess the diagnostic accuracy of artificial intelligence-based algorithms in dentistry.

The development of artificial intelligence (AI) in dentistry requires large and well-annotated datasets. However, the availability of public dental imaging datasets remains unclear. This study aimed to provide a comprehensive overview of all publicly available dental imaging datasets to address this gap and support AI development. This observational study searched all publicly available dataset resources (academic databases, preprints, and AI challenges), focusing on datasets/articles from 2020 to 2023, with PubMed searches extending back to 2011. We comprehensively searched for dental AI datasets containing images (intraoral photos, scans, radiographs, etc.) using relevant keywords. We included datasets of >50 images obtained from publicly available sources. We extracted dataset characteristics, patient demographics, country of origin, dataset size, ethical clearance, image details, FAIRness metrics, and metadata completeness. We screened 131,028 records and extracted 16 unique dental imaging datasets. The datasets were obtained from Kaggle (18.8%), GitHub, Google, Mendeley, PubMed, Zenodo (each 12.5%), Grand-Challenge, OSF, and arXiv (each 6.25%). The primary focus was tooth segmentation (62.5%) and labeling (56.2%). Panoramic radiography was the most common imaging modality (58.8%). Of the 13 countries, China contributed the most images (2,413). Of the datasets, 75% contained annotations, whereas the methods used to establish labels were often unclear and inconsistent. Only 31.2% of the datasets reported ethical approval, and 56.25% did not specify a license. Most data were obtained from dental clinics (50%). Intraoral radiographs had the highest findability score in the FAIR assessment, whereas cone-beam computed tomography datasets scored the lowest in all categories. These findings revealed a scarcity of publicly available imaging dental data and inconsistent metadata reporting. To promote the development of robust, equitable, and generalizable AI tools for dental diagnostics, treatment, and research, efforts are needed to address data scarcity, increase diversity, mandate metadata completeness, and ensure FAIRness in AI dental imaging research.

Since healthcare professionals (HCPs) play a critical role in shaping their local communities' attitudes toward vaccines, HCPs' beliefs and attitudes toward vaccination are of vital importance for primary prevention strategies. The present study was designed as a cross-sectional survey-based study utilizing a self-administered questionnaire to collect data about COVID-19 vaccine booster hesitancy (VBH) among Polish HCPs and students of medical universities (MUSs). Out of the 443 included participants, 76.3% were females, 52.6% were HCPs, 31.8% were previously infected by SARS-CoV-2, and 69.3% had already received COVID-19 vaccine booster doses (VBD). Overall, 74.5% of the participants were willing to receive COVID-19 VBD, while 7.9 and 17.6% exhibited their hesitance and rejection, respectively. The most commonly found promoter for acceptance was protection of one's health (95.2%), followed by protection of family's health (81.8%) and protection of community's health (63.3%). Inferential statistics did not show a significant association between COVID-19 VBH and demographic variables, e.g., age and gender; however, the participants who had been previously infected by SARS-CoV-2 were significantly more inclined to reject the VBD. Protection from severe infection, community transmission, good safety profile, and favorable risk-benefit ratio were the significant determinants of the COVID-19 VBD acceptance and uptake. Fear of post-vaccination side effects was one of the key barriers for accepting COVID-19 VBD, which is consistent with the pre-existing literature. Public health campaigns need to highlight the postulated benefits of vaccines and the expected harms of skipping VBD.

Background: Since the novel coronavirus disease (COVID-19) outbreak, the cases of COVID-19 co-infections have been increasingly reported worldwide. Mucormycosis, an opportunistic fungal infection caused by members of the Mucorales order, had been frequently isolated in severely and critically ill COVID-19 patients. Methods: Initially, the anamnestic, clinical, and paraclinical features of seven COVID-19-associated mucormycosis (CAM) cases from Egypt were thoroughly reported. Subsequently, an extensive review of the literature was carried out to describe the characteristics of CAM cases globally, aiming to explore the potential risk factors of mortality in CAM patients. Results: Out of the seven reported patients in the case series, five (71.4%) were males, six (85.7%) had diabetes mellitus, and three (42.9%) had cardiovascular disease. All patients exhibited various forms of facial deformities under the computed tomography scanning, and two of them tested positive for Mucorales using the polymerase chain reaction (PCR) testing. Liposomal amphotericin B (LAmB) was prescribed to all cases, and none of them died until the end of the follow-up. On reviewing the literature, 191 cases were reported worldwide, of which 74.4% were males, 83.2% were from low-middle income countries, and 51.4% were aged 55 years old or below. Diabetes mellitus (79.1%), chronic hypertension (30%), and renal disease/failure (13.6%) were the most common medical comorbidities, while steroids (64.5%) were the most frequently prescribed medication for COVID-19, followed by Remdesivir (18.2%), antibiotics (12.7%), and Tocilizumab (5.5%). Conclusions: As the majority of the included studies were observational studies, the obtained evidence needs to be interpreted carefully. Diabetes, steroids, and Remdesivir were not associated with increased mortality risk, thus confirming that steroids used to manage severe and critical COVID-19 patients should not be discontinued. Lung involvement, bilateral manifestation, and Rhizopus isolation were associated with increased mortality risk, thus confirming that proactive screening is imperative, especially for critically ill patients. Finally, surgical management and antimycotic medications, e.g., amphotericin B and posaconazole, were associated with decreased mortality risk, thus confirming their effectiveness.