A deep learning method for multi-task intelligent detection of oral cancer based on optical fiber Raman spectroscopy.

In the fight against oral cancer, innovative methods like Raman spectroscopy and deep learning have become powerful tools, particularly in integral tasks encompassing tumor staging, lymph node staging, and histological grading. These aspects are essential for the development of effective treatment strategies and prognostic assessment. However, it is important to note that most research so far has focused on solutions to one of these problems and has not taken full advantage of the potential wealth of information in the data. To compensate for this shortfall, we conceived a method that combines Raman spectroscopy with deep learning for simultaneous processing of multiple classification tasks, including tumor staging, lymph node staging, and histological grading. To achieve this innovative approach, we collected 1750 Raman spectra from 70 tissue samples, including normal and cancerous tissue samples from 35 patients with oral cancer. In addition, we used a deep neural network architecture to design four distinct multi-task network (MTN) models for intelligent oral cancer diagnosis, named MTN-Alexnet, MTN-Googlenet, MTN-Resnet50, and MTN-Transformer. To determine their effectiveness, we compared these multitask models to each other and to single-task models and traditional machine learning methods. The preliminary experimental results show that our multi-task network model has good performance, among which MTN-Transformer performs best. Specifically, MTN-Transformer has an accuracy of 81.5%, a precision of 82.1%, a sensitivity of 80.2%, and an F1_score of 81.1% in terms of tumor staging. In the field of lymph node staging, the accuracy, precision, sensitivity, and F1_score of MTN-Transformer are 81.3%, 83.0%, 80.1%, and 81.5% respectively. Similarly, for the histological grading classification tasks, the accuracy was 83.0%, the precision 84.3%, the sensitivity 76.7%, and the F1_score 80.2%. This code is available at https://github.com/ISCLab-Bistu/MultiTask-OralRamanSystem.

Structural brain feature is associated with changes of masticatory performance in healthy elderly people: Evidence from longitudinal neuroimaging research over two years.

BACKGROUND: Human neuroimaging studies have revealed the association between brain structure and masticatory function. However, the majority of the studies adopted a cross-sectional design, which hardly reveals the change in masticatory function and brain structure between different timepoints, and the dynamical association between changes in masticatory function and changes in brain structure has not been elucidated. OBJECTIVE: With a longitudinal design, we assessed the association between changes in masticatory performance (MP) and regional brain volume. METHODS: Twenty-two elderly participants received assessments of the number of missing teeth and MP (via colour-changeable chewing gum) when they entered the study (i.e. the initial stage, T0 ), approximately 6 months later (T0.5 ), and approximately 1-2 years later (T1 ). Difficulty of food intake was assessed using a questionnaire. The participants received magnetic resonance imaging (MRI) at T0 and T1 . The brain volume of the motor-related area was estimated using FreeSurfer for MRI data. The associations between different stages were analysed using Spearman's rho correlation coefficients. RESULTS: (1) Individually, a smaller volume of right primary motor cortex at T0 was associated with increased MP from T0 to T1 , suggesting the brain's role in changing oral functions; (2) higher MP at T0 was associated with an increased volume of the left superior frontal cortex from T0 to T1 p, suggesting a potential effect on brain plasticity, and (3) increased difficulty to eat was associated with decrease MP but not brain volume of motor-related area. CONCLUSIONS: The preliminary findings revealed a complicated pattern of structural brain features and masticatory function in elderly people, and either the hypothesis that the brain predisposes masticatory function or the hypothesis that mastication reshapes the brain is oversimplified.

Misconceptions about Oral Diagnosis and Radiology among Dental Students: A Questionnaire Study.

BACKGROUND: Misconceptions are learning deficits that may cause clinical judgments in a dental practice to be made incorrectly. AIM: This study aimed to identify and look into students' misconceptions regarding Oral Diagnosis and Radiology. MATERIALS AND METHODS: The fourth and fifth-grade students at the Altinbas University Faculty of Dentistry were given a self-administered questionnaire that included multiple-choice questions about Oral Diagnosis/Medicine and Radiology. 106 students participated in the questionnaire and 50.9% of the participants were fourth-grade students, 49.1% of them were fifth-grade students. The questions were classified into two parts: five scenario-based questions and ten knowledge-based questions. Students' replies were evaluated for accuracy and confidence, and when a student was certain of giving an inaccurate response, misconceptions were noted. Two groups were compared using the Mann-Whitney-U test (P = 0.05). RESULTS: A total of 1590 responses were collected. Regarding the question type, scenario-based questions had more misconceptions (19.6%) than knowledge-based questions (18.4%). Depending on the question, the majority of misconceptions were seen in the questions about denture stomatitis (46.2%) and radiographic contrast (38.7%). CONCLUSIONS: To prevent misdiagnosis, it is essential to recognize and overcome misconceptions in Oral Diagnosis/Medicine and Radiology. Therefore this study assists students and lecturers in defining misconceptions and organizing precautions to avoid and fix them.

John Greenwood's sidenotes on a 1778 John Hunter text at The New York Academy of Medicine.

John Greenwood (1760-1819) was George Washington's preferred dentist. He practiced in New York and made at least one of eight sets of dentures Washington wore (currently in the collection of the New York Academy of Medicine (NYAM). We know very little about John Greenwood's (JG) formal education, except that he came from a famous family of dentists. He inherited from his father, Isaac Greenwood, one important book of the time, John Hunter's 1778 treatise, A Natural History of the Human Teeth. That copy was donated to the New York Academy of Medicine by descendants of John Greenwood. Recently, we became aware of extensive marginalia that John Greenwood wrote in this book. The present article describes John Greenwood's opinion on a variety of dental subjects such as the causes and mechanisms of tooth destruction and gum disease and the presence of microscopic annamalcula that were thought to be connected to poor oral hygiene. Although John Greenwood was self-educated, his observations are surprisingly insightful and at least 37 years ahead of what was described in the contemporary literature.

The development of an online serious game for oral diagnosis and treatment planning: evaluation of knowledge acquisition and retention.

BACKGROUND: While serious games seem to be supportive in healthcare education, none of them had been designed to develop competence in diagnosis and treatment planning of oral lesions. Therefore, this research aimed to develop an online simulation-based serious game for training diagnosis and treatment planning of oral lesions (SimOL) and to evaluate its educational impact in terms of knowledge improvement and retention. METHODS: As a mandatory task in an oral lesion course, all 28 students were required to participate in SimOL activities. Participants were instructed to complete a pre-knowledge assessment following a one-week washout period prior to the game activity. Subsequent to the game completion, they were tasked to complete a post-knowledge assessment I (Full score = 15) and satisfaction questionnaire. A post-knowledge assessment II was administered a week later to evaluate knowledge retention. RESULTS: The findings demonstrated a significant increase in the assessment scores after interacting with the game (P < 0.001), where the pre- and immediate post-knowledge assessment scores were 8.00 (SD = 2.11) and 11.71 (SD = 2.39), respectively. The game also exhibited a positive impact on knowledge retention, as there was no significant difference between the scores of post-knowledge assessment I and II (P > 0.05). Additionally, students perceived the game as positively in all aspects, although the entertainment aspect achieved a slightly lower score of 3.70 (SD = 0.21), in comparison to the usefulness and ease of use with a score of 4.02 (SD = 0.11) and 4.02 (SD = 0.16), respectively. CONCLUSION: SimOL demonstrated its potential as an effective learning tool for improving and retaining knowledge for diagnosis and treatment planning of oral lesions. The game was perceived positively by dental students in all aspects, however further improvements should prioritize the enhancement of entertaining components.

Prevalence of white spot lesions in children up to 71 months of age in Gujarat state.

Introduction: The earliest sign of a new carious lesion is the appearance of chalky white spots on the surface of the tooth, indicating an area of demineralization of enamel. At this stage, the demineralization process can be reversed or arrested. This study aimed to determine the prevalence of white spot lesions (WSLs) among children up to 71 months in Gujarat state and to increase awareness among parents about its various preventive measures. Materials and Methods: Oral examination was done using the mouth mirror and tongue depressor. The prevalence of WSL was recorded using the International Caries Detection and Assessment System II coding and WSL index by Gorelick. Results: The overall prevalence of WSL was 31.8% (n = 2025) in Gujarat state. The parents of the participating children explained the various preventive measures to prevent decay followed by diet counseling and toothbrushing techniques. Conclusion: Knowledge of the actual prevalence of WSL will help in the implementation of appropriate and timely preventive measures required to decrease the incidence of early childhood caries in that region.

Multi-modal deep learning for automated assembly of periapical radiographs.

OBJECTIVES: Periapical radiographs are oftentimes taken in series to display all teeth present in the oral cavity. Our aim was to automatically assemble such a series of periapical radiographs into an anatomically correct status using a multi-modal deep learning model. METHODS: 4,707 periapical images from 387 patients (on average, 12 images per patient) were used. Radiographs were labeled according to their field of view and the dataset split into a training, validation, and test set, stratified by patient. In addition to the radiograph the timestamp of image generation was extracted and abstracted as follows: A matrix, containing the normalized timestamps of all images of a patient was constructed, representing the order in which images were taken, providing temporal context information to the deep learning model. Using the image data together with the time sequence data a multi-modal deep learning model consisting of two residual convolutional neural networks (ResNet-152 for image data, ResNet-50 for time data) was trained. Additionally, two uni-modal models were trained on image data and time data, respectively. A custom scoring technique was used to measure model performance. RESULTS: Multi-modal deep learning outperformed both uni-modal image-based learning (p<0.001) and time-based learning (p<0.05). The multi-modal deep learning model predicted tooth labels with an F1-score, sensitivity and precision of 0.79, respectively, and an accuracy of 0.99. 37 out of 77 patient datasets were fully correctly assembled by multi-modal learning; in the remaining ones, usually only one image was incorrectly labeled. CONCLUSIONS: Multi-modal modeling allowed automated assembly of periapical radiographs and outperformed both uni-modal models. Dental machine learning models can benefit from additional data modalities. CLINICAL SIGNIFICANCE: Like humans, deep learning models may profit from multiple data sources for decision-making. We demonstrate how multi-modal learning can assist assembling periapical radiographs into an anatomically correct status. Multi-modal learning should be considered for more complex tasks, as clinically a wealth of data is usually available and could be leveraged.

Teledentistry: A Future Solution in the Diagnosis of Oral Lesions: Diagnostic Meta-Analysis and Systematic Review.

Introduction: Teledentistry (TD) can offer a wide range of possibilities in the field of oral medicine. Oral potentially malignant disorders (OPMDs) are hard to detect, and even harder to diagnose correctly. With the help of TD, OPMDs can be detected and diagnosed by a remote specialist. Our aim was to investigate whether TD could provide a reliable diagnostic method compared with clinical oral examination (COE) in the diagnosis of OPMDs. Methods: A systematic search was conducted in three databases (Medline, EMBASE, CENTRAL) until November 2021. We included studies that compared telediagnosis and COE, both made by experts. Pooled specificity and sensitivity were calculated and visualized on a two-dimensional plot. Risk of bias was assessed using the QUADAS-2 tool, and the level of evidence is shown with the Grades of Recommendation, Assessment, Development and Evaluation (GRADE) tool. Results: Of the 7,608 studies, 13 were included in the qualitative and 9 in the quantitative synthesis. Using TD tools in the detection of oral lesions (OLs) showed high specificity (0.92 confidence interval [95% CI] = 0.59-0.99) and sensitivity (0.93 95% CI = 0.17-1.00). In the differential diagnosis of lesions, we found high sensitivity and specificity (0.942 95% CI = 0.826-0.982 and 0.982 95% CI = 0.913-0.997), respectively. We summarized the available data on time-effectiveness, screening person, referral decision, and technical settings. Conclusion: Detecting OLs with TD tools might lead to earlier diagnosis, treatment, and stricter follow-up of OPMD. TD may offer a great substitution for COE in the diagnosis of OLs, and thus, fewer referrals could be made to special care, resulting in a greater number of treated OPMDs.

Burning mouth disorder and Parkinson's disease: A scoping review of the literature.

BACKGROUND: Burning mouth disorder (BMD) is a complex medical condition characterized by a burning sensation in the mouth of fluctuating intensity. BMD is considered a diagnosis of exclusion, as oral burning can occur secondary to local or systemic conditions. Parkinson's disease (PD) is one such condition. OBJECTIVE: To provide a scoping review of the literature by assessing all articles written in English that investigated the relationship between BMD and PD. MATERIALS AND METHODS: Various databases (PubMed, Ovid, Web of Science, Science Direct and Scopus) and a search platform (EBSCOhost) were searched following similar investigative approaches. Duplicates were removed and reference lists of original studies were scrutinized for additional articles. Any decision about the inclusion/exclusion in the review was by consensus among the co-authors. RESULTS: Twenty-five original articles and one supplemental article were included in the final review, of which 13 met the inclusion criteria. These were further divided into five categories based on the study design/article, which included Prevalence studies (n = 6), Letter to the editor (n = 1), Incidence study (n = 1), Case reports (n = 2) and Experimental studies (n = 3). Strongest data was provided by epidemiological studies, which suggest BMD and PD are poorly associated. CONCLUSIONS: A scoping review of the existing literature does not suggest that PD patients are any more at risk of developing BMD compared to the general population. While there may be a link through the dopaminergic system as determined by imaging studies, it is unlikely that the pathogenesis of PD disease shares significant commonality with BMD.

Effects of lesion size on the 30-month clinical performance of restorations with bulk fill and a regular nanofilled resin composite in noncarious cervical lesions.

OBJECTIVE: The aim of this double-blind, randomized trial was to evaluate the influence of the occlusogingival distance (OGD) in noncarious cervical lesions (NCCLs) on the clinical performance of a regular bulk-fill resin composite and a regular nanofilled resin composite. MATERIALS AND METHODS: One hundred and forty NCCLs in 77 participants were randomly divided into four groups (n = 35), according to OGD (1.5 mm ± 10% or 3 mm ± 10%) and resin composites (Filtek Bulk Fill Posterior [B] or Filtek Z350 XT [C]), namely: 1.5 mm-B, 1.5 mm-C, 3 mm-B, and 3 mm-C. The restorations were bonded using a two-step self-etch adhesive (Clearfil SE Bond), applied following the manufacturer's instructions. Restorations were polished 1 week after placement. Two experienced and calibrated examiners evaluated the restorations using modified US Public Health Service criteria at baseline (7 days) and after 6, 12, 18, 24, and 30 months. Statistical analyses were carried out using Kruskal-Wallis, Friedman's repeated measures analysis of variance, and the Wilcoxon signed rank test (α = 0.05). RESULTS: After 30 months, the recall rate was 94.2%. Eight restorations were lost (3 for 1.5 mm-C, 2 for 1.5 mm-B, 1 for 3 mm-C, and 2 for 3 mm-B). All groups resulted in a significantly worse marginal discoloration and surface texture at 30 months in comparison with the baseline (1 week). No significant difference was found for the other parameters. CONCLUSION: The restorations performed with both resin composites produced clinically acceptable restorations. The OGD of NCCLs did not influence the clinical performance of restorations. CLINICAL SIGNIFICANCE: The OGD of NCCLs did not have a significant effect on the clinical performance of a regular bulk-fill and nanofilled restorations. Both materials showed a very good performance on 30-month evaluation.

Oral examination of fourth-year medical students on surgery rotations allows faculty to assess Core Entrustable Professional Activities for entering Residency (CEPAR): Proof-of-concept and analysis of student submissions.

BACKGROUND: As a community-based medical school which recruited faculty preceptors new to teaching, we sought to create objective assessments for fourth-year surgery experiences via administration of an oral exam. Students provided three authentic cases, which faculty used as a springboard to ascertain student proficiency in five entrustable professional activities: 1-oral presentation, 2-recognition of urgency/instability, 3-calling consults, 4-transitions of care, 5-informed consent. We present proof-of-concept and analysis of student case submissions. METHODS: Twenty-seven student submissions (79 cases in total) were evaluated for case complexity, level-appropriateness, and an estimation of the ability to conduct a quality exam based on the information provided (subjective measures). Objective metrics included word count, instruction adherence, inclusion of figures/captions. A resident-in-training rated cases via the same metrics. In-examination data was separately culled. RESULTS: The average word count was 281.70 (SD 140.23; range 40-743). Figures were included in 26.1% of cases. Faculty raters scored 29.0% as low-complexity, 37.7% medium-complexity, and 33.3% high-complexity. Raters felt 62.3% of cases provided enough information to conduct a quality exam. The majority of cases submitted (65.2%) were level-appropriate or higher. The resident rater scored cases more favorably than surgeons (Cohen's kappa of -0.5), suggesting low inter-rater agreement between those of differing experience levels. CONCLUSION: Student's case submissions lessened faculty burden and provided assessors with adequate information to deliver a quality exam to assess proficiency in clinical skills essential for residency. Cases demonstrated sufficient complexity and level-appropriateness. The request to correlate case rating with exam performance is under review by our institution's assessment office. Near-peer tutoring by resident alumni is a program under development.

Radiographic ratios for classifying furcation anatomy: proposal of a new evaluation method and an intra-rater and inter-rater operator reliability study.

OBJECTIVES: Even if it seems to be an important anatomical parameter for tissue regeneration, few studies in literature evaluate the "mean measure" of root divergence. Most of them are linear measurements, which hardly describe the dental furcation conformation in its entirety. It is left to the subjectivity of the operator deciding whether a furcation is convergent or divergent. The goal of this study is to create a visual evaluation method using specific measurements applied on endo-oral X-rays to overcome these problems, giving a conformation of the entire interradicular space and its divergence. MATERIAL AND METHODS: A user-friendly software (Paint®, Windows10®) was used to take three different measurements on endo-oral radiographs of upper and lower molars. Three blind operators measured 20 radiographs, to analyze the intra- and inter-operator reproducibility of the measurements. Then, the technique was repeated on 250 radiographic images to identify an average value and define a main conformation of the interradicular space. The ratio of these three measurements allowed to develop a new visual evaluation method of the interradicular space. RESULTS: Intra and inter-operator reproducibility was statistically confirmed on a sample of 20 anonymous endo-oral radiographs measured by 3 blind operators, indicating that the measurement technique was not operator dependent. Measurement made on 250 X-rays obtained with this technique permitted to subdivide in five groups the conformation of the interradicular space and define a mean value of the interradicular space. CONCLUSIONS: A new anatomical evaluation of the interradicular space in its entirety, which could help the clinicians in diagnostic and decisional phase in the therapy of furcated molars, can be obtained. CLINICAL RELEVANCE: A pre-operative evaluation of interradicular space conformation could affect therapy treatment choice.

[Evaluating the relationship between oral health status in male workers and question item regarding subjective chewing symptoms].

OBJECTIVES: In recent years, the relationship between oral health status and various diseases has been increasingly reported worldwide, leading to a growing understanding of the importance of oral health. This study aimed to investigate the relationship between oral health status, determined after a dental health check-up, and chewing condition, determined via a questionnaire for specific health check-ups with the newly added chewing condition item-When you chew your food, which most accurately describes your chewing-. METHODS: From 20,834 Japanese workers who underwent dental health check-ups and specific health check-ups from April 2018 to March 2019, 4,011 male workers (51.2 ± 6.1 years, range 40-64 years) were extracted for this study. Participants were divided into two groups, the good chewing condition group (GCG) and poor chewing condition group (PCG), according to their responses to a questionnaire regarding chewing conditions. We collected and compared data on subjects' age, smoking status, number of teeth present, number of filled teeth, number of decayed teeth, number of missing teeth with prosthetic treatment, periodontal pockets, gingival bleeding, oral hygiene status, and Eichner's classification. Additionally, to clarify the risk associated with chewing condition, we performed stepwise multiple logistic regression analysis with good chewing condition/poor chewing condition as the dependent variable, and age, smoking status, number of teeth present, number of filled teeth, number of missing teeth with prosthetic treatment, periodontal pockets, oral hygiene status, and Eichner's classification as the independent variables. RESULTS: The result of stepwise multiple logistic regression analyses, the odds ratio (OR) and 95% confidence interval (95% CI) of the factors that remained in the final model were as follows; the number of decayed teeth (OR = 1.18 [95% CI: 1.12-1.24]); periodontal pockets of 3 mm or less vs. 6 mm or more (OR = 1.63 [95% CI: 1.12-2.37]); Eichner's classification A1 vs. A2 (OR = 1.40 [95% CI: 1.08-1.82]), A3 (OR = 1.66 [95% CI: 1.09-2.52]), B1 (OR = 3.38 [95% CI: 2.04-5.61]), B2 (OR = 5.26 [95% CI: 2.46-11.2]), B3 (OR = 4.28 [95% CI: 1.20-15.2]), B4 (OR = 7.59 [95% CI: 1.06-54.5]). CONCLUSIONS: The results of this study suggest a significant association between the newly added "chewing condition" item in the questionnaire for specific health check-ups and oral status; the number of decayed teeth, periodontal pockets, Eichner's classification.

Care-resistant behaviour during oral examination in Dutch nursing home residents with dementia.

OBJECTIVE: To assess the occurrence and associations of verbal and non-verbal care-resistant behaviour (CRB) during oral examination by a dental hygienist in nursing home residents with dementia. BACKGROUND: CRB is a barrier to providing professional oral care and daily oral hygiene care. Understanding the predictors of CRB might help care professionals in learning to anticipate this behaviour. METHODS: In this multicentre cross-sectional study signs of verbal and non-verbal CRB were reported during the oral examination. Data collection occurred in the psychogeriatrics wards of 14 different nursing homes in the Netherlands (N = 367). RESULTS: A total of 367 residents were included. CRB was evident in 82 residents (22.3%), of whom 45 (55%) showed verbal and 37 (45%) non-verbal CRB. Associated with CRB were age >85 years, duration of residential stay longer than 2 years, and having Korsakov dementia. Other factors associated with CRB were duration of residential stay (categories ">2 and ≤4 years" or ">4 years") and having a natural dentition (P = .043-.005, OR = 1.20-1.33, 95% CI = 1.00-8.48). Significant associations for verbal and non-verbal CRB were age between 76 and 85 years, vascular dementia and Korsakov dementia (P = .031-.006, OR = .020-1.49, 95% CI = 0.43-2.15). CONCLUSION: The occurrence of CRB was 22.3% and was associated with older age and longer duration of residential stay, Vascular and Korsakov dementia and natural dentition.

Origin and Development of Cervical Dentin Hypersensitivity and Noncarious Cervical Lesions: Literature Review.

This article reports on published literature for causative factors of cervical dentin hypersensitivity and noncarious cervical lesions. The author conducted an exhaustive literary review of both conditions to examine etiologic co-factors involved for these dental findings. Previous literature found that these two conditions arise from combinations of dental stress distant from occlusal contacts, biocorrosion, and possibly friction. It is impossible to separate these three factors for the modern dentate human due to masticatory function and tooth contact when swallowing. The author concludes that in vivo study is needed to clarify the roles that etiologic factors play in the development of this type of dental pain and/or noncarious lesions. The clinical significance of this review is that a dental and medical history and active etiologic factors need to be uncovered for cervical dentin hypersensitivity with resulting noncarious cervical lesions. The successful clinician needs to determine causative factors, if possible, prior to treatment.