Is it feasible to use smartphone images to perform telediagnosis of different stages of occlusal caries lesions?

The accuracy of asynchronous tele-screening for detecting dental caries in patient-captured mobile photos: A pilot study

Objectives

Unaided visual inspection is a primary dental screening technique. Given the uneven distribution of dental services and prolonged waiting periods, an alternative screening approach is required to increase access to dental care. The purpose of this study was to evaluate the accuracy and reliability of tele-screening for detecting dental caries using mobile intra-oral photos taken by participants.

Methods

Dental care seekers attending Umm Al-Qura University Teaching Dental Hospital in 2022 were invited to participate in this study. The participants were initially examined by dental interns at the hospital under the supervision of faculty dentists (reference standard) before intra-oral photos were acquired by a trained sixth-year dental student using a Samsung S10 camera. Following an introduction to the photography guide, the same participants then took intra-oral photos of their teeth at home using their mobile devices, which were all uploaded to WhatsApp for later review. Two trained dental reviewers (sixth-year dental students) independently reviewed the intra-oral photos. Sensitivity, specificity, and Kappa scores were estimated to assess the performance of the tele-screening approach relative to the reference unaided dental examination.

Results

Twenty-three participants, with a mean age of 30 ± 12 years, were enrolled. The mean decayed, missing, and filled teeth (DMFT) was 13.43 ± 5.48. Patient-delivered tele-screening demonstrated a sensitivity, specificity, and inter-rater reliability kappa of 94 %, 90 %, and 0.81, respectively, when compared to unaided dental examination. Dentist-delivered tele-screening approach demonstrated a sensitivity of 88-89 %, specificity of 88-91 %, and kappa score of 0.75-0.79 relative to unaided dental examination.

Conclusions

This study demonstrated that the tele-screening approach based on reviewing intra-oral photos taken by participants can be a valid and reliable alternative to unaided dental examination. This is important for ensuring sustainable access to dental care.

Comparative Evaluation of Dental Caries Score Between Teledentistry Examination and Clinical Examination: A Systematic Review and Meta-Analysis

Dental caries is a common dental health problem affecting all age groups across the globe. Accurate detection and assessment of dental caries are crucial for effective treatment and preventive measures. Teledentistry, which involves remote dental assessment using digital technologies, has shown promise as a potential tool for caries screening. This systematic review and meta-analysis aims to compare the dental caries scores obtained from clinical examinations and teledentistry assessments. Literature searches were conducted across databases such as PubMed, Embase, the Cochrane Library, Scopus, the Web of Science, the Cumulative Index to Nursing and Allied Health Literature (CINAHL), and PsycINFO by using predefined search terms and inclusion criteria. Two reviewers separately extracted the data. The study designs, evaluation techniques, dentition types, mean scores, and follow-up times of the included studies were examined. The New Castle-Ottawa Scale was used to assess the risk of bias. Review Manager (RevMan) (computer program) Version 5.4, The Cochrane Collaboration 2020, was used for the quantitative assessment of the data. Eight studies met the inclusion criteria and were included in the review. The findings revealed that teledentistry assessments (based on intraoral photographs captured using smartphones or intraoral cameras) demonstrated comparable accuracy to traditional clinical examinations in detecting and assessing dental caries. Among the four studies that were quantitatively analysed, no significant difference was noted at p = 0.09. A mean difference of 0.64 (95% confidence interval (CI): -0.10; 1.38) suggested that clinical examination and teledentistry-based checkup were on par with each other for the detection of dental caries. The New Castle-Ottawa scale (NOS) grading indicated that the studies were of good quality. Teledentistry may be an effective approach for identifying and evaluating dental caries. However, further research is required to substantiate the findings observed in the present review.

Visual Diagnostics of Dental Caries through Deep Learning of Non-Standardised Photographs Using a Hybrid YOLO Ensemble and Transfer Learning Model

BACKGROUND

Access to oral healthcare is not uniform globally, particularly in rural areas with limited resources, which limits the potential of automated diagnostics and advanced tele-dentistry applications. The use of digital caries detection and progression monitoring through photographic communication, is influenced by multiple variables that are difficult to standardize in such settings. The objective of this study was to develop a novel and cost-effective virtual computer vision AI system to predict dental cavitations from non-standardised photographs with reasonable clinical accuracy.

METHODS

A set of 1703 augmented images was obtained from 233 de-identified teeth specimens. Images were acquired using a consumer smartphone, without any standardised apparatus applied. The study utilised state-of-the-art ensemble modeling, test-time augmentation, and transfer learning processes. The "you only look once" algorithm (YOLO) derivatives, v5s, v5m, v5l, and v5x, were independently evaluated, and an ensemble of the best results was augmented, and transfer learned with ResNet50, ResNet101, VGG16, AlexNet, and DenseNet. The outcomes were evaluated using precision, recall, and mean average precision (mAP).

RESULTS

The YOLO model ensemble achieved a mean average precision (mAP) of 0.732, an accuracy of 0.789, and a recall of 0.701. When transferred to VGG16, the final model demonstrated a diagnostic accuracy of 86.96%, precision of 0.89, and recall of 0.88. This surpassed all other base methods of object detection from free-hand non-standardised smartphone photographs.

CONCLUSION

A virtual computer vision AI system, blending a model ensemble, test-time augmentation, and transferred deep learning processes, was developed to predict dental cavitations from non-standardised photographs with reasonable clinical accuracy. This model can improve access to oral healthcare in rural areas with limited resources, and has the potential to aid in automated diagnostics and advanced tele-dentistry applications.

Evaluation of the marginal adaptation and gingival status of full-crown restorations using an intraoral camera

Objective

The purpose of this study was to compare the usefulness of intraoral photographs, acquired with a household intraoral camera operating in conventional, calibrated, and polarized modes, with clinical examinations for assessing the marginal adaptation and gingival status of full-crown restorations.

Methods

Clinical examinations were performed by a prosthodontist who classified the marginal adaptation of full-crown restorations according to FDI World Dental Federation criteria, and a periodontal expert who classified gingival status according to the Modified Gingival Index (MGI). The margins and gingival status of the conventional, calibration, and polarization groups of full-crown restorations were independently assessed by three evaluators who obtained photographs using an intraoral camera. Cases where at least two of three assessors were in agreement were analyzed using Cohen’s kappa coefficient and the chi-square test, and the sensitivity and specificity were calculated.

Results

The conventional, calibration, and polarization groups differed significantly in marginal and gingival status of full-crown restorations. In the calibration group, there was good agreement between the camera-based and oral clinical examinations in terms of the gingival status of full-crown restorations (kappa = 0.945), with 100% sensitivity and 91.67% specificity; this was also the case in the polarization group with respect to the margins of full-crown restorations (kappa = 0.917, sensitivity = 97.22%, specificity = 94.44%).

Conclusions

An intraoral camera with black and white calibrated images is useful to assess the gingival status of full-crown restorations. Polarization mode can be used to assess the marginal adaptation of full-crown restorations. The camera is a feasible and valid diagnostic aid.

Accuracy of Teledentistry for Diagnosis and Treatment Planning of Pediatric Patients during COVID-19 Pandemic

Teledentistry is a new technology in the dentistry field, which has great benefits during pandemic such as the coronavirus disease 2019 (COVID-19). The overall purpose of the study was to assess the diagnostic sensitivity and specificity of virtual (mobile phone teledentistry) compared with clinical examinations during COVID-19. The basic design of the study was based on the comparison treatment plans by the students and the gold standard (clinical treatment plan of an expert pedodontist with 10 years of clinical experience). This double-blind clinical trial was conducted on 20 children (aged 6 to 12 years) with a chief complaint of dental caries with or without pain. An appropriate radiograph and five standard intraoral photographs (frontal view occlusion, maxillary occlusal view, mandibular occlusal view, right lateral view, and left lateral view) were prescribed for each patient according to the guidelines of the American Association of Pediatric Dentistry. Then, the treatment plan for the carious teeth was recorded for each patient. Each patient underwent a clinical examination at first and was followed randomly by a virtual examination by two dental students. Then, the clinical and virtual treatment plans were compared with each other, and also with the gold standard. The sensitivity and specificity values were calculated for each group. The accuracy of the diagnosis was measured by applying Cohen's kappa. Interexaminer reliability was measured using the intraclass correlation coefficient (ICC) and Cronbach's alpha. The mean kappa coefficient for the interexaminer agreement (for 24 teeth) was 0.62 in clinical and 0.69 in virtual examinations. The results showed no significant difference in the treatment plans of students and the gold standard (P > 0.05). The diagnostic sensitivity and specificity were 73.22% and 95.8% for clinical and 76.44% and 92.9% for virtual treatment plans showing no significant differences between virtual (mobile phone teledentistry) and clinical examinations (P > 0.05). The intraexaminer reliability of the examiners was found to be 0.92 by calculating the ICC. Then, teledentistry can be considered as a supplement to clinical examinations of pediatric dentistry, finally resulting in better patient management. However, more studies are necessary for teledentistry.

Diagnostic accuracy of a telediagnosis service of oral mucosal diseases: A multicentric survey

OBJECTIVE

The aim of this multicentric study was to assess the diagnostic accuracy of a telediagnosis service for oral mucosal disorders.

STUDY DESIGN

This study included 100 patients seen at the oral medicine outpatient clinic of 3 Brazilian Dental Schools (University of Campinas, Federal University of Pernambuco, and Federal University of Santa Catrina) from March 2019 to October 2019. In addition to the face-to-face assistance provided by graduate students and the final diagnosis validated by the professors of these institutions, a remote evaluation was requested for these patients through the EstomatoNet/TelessaúdeRS platform.

RESULTS

The sensitivity and specificity of telediagnosis were compared with those of the face-to-face approach and found to be 100% and 97.4%, respectively. The concordance between the examiners was 95%, and case management was relatively simple in approximately 60% of cases.

CONCLUSIONS

Based on the results, telediagnosis for oral diseases can be considered a reliable method, representing a promising alternative for the clinical support of health professionals, particularly in remote locations.

Is Teledentistry a Method for Optimizing Dental Practice, Even in the Post-Pandemic Period? An Integrative Review

Background: For the past two and half years, dentists all across the world, along with their patients, have faced numerous challenges. In this context, the aim of this integrative review was to assess if dentists’ and patients’ attitudes regarding teledentistry (TD) have changed since the COVID-19 outbreak, and if the use of TD will continue to rise, even in the post-pandemic period; (2) Methods: A literature search was performed between August 2021 and January 2022. The PubMed, Scopus, and Science Direct databases were searched for articles published between 2012 and 2022 using a combination of the following Mesh terms: “COVID-19”, “pandemic”, “oral telemedicine”, “teledentistry”; (3) Results: Among the 52 included papers, nine papers were published between 2011 and 2019, and 43 articles were published after 2020 (12 were published in 2020, 29 papers were published in 2021, and two in 2022). Among the articles published before 2020, seven out of nine included papers were reviews, and two were original research. Among the 43 papers published after 2020, 18 were reviews and 25 original research. (4) Conclusions: Based on the results of this integrative review, there is clear evidence that the interest in teledentistry and teleassistance in the dental field has increased rapidly, especially in the context of the COVID-19 pandemic. Therefore, while dental practitioners should be encouraged to keep themselves updated about new technologies, patients should also be constantly informed about their options for receiving special oral health care.

Deep Learning Application in Dental Caries Detection Using Intraoral Photos Taken by Smartphones

A mobile-phone-based diagnostic tool, which most of the population can easily access, could be a game changer in increasing the number of examinations of people with dental caries. This study aimed to apply a deep learning algorithm in diagnosing the stages of smooth surface caries via smartphone images. Materials and methods: A training dataset consisting of 1902 photos of the smooth surface of teeth taken with an iPhone 7 from 695 people was used. Four deep learning models, consisting of Faster Region-Based Convolutional Neural Networks (Faster R-CNNs), You Only Look Once version 3 (YOLOv3), RetinaNet, and Single-Shot Multi-Box Detector (SSD), were tested to detect initial caries lesions and cavities. The reference standard was the diagnosis of a dentist based on image examination according to the International Caries Classification and Management System (ICCMS) classification. Results: For cavitated caries, YOLOv3 and Faster R-CNN showed the highest sensitivity among the four tested models, at 87.4% and 71.4%, respectively. The sensitivity levels of these two models were only 36.9 % and 26% for visually non-cavitated (VNC). The specificity of the four models reached above 86% for cavitated caries and above 71% for VNC. Conclusion: The clinical application of YOLOv3 and Faster R-CNN models for diagnosing dental caries via smartphone images was promising. The current study provides a preliminary insight into the potential translation of AI from the laboratory to clinical practice.

Remote assessment of DMFT and number of implants with intraoral digital photography in an elderly patient population – a comparative study

Objectives

This comparative study aimed to evaluate intraoral digital photography (IODP) as assessment-tool for DMFT and number of implants (IMPL) compared to clinical diagnosis (CLIN) in an elderly population with high restorative status. Secondary research questions were whether an additional evaluation of panoramic radiographs (PAN-X) or raters’ clinical experience influence the agreement.

Methods

Fifty patients (70.98±7.60 years) were enrolled for standardized CLIN and IODP. The clinical reference examiner and ten blinded raters evaluated the photographs without and with a PAN-X regarding DMFT and IMPL. CLIN were used as reference standard and differences to IODP and IODP-PAN-X findings were analysed descriptively. To assess intra-rater agreement, pairwise Gwet’s AC1s of the three diagnostic methods CLIN, IODP and IODP+PAN-X were calculated.

Results

Compared to a DMFT of 22.10±3.75 (CLIN), blinded raters evaluated a DMFT of 21.54±3.40 (IODP) and 22.12±3.45 (IODP+PAN-X). Mean values for “Decayed” were 0.18±0.52 (CLIN), 0.45±0.46 (IODP) and 0.48±0.47 (IODP-PAN-X), while 11.02±5.97 (CLIN), 10.66±5.78 (IODP) and 10.93±5.91 (IODP+PAN-X) were determined for “Missing” and 10.90±5.61 (CLIN), 10.43±4.85 (IODP) and 10.71±5.11 (IODP+PAN-X) for “Filled”. IMPL were 0.78±2.04 (CLIN), 0.58±1.43 (IODP), 0.78±2.04 (IODP+PAN-X). Gwet’s AC1 using the mode of the blinded raters’ assessment of "Decayed", "Missing" and IMPL compared to CLIN ranged from 0.81 to 0.89 (IODP) and 0.87 to 1.00 (IODP+PAN-X), while for "Filled" and DMFT they were 0.29 and 0.36 (IODP) as well as 0.33 and 0.36 (IODP+PAN-X), respectively. Clinical experience did not influence the agreement.

Conclusions

Assessment of “Decayed”, “Missing” and IMPL by IODP showed almost perfect agreement, whereas of “Filled” and DMFT revealed fair to moderate agreement with clinical findings. Additional PAN-X-evaluation increased agreement compared to IODP-diagnostics alone. IODP for the assessment of DMFT and IMPL might be a suitable method in large-scale epidemiological studies, considering high agreement in total values and miscellaneous agreement at patient-level.

Dentist perceptions about the value of teledentistry

Background

Teledentistry has expanded access to oral health care by allowing patients and providers the option to receive care using technology and telecommunications. This study used a cross-sectional, mixed-methods design to evaluate dentists’ perceptions in the United States and understanding of the value and scope of teledentistry in their practices and to adopt virtual encounters as a care delivery methodology.

Methods

This study used a cross-sectional, mixed-methods design. The DentaQuest Partnership for Oral Health Advancement (now CareQuest Institute for Oral Health) conducted an electronic survey of providers in the DentaQuest Network that assessed the impact of COVID-19 on dental practices' patient volume, staffing, dental insurance carriers, treatment protocols, and the office's pre-and post-COVID finances. A total of 2767 dental providers completed the survey with a response rate of 13%. Qualitative interviews were then conducted with ten providers to get more in-depth information on teledentistry. Descriptive statistics summarize the survey population. Thematic analysis, which allows both deductive and inductive approaches, were used to analyze the interviews.

Results

About 23% of the dentists used teledentistry or virtual platforms. Findings illustrate that early adopter dentists were more likely to perceive the benefits of teledentistry as being more significant than its drawbacks. Late/resistant adopters to teledentistry were less aware of its benefits and were more focused on the drawbacks, such as upfront cost. Late adopters were also concerned about the level of care delivered through teledentistry.

Conclusions

This study explored dentists’ perceptions of teledentistry. Expanding access to care was recognized as one of the greater values of teledentistry.

Teledentistry in the Management of Patients with Dental and Temporomandibular Disorders

Telemedicine is a subunit of telehealth, and it uses telecommunication technology, video, digital images, and electronic medical records to allow the exchange of clinical information and images over remote distances for dental consultation, diagnosis, and treatment planning. Dental clinical practice requires face-to-face interaction with the patients, and therefore, during the COVID-19 pandemic, it has mostly been suspended. In this view, teledentistry offers the opportunity to continue dental practice, avoiding the face-to-face examination that put patients and healthcare professionals at infection risk. Teledentistry encompasses several subunits such as teleconsultation, telediagnosis, telemonitoring, and teletriage. To date, there are several experiences described in literature that suggest that teledentistry could be applied to support traditional care of different oral diseases. However, there are some issues that need to be addressed. Reimbursement concerns, costs, license regulations, limits in physical examinations, and expert equipment are principal issues that should be overcome in telemedicine and in teledentistry. In this narrative review, we provide an overview of the different teledentistry approaches in the care of patients with dental and temporomandibular disorders, as well as discussing the issues that need to be addressed to implement this approach in clinical practice.

Comparison of color accuracy and picture quality of digital SLR, point and shoot and mobile cameras used for dental intraoral photography - A pilot study

The present study aimed to compare the picture quality and color accuracy of three cameras, namely, Point and shoot, DSLR and mobile cameras, and determine the most suitable camera for dental photography (intra-orally and for casts). A computer program, namely, NRM (No-Reference matrix BRISQUE), was used to evaluate the quality of the photos taken by three cameras. Further, color accuracy was determined by computation of total color difference (ΔE) by identifying the L∗a∗b∗ values.

The ANOVA (Kruskal-Wallis) analysis was done to assess the difference in the quality of cast photos, and it showed a statistically significant difference (p < 0.05) between the cameras. The post hoc analysis showed the NRM value of Point and shoot (18.93 ± 2.04) better than the Mobile phone (20.59 ± 2.65). However, no statistically significant difference was obtained while assessing the picture quality of the intraoral photographs using One-Way ANOVA (Fisher's) (P = 0.05).

Evaluation of total color difference (ΔE) showed fewer differences between the DSLR and the Point and shoot than the mobile camera. There was no statistically significant difference in ΔE value in the participant photographs. The L in the LAB values of both the cast and the participant photograph showed a similar result, with the mobile phone showing a lighter value than the other two cameras. The B value in the participant photos showed a significant difference between the mobile and the Point and shoot cameras.

The quality of Point and shoot, DSLR, and mobile cameras were equally good for taking pictures of any external surface, but the mobile camera offered more brightness and appeared more yellow. On the other hand, the quality was similar for intraoral images with mobile and Point and shoot cameras, although color accuracy was better with Point and shoot and DSLR cameras.

The accuracy of teledentistry in caries detection in children – A diagnostic study

Introduction

: The increasing burden of dental caries and the lack of effective dental caries screening protocols in non-dental settings, such as schools, demand an innovative and cost-effective approach. Teledentistry is the field of dentistry that combines telecommunication with health records and digital imaging to improve access to dental care and help in epidemiological surveys. This study aimed to assess the accuracy of non-dentist teledentistry in caries detection compared with the clinical dental examination of a sample of 5–10-year-old schoolchildren.

Methods

A calibrated dentist examined schoolchildren aged 5–10 years old. The dentist and two teachers took intraoral photographs for each child, using a smartphone. The photographs were concealed; therefore, the dentist assessed the three sets of photographs blindly two weeks after the clinical examination. Accuracy was measured to compare the teledentistry examination with the clinical dental examination.

Results

The mean DMFT of primary teeth was 3.38, 3.42, and 3.17 upon clinical examination, dental-teledentistry examination (findings of photographs taken by a dentist), and non-dental teledentistry (findings of photographs taken by teachers), respectively. The mean DMFT of permanent teeth was 0.75, 0.69, and 0.65 upon clinical examination, dental-teledentistry examination, and non-dental teledentistry examination, respectively. In primary teeth, dental teledentistry and non-dental teledentistry examinations showed 95 and 98.3 sensitivity and 94.3 and 91.4 specificity, respectively. In permanent teeth, dental teledentistry and non-dental teledentistry examinations showed 80.8 and 88.5 sensitivity and 94.1 and 96.1 specificity, respectively.

Conclusions

Teledentistry has acceptable accuracy for caries detection in schoolchildren compared to a clinical dental examination.

Detection of dental caries in oral photographs taken by mobile phones based on the YOLOv3 algorithm

Background

The aim of this study was to explore the value of using the YOLOv3 algorithm for detection and diagnosis of dental caries in oral photographs taken with mobile phones.

Methods

Oral photographs taken with the mobile phones of 570 patients were used as 3 datasets: the augmented images (n=3,990), the enhanced images (n=3,990), and the combined augmented and enhanced images (n=7,980). Oral photographs taken by mobile phones from another 70 patients were used as an independent test set. We used the YOLOv3 network for migration learning for modelling. Diagnostic precision, recall, F1-score, and mean average precision (mAP) were calculated to obtain the detection and diagnostic performance of the YOLOv3 algorithm.

Results

After 3 independent training, the mAP value of the original group YOLOv3 algorithm was 56.20%, in which the precision for primary caries recognition was 76.92%, recall was 49.59%, and F1-score was 0.60; the precision for secondary caries recognition was 91.67%, recall was 52.38%, and F1-score was 0.67. The mAP value of the enhance group algorithm was 66.69%, in which the precision for primary caries identification was 81.82%, recall was 52.07%, and F1-score was 0.64, and the precision for secondary caries identification was 100%, recall was 33.33%, and F1-score was 0.50. The mAP value of the comprehensive group algorithm was 85.48%, in which the precision for primary caries identification was 93.33%, recall was 69.42%, F1-score was 0.80, and the F1-score for secondary caries identification was 0.50; precision was 100%, recall was 52.38%, and F1-score was 0.69.

Conclusions

The caries detection capability based on the YOLOv3 algorithm highlights the potential utility of deep learning in caries detection and diagnosis. Comparing the 3 experiments, the detection of the model trained after using image augmented and enhancement techniques was significantly improved.

Validity of mHealth devices for counting steps in individuals with Parkinson's disease

BACKGROUND

Step quantification is a good way to characterize the mobility and functional status of individuals with some functional disorder. Therefore, a validation study may lead to the feasibility of devices to stimulate an increase in the number of steps and physical activity level of individuals with Parkinson's Disease (PD).

AIM

To investigate the validity of mHealth devices to estimate the number of steps in individuals with PD and compare the estimate with a standard criterion measure.

METHOD

An observational study in a university laboratory with 34 individuals with idiopathic PD. The number of steps was measured using mHealth devices (Google Fit, Health, STEPZ, Pacer, and Fitbit INC®), and compared against a criterionstandard measure during the Two-Minute Walk Test using habitual speed.

RESULTS

Our sample was 82% men with a Hoehn and Yahr mean of 2.3 ± 1.3 and mean walking speed of 1.2 ± 0.2 m/s. Positive and statistically significant associations were found between Google Fit (r = 0.92; p < 0.01), STEPZ (r = 0.91; p < 0.01), Pacer (r = 0.77; p < 0.01), Health (r = 0.54; p < 0.01), and Fitbit Inc® (r = 0.82; p < 0.01) with the criterion-standard measure.

CONCLUSIONS

GoogleFit, STEPZ, Fitbit Inc.®, Pacer, and Health are valid instruments to measure the number of steps over a given period of time with moderate to high correlation with the criterion-standard in individuals with PD. This result shows that technology such as smartphone applications and activity monitor can be used to assess the number of steps in individuals with PD, and allows the possibility of using this technology for assessment and intervention purposes.

Automated caries detection with smartphone color photography using machine learning

Untreated caries is significant problem that affected billion people over the world. Therefore, the appropriate method and accuracy of caries detection in clinical decision-making in dental practices as well as in oral epidemiology or caries research, are required urgently. The aim of this study was to introduce a computational algorithm that can automate recognize carious lesions on tooth occlusal surfaces in smartphone images according to International Caries Detection and Assessment System (ICDAS). From a group of extracted teeth, 620 unrestored molars/premolars were photographed using smartphone. The obtained images were evaluated for caries diagnosis with the ICDAS II codes, and were labeled into three classes: "No Surface Change" (NSC); "Visually Non-Cavitated" (VNC); "Cavitated" (C). Then, a two steps detection scheme using Support Vector Machine (SVM) has been proposed: "C versus (VNC + NSC)" classification, and "VNC versus NSC" classification. The accuracy, sensitivity, and specificity of best model were 92.37%, 88.1%, and 96.6% for "C versus (VNC + NSC)," whereas they were 83.33%, 82.2%, and 66.7% for "VNC versus NSC." Although the proposed SVM system required further improvement and verification, with the data only imaged from the smartphone, it performed an auspicious potential for clinical diagnostics with reasonable accuracy and minimal cost.

Telediagnosis of oral lesions using smartphone photography

OBJECTIVE

The objective of this observational study was to evaluate telediagnosis of oral lesions using smartphone photography.

MATERIALS AND METHODS

Individuals with visible oral lesions composed a convenience sample. The lesions were photographed using a smartphone camera and emailed along with clinical information to three evaluators, who formulated up to two diagnostic hypotheses for each case. A total of 235 photographs from 113 clinical cases were obtained. The evaluators answered questions regarding referral decisions, requests for additional tests, diagnostic difficulties, and image quality. The diagnostic hypotheses were compared to the gold standard by means of percent agreement and kappa coefficient. Consensual face-to-face diagnoses of three specialists-when only a clinical diagnosis was necessary-or histopathological results-when a biopsy was necessary-were considered the gold standard.

RESULTS

The telediagnosis was similar to the gold standard in 76% of the cases, and kappa coefficients showed almost perfect agreement (k = 0.817-0.903). The evaluators considered that referrals could have been avoided on an average of 35,4% of the cases.

CONCLUSION

Diagnosis of oral lesions using images taken with a smartphone showed almost perfect agreement and diagnostic accuracy comparable to face-to-face diagnosis.

Proof-of-Concept Study on an Automatic Computational System in Detecting and Classifying Occlusal Caries Lesions from Smartphone Color Images of Unrestored Extracted Teeth

Dental caries has been considered the heaviest worldwide oral health burden affecting a significant proportion of the population. To prevent dental caries, an appropriate and accurate early detection method is demanded. This proof-of-concept study aims to develop a two-stage computational system that can detect early occlusal caries from smartphone color images of unrestored extracted teeth according to modified International Caries Detection and Assessment System (ICDAS) criteria (3 classes: Code 0; Code 1-2; Code 3-6): in the first stage, carious lesion areas were identified and extracted from sound tooth regions. Then, five characteristic features of these areas were intendedly selected and calculated to be inputted into the classification stage, where five classifiers (Support Vector Machine, Random Forests, K-Nearest Neighbors, Gradient Boosted Tree, Logistic Regression) were evaluated to determine the best one among them. On a set of 587 smartphone images of extracted teeth, our system achieved accuracy, sensitivity, and specificity that were 87.39%, 89.88%, and 68.86% in the detection stage when compared to modified visual and image-based ICDAS criteria. For the classification stage, the Support Vector Machine model was recorded as the best model with accuracy, sensitivity, and specificity at 88.76%, 92.31%, and 85.21%. As the first step in developing the technology, our present findings confirm the feasibility of using smartphone color images to employ Artificial Intelligence algorithms in caries detection. To improve the performance of the proposed system, there is a need for further development in both in vitro and in vivo modeling. Besides that, an applicable system for accurately taking intra-oral images that can capture entire dental arches including the occlusal surfaces of premolars and molars also needs to be developed.

Diagnostic Value of Fluorescence Methods, Visual Inspection and Photographic Visual Examination in Initial Caries Lesion: A Systematic Review and Meta-Analysis

This systematic review and meta-analysis aimed to investigate the efficacy of fluorescence-based methods, visual inspections, and photographic visual examinations in initial caries detection. A literature search was undertaken in the PubMed and Cochrane databases. Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) guidelines were followed, and eligible articles published from 1 January 2009 to 30 October 2019 were included if they met the following criteria: they (1) assessed the accuracy of methods of detecting initial tooth caries lesions on occlusal, proximal, or smooth surfaces in both primary and permanent teeth (in clinical); (2) used a reference standard; (3) reported data regarding the sample size, prevalence of initial tooth caries, and accuracy of the methods. Data collection and extraction, quality assessment, and data analysis were conducted according to Cochrane standards Quality Assessment of Diagnostic Accuracy Studies-2. Statistical analyses were performed using Review Manager 5.3 and STATA 14.0. A total of 12 eligible articles were included in the meta-analysis. The results showed that the sensitivity and specificity of fluorescence-based methods were 80% and 80%, respectively; visual inspection was measured at 80% and 75%, respectively; photographic visual examination was measured at 67% and 79%, respectively. We found that the visual method and the fluorescence method were reliable for laboratory use to detect early-stage caries with equivalent accuracy.

Use of smartphone video calls in the diagnosis of oral lesions: Teleconsultations between a specialist and patients assisted by a general dentist

BACKGROUND

Teleassistance in dentistry enables the support of dentists in areas without access to specialists. The aim of this study was to assess the feasibility and accuracy of synchronous teleconsultation in oral medicine.

METHODS

Patients referred for specialized care owing to oral lesions were evaluated in person by a general dentist who obtained photographs of the lesions with a smartphone. The images were sent via a mobile application to an oral medicine specialist, with whom a video call was initiated on the same instant messaging application. After interviewing the patient, the specialist formulated a diagnostic hypothesis and suggestions for case management. Then a second specialist, blinded to the first evaluation, assessed the oral lesion in person and defined a diagnosis, which was considered as the reference standard. Diagnoses from the remote and the face-to-face consultations were compared in percentage levels of agreement and κ coefficient.

RESULTS

Thirty-three patients, 25 through 83 years old, had 41 oral lesions. The average teleconsultation length was approximately 10 minutes. In 92.7% of the cases, there was concordance between the telediagnosis and the reference standard (κ = 0.922).

CONCLUSIONS

Synchronous teleconsultation can provide reliable remote diagnosis through the support to primary care health care professionals in management of oral lesions.

PRACTICAL IMPLICATIONS

Earlier diagnosis of malignancies, improvement of access for unassisted populations, and reduction of unnecessary referrals are possible practical implications of remote support of a specialist in the management and diagnosis of oral lesions.

Comparison of smartphone-camera and conventional flatbed scanner images for analytical evaluation of chewing function

BACKGROUND

The two-colour mixing test is a quick method to assess chewing function (CF). The use of smartphone cameras for acquiring images may help in further simplifying the process.

OBJECTIVE

This study evaluated the reliability of smartphone-camera images of chewing gums to assess CF.

METHODS

Five test samples of a bicoloured chewing gum were produced by a single fully dentate adult volunteer. The specimens were flattened to 1-mm thick wafers. The two sides of the wafers were digitised with a conventional flatbed scanner (control) and were photographed 20 times using 8 different smartphones. The images were assessed optoelectronically to obtain the variance of hue (VoH) and subjectively by visual assessment (SA) using a categorical scale (SA1-SA5). Spearman's correlation and regression models were used for statistical analyses.

RESULTS

The intra-group variability for SA1-SA3 was <1% for all smartphones, but significantly higher than controls for SA4 and SA5 (smartphone: SA4 = 5.57%; SA5 = 8.76%; control: SA4 = 2.5%; SA5 = 0.79%). VoH was progressively lower from SA1 to SA5 for all imaging devices (r > -.97; P < .001). VoH comparisons between control and smartphone images revealed significant differences for the individual SA categories, and however, the magnitude of differences was small and non-significant when the full range of SA levels were considered. The linear mixed model regression showed significant effects for all the smartphones (P < .001) and SA levels (P < .001) in relation to the flatbed scanner values.

CONCLUSIONS

Smartphone cameras may be used to evaluate colour mixture for a bolus-kneading test, however, the precision is lower with higher degrees of colour mixing.

Teledentistry during COVID-19 pandemic

BACKGROUND AND AIMS

Dentistry involves close face-to-face interaction with patients, hence during the COVID-19 pandemic, it has mostly been suspended. Teledentistry can offer an innovative solution to resume dental practice during this pandemic. In this review, we provide a brief overview of applications of teledentistry.

METHODS

Articles on teledentistry, relevant to this review, were searched and consulted from PubMed, Google Scholar, and Cochrane database.

RESULTS

Teledentistry is the remote facilitating of dental treatment, guidance, and education via the use of information technology instead of direct face-to-face contact with patients. Teleconsultation, telediagnosis, teletriage, and telemonitoring are subunits of teledentistry that have important functions relevant to dental practice. There are many challenges for acceptance of teledentistry by the dentists as well as patients, which need to be addressed urgently.

CONCLUSION

Teledentistry can offer a novel solution to resume dental practice during the current pandemic, hence, the need of the hour is to incorporate teledentistry into routine dental practice. If not fully replace, at least teledentistry can complement the existing compromised dental system during the current pandemic.