Deep Learning-Based Image Classification and Segmentation on Digital Histopathology for Oral Squamous Cell Carcinoma: A Systematic Review and Meta-Analysis.

BACKGROUND: Artificial intelligence (AI)-based tools have shown promise in histopathology image analysis in improving the accuracy of oral squamous cell carcinoma (OSCC) detection with intent to reduce human error. OBJECTIVES: This systematic review and meta-analysis evaluated deep learning (DL) models for OSCC detection on histopathology images by assessing common diagnostic performance evaluation metrics for AI-based medical image analysis studies. METHODS: Diagnostic accuracy studies that used DL models for the analysis of histopathological images of OSCC compared to the reference standard were analyzed. Six databases (PubMed, Google Scholar, Scopus, Embase, ArXiv, and IEEE) were screened for publications without any time limitation. The QUADAS-2 tool was utilized to assess quality. The meta-analyses included only studies that reported true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN) in their test sets. RESULTS: Of 1267 screened studies, 17 studies met the final inclusion criteria. DL methods such as image classification (n = 11) and segmentation (n = 3) were used, and some studies used combined methods (n = 3). On QUADAS-2 assessment, only three studies had a low risk of bias across all applicability domains. For segmentation studies, 0.97 was reported for accuracy, 0.97 for sensitivity, 0.98 for specificity, and 0.92 for Dice. For classification studies, accuracy was reported as 0.99, sensitivity 0.99, specificity 1.0, Dice 0.95, F1 score 0.98, and AUC 0.99. Meta-analysis showed pooled estimates of 0.98 sensitivity and 0.93 specificity. CONCLUSION: Application of AI-based classification and segmentation methods on image analysis represents a fundamental shift in digital pathology. DL approaches demonstrated significantly high accuracy for OSCC detection on histopathology, comparable to that of human experts in some studies. Although AI-based models cannot replace a well-trained pathologist, they can assist through improving the objectivity and repeatability of the diagnosis while reducing variability and human error as a consequence of pathologist burnout.

Artificial intelligence for classification and detection of oral mucosa lesions on photographs: a systematic review and meta-analysis.

OBJECTIVE: This study aimed to review and synthesize studies using artificial intelligence (AI) for classifying, detecting, or segmenting oral mucosal lesions on photographs. MATERIALS AND METHOD: Inclusion criteria were (1) studies employing AI to (2) classify, detect, or segment oral mucosa lesions, (3) on oral photographs of human subjects. Included studies were assessed for risk of bias using Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). A PubMed, Scopus, Embase, Web of Science, IEEE, arXiv, medRxiv, and grey literature (Google Scholar) search was conducted until June 2023, without language limitation. RESULTS: After initial searching, 36 eligible studies (from 8734 identified records) were included. Based on QUADAS-2, only 7% of studies were at low risk of bias for all domains. Studies employed different AI models and reported a wide range of outcomes and metrics. The accuracy of AI for detecting oral mucosal lesions ranged from 74 to 100%, while that for clinicians un-aided by AI ranged from 61 to 98%. Pooled diagnostic odds ratio for studies which evaluated AI for diagnosing or discriminating potentially malignant lesions was 155 (95% confidence interval 23-1019), while that for cancerous lesions was 114 (59-221). CONCLUSIONS: AI may assist in oral mucosa lesion screening while the expected accuracy gains or further health benefits remain unclear so far. CLINICAL RELEVANCE: Artificial intelligence assists oral mucosa lesion screening and may foster more targeted testing and referral in the hands of non-specialist providers, for example. So far, it remains unclear if accuracy gains compared with specialized can be realized.

A hierarchical deep learning approach for diagnosing impacted canine-induced root resorption via cone-beam computed tomography.

OBJECTIVES: Canine-induced root resorption (CIRR) is caused by impacted canines and CBCT images have shown to be more accurate in diagnosing CIRR than panoramic and periapical radiographs with the reported AUCs being 0.95, 0.49, and 0.57, respectively. The aim of this study was to use deep learning to automatically evaluate the diagnosis of CIRR in maxillary incisors using CBCT images. METHODS: A total of 50 cone beam computed tomography (CBCT) images and 176 incisors were selected for the present study. The maxillary incisors were manually segmented and labeled from the CBCT images by two independent radiologists as either healthy or affected by root resorption induced by the impacted canines. We used five different strategies for training the model: (A) classification using 3D ResNet50 (Baseline), (B) classification of the segmented masks using the outcome of a 3D U-Net pretrained on the 3D MNIST, (C) training a 3D U-Net for the segmentation task and use its outputs for classification, (D) pretraining a 3D U-Net for the segmentation and transfer of the model, and (E) pretraining a 3D U-Net for the segmentation and fine-tuning the model with only the model encoder. The segmentation models were evaluated using the mean intersection over union (mIoU) and Dice coefficient (DSC). The classification models were evaluated in terms of classification accuracy, precision, recall, and F1 score. RESULTS: The segmentation model achieved a mean intersection over union (mIoU) of 0.641 and a DSC of 0.901, indicating good performance in segmenting the tooth structures from the CBCT images. For the main classification task of detecting CIRR, Model C (classification of the segmented masks using 3D ResNet) and Model E (pretraining on segmentation followed by fine-tuning for classification) performed the best, both achieving 82% classification accuracy and 0.62 F1-scores on the test set. These results demonstrate the effectiveness of the proposed hierarchical, data-efficient deep learning approaches in improving the accuracy of automated CIRR diagnosis from limited CBCT data compared to the 3D ResNet baseline model. CONCLUSION: The proposed approaches are effective at improving the accuracy of classification tasks and are helpful when the diagnosis is based on the volume and boundaries of an object. While the study demonstrated promising results, future studies with larger sample size are required to validate the effectiveness of the proposed method in enhancing the medical image classification tasks.

Applications of Machine Learning in Facial Cosmetic Surgeries: A Scoping Review.

OBJECTIVE: To review the application of machine learning (ML) in the facial cosmetic surgeries and procedures METHODS AND MATERIALS: Electronic search was conducted in PubMed, Scopus, Embase, Web of Science, ArXiv and Cochrane databases for the studies published until August 2022. Studies that reported the application of ML in various fields of facial cosmetic surgeries were included. The studies' risk of bias (ROB) was assessed using the QUADAS-2 tool and NIH tool for before and after studies. RESULTS: From 848 studies, a total of 29 studies were included and categorized in five groups based on the aim of the studies: outcome evaluation (n = 8), face recognition (n = 7), outcome prediction (n = 7), patient concern evaluation (n = 4) and diagnosis (n = 3). Total of 16 studies used public data sets. ROB assessment using QUADAS-2 tool revealed that six studies were at low ROB, five studies were at high ROB, and others had moderate ROB. All studies assessed with NIH tool showed fair quality. In general, all studies showed that using ML in the facial cosmetic surgeries is accurate enough to benefit both surgeons and patients. CONCLUSION: Using ML in the field of facial cosmetic surgery is a novel method and needs further studies, especially in the fields of diagnosis and treatment planning. Due to the small number of articles and the qualitative analysis conducted, we cannot draw a general conclusion about the impact of ML in the sphere of facial cosmetic surgery. LEVEL OF EVIDENCE IV: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Comparison of pleasant and unpleasant smile characteristics in the perception of the laypeople in an Iranian population.

INTRODUCTION: This study aimed to compare the characteristics of pleasant and unpleasant smiles from the perception of laypeople. METHODS: Two-hundred posed smile photographs were obtained from adult participants with no anomaly, restoration, or severe crowding and spacing in anterior teeth. Photographs were shown to 26 judges to give each photograph a score for attractiveness. Upper and lower quartiles for the most and least rated smiles were determined, and variables including gingival display, smile arc, midline deviation, buccal corridor, smile width, tooth rotation or malposition, diastema, upper and lower vermilion show, and tooth form were measured. Independent-sample t test and Pearson chi-square analysis were used to determine the differences between the pleasant and unpleasant groups for quantitative and qualitative variables, respectively. The linear regression model revealed variables with the most significant impact on the mean score. RESULTS: All quantitative and qualitative variables except tooth form significantly differed between pleasant and unpleasant smile groups (P <0.05). The consonant smile arc was associated with an increase of 12.59% in mean scores compared with the inconsonant smile arc. Each tooth reported with malposition was correlated with a decrease of 9.37% in the scores. In the same way, each 1-mm increase in midline diastema and occlusal cant coincided with a drop of 8.73% and 3.59% in scores, respectively. CONCLUSIONS: The results of this study suggested that smile arc, tooth malposition, midline diastema, and occlusal plane canting had the most impact on smile esthetics and should be given priority by orthodontists in the treatment plan of choice.

Deep learning in periodontology and oral implantology: A scoping review.

Deep learning (DL) has been employed for a wide range of tasks in dentistry. We aimed to systematically review studies employing DL for periodontal and implantological purposes. A systematic electronic search was conducted on four databases (Medline via PubMed, Google Scholar, Scopus, and Embase) and a repository (ArXiv) for publications after 2010, without any limitation on language. In the present review, we included studies that reported deep learning models' performance on periodontal or oral implantological tasks. Given the heterogeneities in the included studies, no meta-analysis was performed. The risk of bias was assessed using the QUADAS-2 tool. We included 47 studies: focusing on imaging data (n = 20) and non-imaging data in periodontology (n = 12), or dental implantology (n = 15). The detection of periodontitis and gingivitis or periodontal bone loss, the classification of dental implant systems, or the prediction of treatment outcomes in periodontology and implantology were major use cases. The performance of the models was generally high. However, it varied given the employed methods (which includes various types of convolutional neural networks (CNN) and multi-layered perceptron (MLP)), the variety in specific modeling tasks, as well as the chosen and reported outcomes, outcome measures and outcome level. Only a few studies (n = 7) showed a low risk of bias across all assessed domains. A growing number of studies evaluated DL for periodontal or implantological objectives. Heterogeneity in study design, poor reporting and a high risk of bias severely limit the comparability of studies and the robustness of the overall evidence.

Effect of mesenchymal stem cells with platelet-rich plasma carriers on bone formation after rapid maxillary expansion: An Animal Study.

OBJECTIVE: To evaluate the effect of bone mesenchymal stem cells (BMSCs) with or without platelet-rich plasma (PRP) carriers on sutural new bone formation after rapid palatal expansion (RPE). SETTINGS AND SAMPLE POPULATION: Sixty male Wistar rats were used in this study. MATERIAL AND METHODS: All samples were subjected to 50cN of palatal expansion force for 7 days followed by 3 weeks of the retention period. The experimental groups received a single-dose injection of the specified solution at the time of retainer placement (BMSCs, PRP, BMSCs+PRP, normal saline). BMSCs used in this study were marked with the green fluorescent protein (GFP). New bone formation (NBF) in the sutural area was evaluated by µCT and occlusal radiography. In addition, semi-quantitative analyses were performed on histology images to analyse the quality of sutural bone, connective tissue and vascularization. Immunohistochemistry analyses were conducted for osteocalcin and collagen type I proteins. RESULTS: After the 21-day retention period, limited GFP marked cells were detected around the sutural area. Samples treated with BMSCs + PRP had the highest NBF and showed higher expression of collagen type I and osteocalcin. CONCLUSION: Injecting BMSCs + PRP may increase sutural bone density significantly. However, injecting BMSCs or PRP carriers alone did not affect sutural bone density.

Role of ACE2 polymorphism in COVID-19: impact of age.

More than 2 million people have died as a result of the COVID-19 outbreak. Angiotensin-converting enzyme 2 (ACE2) is a counter-regulatory enzyme that converts angiotensin-2 to Ang-(1-7) form in the renin-angiotensin system. Several studies have been analyzed the correlation between ACE2 and COVID-19. Indeed, ACE2/Ang (1-7) system protects the lung against acute respiratory distress syndrome by its anti-inflammatory/anti-oxidant function. However, SARS-Cov-2 can use ACE2 for host cell entry. Expression of ACE2 can be altered by several factors, including hypertension, diabetes and obesity, which also could increase the severity of COVID-19 infection. Besides, since androgens increase the expression of ACE-2, males are at higher risks of COVID-19 infection. Although reported statistics showed a significantly different infection risks of COVID-19 between adults and children, the reason behind the different responses is still unclear. This review proposes the effect of ACE polymorphism on the severity of SARS-COV-2 induced pneumonia. The previous meta-analysis regarding the effect of ACE polymorphism on the severity of pneumonia showed that polymorphism only affects the adult's illness severity and not the children. Two recent meta-analyses examined the effect of ACE polymorphism on the prevalence and mortality rate of COVID-19 and reported contradicting results. Our opinion paper suggests that the effect of ACE polymorphism on the severity of COVID-19 depends on the patients age, same as of the pneumonia.

Machine learning and orthodontics, current trends and the future opportunities: A scoping review.

INTRODUCTION: In recent years, artificial intelligence (AI) has been applied in various ways in medicine and dentistry. Advancements in AI technology show promising results in the practice of orthodontics. This scoping review aimed to investigate the effectiveness of AI-based models employed in orthodontic landmark detection, diagnosis, and treatment planning. METHODS: A precise search of electronic databases was conducted, including PubMed, Google Scholar, Scopus, and Embase (English publications from January 2010 to July 2020). Quality Assessment and Diagnostic Accuracy Tool 2 (QUADAS-2) was used to assess the quality of the articles included in this review. RESULTS: After applying inclusion and exclusion criteria, 49 articles were included in the final review. AI technology has achieved state-of-the-art results in various orthodontic applications, including automated landmark detection on lateral cephalograms and photography images, cervical vertebra maturation degree determination, skeletal classification, orthodontic tooth extraction decisions, predicting the need for orthodontic treatment or orthognathic surgery, and facial attractiveness. Most of the AI models used in these applications are based on artificial neural networks. CONCLUSIONS: AI can help orthodontists save time and provide accuracy comparable to the trained dentists in diagnostic assessments and prognostic predictions. These systems aim to boost performance and enhance the quality of care in orthodontics. However, based on current studies, the most promising application was cephalometry landmark detection, skeletal classification, and decision making on tooth extractions.

The influence of initial alveolar ridge defect morphology on the outcome of implants in augmented atrophic posterior mandible: an exploratory retrospective study.

OBJECTIVES: Clinicians commonly consider atrophic site topography as an important determinant in deciding the augmentation technique to utilize, as well as forecasting the likelihood of success. The purpose of this retrospective study was to examine the influence of initial atrophic posterior mandible morphology on the outcome of implants placed following augmentation. MATERIALS AND METHODS: A total of 52 patients contributed 71 edentulous sites, and 185 implants were placed with mean follow-up of 37.97 months. The initial defect morphology was classified according to ABC classification (Journal of Oral Implantology, 37, 2013a and 361). Ridge augmentation was performed by "cortical autogenous tenting" (CAT) followed by either simultaneous or delayed implant placement after 4-6 months of healing. The European Academy of Osseointegration success criteria were used to evaluate implant outcomes. RESULTS: The overall survival and success rates of dental implants were 98.91% and 80%, respectively. Cumulative success and survival rates in CAT group were 95% and 100% after 2 years of follow-up. The highest marginal bone loss (MBL) was observed (1.26 mm ± 0.99) around implants placed in augmented edentulous sites with initially narrow and flat alveolar crest (defect class CII). Conversely, least MBL (0.48 mm ± 0.78) was detected around implants placed into edentulous sites with two sloped boney walls (defect class AII). Differences between MBL observed around implants placed into initial defect class C, initial defect type and class A (I, II), as well as class BII, were statistically significant (P < 0.05). Among all implants, 148 were considered as successful, 26 exhibited satisfactory survival, nine with compromised survival, and two implants failed. CONCLUSION: The present data confirmed the effect of initial ridge morphology on the outcome of implants placed into augmented bone. Specifically, class A and class B atrophic ridge defects, with one and two vertical boney walls, respectively, may be considered as more favorable recipient sites than class C defects with flat morphology. This conclusion is based on least MBL around implants placed into initial defect class A and class B augmented sites, and higher MBL in implants placed into class C recipient sites. A randomized controlled trial is warranted to examine these exploratory observations.

Thickness of labial alveolar bone overlying healthy maxillary and mandibular anterior teeth.

AIM: This study aimed to measure the thickness of labial bone overlying maxillary and mandibular anterior teeth and the distance between cementoenamel junction and bone crest in a Persian population. MATERIALS & METHODS: Two calibrated examiners evaluated tomographic data of 152 maxillary and 200 mandibular anterior teeth. Labial bone width was assessed at levels 1.0 to 5.0 mm apical to bone crest. Moreover, the distance between cementoenamel junction and bone crest was measured for both maxillary and mandibular teeth and its potential effect on the amount of labial bone thickness was assessed. RESULTS: One hundred-twenty nine maxillary central incisors, 77 lateral incisors, 70 canines, 105 mandibular central incisors, 103 lateral incisors and 81 canines were included for measurements. In maxilla, width of bone averaged 1.08mm, 1.11mm, and 1.3mm for central incisors, lateral incisors, and canines, respectively. Corresponding numbers for mandibular central incisors, lateral incisors, and canines were 0.74mm, 0.66mm and 0.40mm. High variation of cementoenamel junction to bone crest distance (range 0.5 to 5.15 mm) was detected. The mean amount of labial bone width was not statistically different in patients with different distances between cementoenamel junction and bone crest; except for mandibular lateral incisors. CONCLUSION: The mean thickness of the labial alveolar bone overlying maxillary anterior teeth was found to be between 1 to 1.2 mm and between 0.5 to 0.8 mm for mandibular anterior teeth at the first 5 mm from bone crest in a Persian population.

Artificial Intelligence for Detection of External Cervical Resorption Using Label-Efficient Self-Supervised Learning Method.

INTRODUCTION: The aim of this study was to leverage label-efficient self-supervised learning (SSL) to train a model that can detect ECR and differentiate it from caries. METHODS: Periapical (PA) radiographs of teeth with ECR defects were collected. Two board-certified endodontists reviewed PA radiographs and cone beam computed tomographic (CBCT) images independently to determine presence of ECR (ground truth). Radiographic data were divided into 3 regions of interest (ROIs): healthy teeth, teeth with ECR, and teeth with caries. Nine contrastive SSL models (SimCLR v2, MoCo v2, BYOL, DINO, NNCLR, SwAV, MSN, Barlow Twins, and SimSiam) were implemented in the assessment alongside 7 baseline deep learning models (ResNet-18, ResNet-50, VGG16, DenseNet, MobileNetV2, ResNeXt-50, and InceptionV3). A 10-fold cross-validation strategy and a hold-out test set were employed for model evaluation. Model performance was assessed via various metrics including classification accuracy, precision, recall, and F1-score. RESULTS: Included were 190 PA radiographs, composed of 470 ROIs. Results from 10-fold cross-validation demonstrated that most SSL models outperformed the transfer learning baseline models, with DINO achieving the highest mean accuracy (85.64 ± 4.56), significantly outperforming 13 other models (P < .05). DINO reached the highest test set (ie, 3 ROIs) accuracy (84.09%) while MoCo v2 exhibited the highest recall and F1-score (77.37% and 82.93%, respectively). CONCLUSIONS: This study showed that AI can assist clinicians in detecting ECR and differentiating it from caries. Additionally, it introduced the application of SSL in detecting ECR, emphasizing that SSL-based models can outperform transfer learning baselines and reduce reliance on large, labeled datasets.

Deep learning for diagnosis of head and neck cancers through radiographic data: a systematic review and meta-analysis.

PURPOSE: This study aims to review deep learning applications for detecting head and neck cancer (HNC) using magnetic resonance imaging (MRI) and radiographic data. METHODS: Through January 2023, a PubMed, Scopus, Embase, Google Scholar, IEEE, and arXiv search were carried out. The inclusion criteria were implementing head and neck medical images (computed tomography (CT), positron emission tomography (PET), MRI, Planar scans, and panoramic X-ray) of human subjects with segmentation, object detection, and classification deep learning models for head and neck cancers. The risk of bias was rated with the quality assessment of diagnostic accuracy studies (QUADAS-2) tool. For the meta-analysis diagnostic odds ratio (DOR) was calculated. Deeks' funnel plot was used to assess publication bias. MIDAS and Metandi packages were used to analyze diagnostic test accuracy in STATA. RESULTS: From 1967 studies, 32 were found eligible after the search and screening procedures. According to the QUADAS-2 tool, 7 included studies had a low risk of bias for all domains. According to the results of all included studies, the accuracy varied from 82.6 to 100%. Additionally, specificity ranged from 66.6 to 90.1%, sensitivity from 74 to 99.68%. Fourteen studies that provided sufficient data were included for meta-analysis. The pooled sensitivity was 90% (95% CI 0.820.94), and the pooled specificity was 92% (CI 95% 0.87-0.96). The DORs were 103 (27-251). Publication bias was not detected based on the p-value of 0.75 in the meta-analysis. CONCLUSION: With a head and neck screening deep learning model, detectable screening processes can be enhanced with high specificity and sensitivity.

Effect of mechanical forces on the behavior of osteoblasts: a systematic review of in vitro studies.

Mechanical loading can play a critical role in bone modeling/remodeling through osteoblasts, with several factors being involved in this process.The present study aims to systematically review the effect of mechanical stimulation on human osteoblast cell lineage combined with other variables.The PubMed and Scopus databases were electronically searched for studies analyzing the effect of compression and tension on human osteoblasts at different differentiation stages. Studies that used carcinogenic osteoblasts were excluded. In addition, studies that did not analyze the osteogenic differentiation or proliferation of cells were excluded. The risk of bias of the studies was evaluated using the modified CONSORT (Consolidated Standards of Reporting Trials) checklist. a total of 20 studies were included. The cells were subjected to tension and compression in 5 and 15 studies, respectively. The application of uniaxial and cyclic strain increased the proliferation of osteoblasts. The same increased pattern could be observed for the osteogenesis of the cells. The impact of the tensile force on the expression of the osteoclastic markers differed based on the loading characteristics. On the other side, the impact of compression on the proliferation of osteoblasts varied according to the magnitude and duration of the force. Besides, different patterns of alternations were observed among the osteogenic markers in response to compression. Meanwhile, compression increased the expression of the osteoclastic markers. It has been shown that the response of the markers related to bone formation or resorption can be altered based on the differentiation stage of the cells, the cell culture system, and the magnitude and duration of the force.

Evaluation of facial profile characteristics of aesthetically pleasing Iranian faces.

BACKGROUND: The objective of this study was to assess the soft and hard tissue cephalometric indexes of facial profiles perceived as attractive. METHODS: A total of 360 individuals (180 females and 180 males) with well-balanced faces and no history of orthodontic or cosmetic procedures were selected. Twenty-six raters (13 females and 13 males) rated the attractiveness of profile view photographs of the enrolled individuals. According to the total score, the rated top 10% of photographs were selected as attractive. Overall, 81 (40 soft tissue and 41 hard tissue) cephalometric measurements were made on traced cephalograms of the attractive faces. The obtained values were compared with orthodontic norms and attractive Whites using Bonferroni-corrected t tests. They were also analyzed regarding age and sex effects using a two-way ANOVA test. RESULTS: Significant differences were found between the cephalometric measurements of attractive profiles and orthodontic norms. Among the most important parameters were greater H angle and basic upper lip thickness in attractive males, and greater facial convexity and smaller nose prominence in attractive females. Also, attractive male participants had greater soft tissue chin thickness and subnasale perpendicular to the upper lip compared with attractive females. CONCLUSIONS: According to the results, males with a normal profile and thicker protruded upper lips were perceived as more attractive. Also, females with a slightly convex profile, deeper mentolabial sulcus, less prominent nose, and shorter maxilla and mandible were perceived as more attractive.

Application of chemical factors for acceleration of consolidation phase of the distraction osteogenesis: a scoping review.

PURPOSE: This study aimed to analyze the effect of injecting chemical factors compared to conventional distraction osteogenesis (DO) treatment on the bone formation of the distracted area of the maxillofacial region in human and animal studies. METHOD: Electronic search was done in PubMed, Scopus, Embase, and Cochrane database for studies published until September 2021. The studies' risk of bias (ROB) was assessed using the Cochrane Collaborations and NIH quality assessment tools. Meta-analyses were performed to assess the difference in the amount of bone formation and maximal load tolerance. RESULTS: Among a total of 58 included studies, eight studies analyzed the bone formation rate of the distracted area in human models and others in animal models. Results of the human studies showed acceptable outcomes in the case of using bone morphogenic protein-2 (BMP-2), autologous bone-platelet gel, and calcium sulfate. However, using platelet reach plasma does not increase the rate of bone formation significantly. Quantitative analyses showed that both BMP-2 (SMD = 26.57; 95% CI = 18.86 to 34.28) and neuron growth factor (NGF) (SMD = 16.19; 95% CI = 9.64 to 22.75) increase the amount of bone formation. Besides, NGF increased the amount of load tolerance significantly (SMD = 30.03; 95% CI = 19.91 to 40.16). Additionally, BMP-2 has no significant impact on the post-treatment maxillary length (SMD = 9.19; 95% CI = - 2.35 to 20.73). CONCLUSION: Limited number of human studies with low quality used chemical factors to enhance osteogenesis and showed acceptable results. However, more studies with higher quality are required.

Effects of distraction osteogenesis with Le Fort osteotomies on upper airway volumes: a systematic review and meta-analyses.

OBJECTIVE: Distraction osteogenesis is one of the treatment options in patients with severe maxillomandibular abnormalities to treat morphological and respiratory problems (obstructive sleep apnea syndrome). The study aimed to evaluate the effect of Le Fort I, II and III distraction osteogenesis (DO) on upper airway dimensions and respiratory function. METHODS: Electronic search was performed in PubMed, Scopus, Embase, Google Scholar and Cochrane databases. Studies that only involved two dimensional analyses were excluded. Besides, studies that performed DO in conjunction with orthognathic surgery were not considered. NIH quality assessment tool was used to evaluate the risk of bias. Meta-analyses were performed to assess sleep apnea indices and the mean differences in the airway dimensions before and after DO. Gradings of Recommendations, Assessment, Development and Evaluation were used to analyze the evidence level. RESULTS: Among the 114 studies that went under full-text analyses, 11 articles met the inclusion criteria. Results of the quantitative analyses showed that maxillary Le Fort III DO significantly increased the amounts of oropharyngeal, pharyngeal and upper airway volumes. However, apnea-hypopnea index (AHI) showed a non-significant improvement after this procedure. Besides, the dimensions of the airways increased with Le Fort I and II DO, according to a qualitative analysis. Considering the design of the included studies, our results had a low level of evidence. CONCLUSION: Maxillary Le Fort DO does not significantly impact AHI, while it significantly increases the airway dimensions. Meanwhile, multicentric studies with standardized evaluation are still required to confirm the effects of maxillary Le Fort DO on airway obstruction.

A deep learning framework to scale linear facial measurements to actual size using horizontal visible iris diameter: a study on an Iranian population.

Digital images allow for the objective evaluation of facial appearance and abnormalities as well as treatment outcomes and stability. With the advancement of technology, manual clinical measurements can be replaced with fully automatic photographic assessments. However, obtaining millimetric measurements on photographs does not provide clinicians with their actual value due to different image magnification ratios. A deep learning tool was developed to estimate linear measurements on images with unknown magnification using the iris diameter. A framework was designed to segment the eyes' iris and calculate the horizontal visible iris diameter (HVID) in pixels. A constant value of 12.2 mm was assigned as the HVID value in all the photographs. A vertical and a horizontal distance were measured in pixels on photographs of 94 subjects and were estimated in millimeters by calculating the magnification ratio using HVID. Manual measurement of the distances was conducted on the subjects and the actual and estimated amounts were compared using Bland-Altman analysis. The obtained error was calculated as mean absolute percentage error (MAPE) of 2.9% and 4.3% in horizontal and vertical measurements. Our study shows that due to the consistent size and narrow range of HVID values, the iris diameter can be used as a reliable scale to calibrate the magnification of the images to obtain precise measurements in further research.

Deep Learning for Detection of Periapical Radiolucent Lesions: A Systematic Review and Meta-analysis of Diagnostic Test Accuracy.

INTRODUCTION: The aim of this systematic review and meta-analysis was to investigate the overall accuracy of deep learning models in detecting periapical (PA) radiolucent lesions in dental radiographs, when compared to expert clinicians. METHODS: Electronic databases of Medline (via PubMed), Embase (via Ovid), Scopus, Google Scholar, and arXiv were searched. Quality of eligible studies was assessed by using Quality Assessment and Diagnostic Accuracy Tool-2. Quantitative analyses were conducted using hierarchical logistic regression for meta-analyses on diagnostic accuracy. Subgroup analyses on different image modalities (PA radiographs, panoramic radiographs, and cone beam computed tomographic images) and on different deep learning tasks (classification, segmentation, object detection) were conducted. Certainty of evidence was assessed by using Grading of Recommendations Assessment, Development, and Evaluation system. RESULTS: A total of 932 studies were screened. Eighteen studies were included in the systematic review, out of which 6 studies were selected for quantitative analyses. Six studies had low risk of bias. Twelve studies had risk of bias. Pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio of included studies (all image modalities; all tasks) were 0.925 (95% confidence interval [CI], 0.862-0.960), 0.852 (95% CI, 0.810-0.885), 6.261 (95% CI, 4.717-8.311), 0.087 (95% CI, 0.045-0.168), and 71.692 (95% CI, 29.957-171.565), respectively. No publication bias was detected (Egger's test, P = .82). Grading of Recommendations Assessment, Development and Evaluationshowed a "high" certainty of evidence for the studies included in the meta-analyses. CONCLUSION: Compared to expert clinicians, deep learning showed highly accurate results in detecting PA radiolucent lesions in dental radiographs. Most studies had risk of bias. There was a lack of prospective studies.

Evaluation of the association between gingival phenotype and alveolar bone thickness: A systematic review and meta-analysis.

OBJECTIVE: To conduct a systematic review and meta-analysis of studies that evaluated the association between gingival phenotype (GP) and the underlying alveolar bone thickness (ABT). DESIGN: An electronic search was performed in PubMed, Embase, Scopus, ProQuest, and Web of Science. The following inclusion criteria were applied: English original studies that compared the ABT in periodontally healthy patients presenting thin versus thick GPs. Studies that evaluated the correlation between gingival thickness (GT) and ABT were also included. Pooled mean difference (95% confidence interval) was estimated using random-effects maximum likelihood model meta-analysis. RESULTS: From a total of 1427 retrieved articles, 17 were included. The majority of eight studies that compared the ABT between thick and thin GPs, reported a significantly greater ABT associated with a thick phenotype. Based on the meta-analysis results of six studies, the mean difference between the two phenotypes (0.33 mm) was statistically significant (P < 0.01). The majority of ten studies that investigated the correlation between GT and ABT evidenced a significant positive correlation (r = 0.11 -0.49). The association was more evident in the crestal areas and decreased toward the apex. CONCLUSIONS: There is contradictory evidence concerning the correlation between soft and hard tissue thickness; however, the meta-analysis revealed a significantly thicker alveolar plate in the presence of a thick phenotype. Since the evaluation of GP could be simply performed using a periodontal probe, such a relationship could provide clinical perspective at the initial examination. This is particularly beneficial in procedures affecting periodontal structures, including immediate implant placement and orthodontic treatments.