Designing an artificial intelligence system for dental occlusion classification using intraoral photographs: A comparative analysis between artificial intelligence-based and clinical diagnoses.

INTRODUCTION: This study aimed to design an artificial intelligence (AI) system for dental occlusion classification using intraoral photographs. Moreover, the performance of this system was compared with that of an expert clinician. METHODS: This study included 948 adult patients with permanent dentition who presented to the Department of Orthodontics, School of Dentistry, Mashhad University of Medical Sciences, during 2022-2023. The intraoral photographs taken from the patients in left, right, and frontal views (3 photographs for each patient) were collected and underwent augmentation, and about 7500 final photographs were obtained. Moreover, the patients were clinically examined by an expert orthodontist for malocclusion, overjet, and overbite and were classified into 6 groups: Class I, Class II, half-cusp Class II, Super Class I, Class III, and unclassifiable. In addition, a multistage neural network system was created and trained using the photographs of 700 patients. Then, it was used to classify the remaining 248 patients using their intraoral photographs. Finally, its performance was compared with that of the expert clinician. All statistical analyses were performed using the Stata software (version 17; Stata Corp, College Station, Tex). RESULTS: The accuracy, precision, recall, and F1 score of the AI system in the malocclusion classification of molars were calculated to be 93.1%, 88.6%, 91.2%, and 89.7%, respectively, whereas the AI system had an accuracy, precision, recall, and F1 score of 89.1%, 88.8%, 91.42%, and 89.8% for malocclusion classification of canines, respectively. Moreover, the mean absolute error of the AI system accuracy was 1.98 ± 2.11 for overjet and 1.28 ± 1.60 for overbite classifications. CONCLUSIONS: AI exhibited remarkable performance in detecting all classes of malocclusion, which was higher than that of orthodontists, especially in predicting angle classification. However, its performance was not acceptable in overjet and overbite measurement compared with expert orthodontists.

Comparing the efficacy of a novel mucoadhesive patch containing Nigella sativa 10% with triamcinolone 0.1% in patients with erosive-atrophic oral lichen planus: A pilot study.

OBJECTIVE: This study evaluates the efficacy of a novel mucoadhesive patch containing Nigella sativa 10% extract compared to triamcinolone 0.1% in alleviating symptoms and reducing lesion severity in patients with erosive-atrophic oral lichen planus. METHODS AND MATERIALS: A pilot study comprising two groups, each with 10 patients, was conducted. The intervention group received mucoadhesive patches containing N. sativa 10% extract, while the control group received triamcinolone acetonide 0.1% patches. Pain and burning intensity, measured through visual analog scale, and lesion severity based on the Thongprasom scale were assessed weekly for 4 weeks. Descriptive records were kept for side effects and patient satisfaction. RESULTS: Pain and burning intensity decreased in both groups throughout the sessions, with the N. sativa group showing a greater reduction than the triamcinolone group. The reduction in burning intensity within each group was significant (p < .001), and there was a significant difference between groups only in the second session (p = .045). The overall difference between groups was not significant (p > .05). Lesion severity also decreased significantly in both groups (p < .001), with a significant difference between groups observed in the third session (p = .043) and overall throughout the study (p = .006). CONCLUSION: The use of N. sativa extract in mucoadhesive patches was as effective as corticosteroids in reducing pain, burning, and lesion severity in patients with oral lichen planus, with N. sativa showing superior results in some sessions. Notably, no significant complications were observed with N. sativa use, making it a promising treatment option for lichen planus.

Enhancing oral function: A case report on mandibular overdenture utilization with custom-made subperiosteal implant.

Subperiosteal implants, previously set aside because of complications, are now emerging again as effective treatments for severe mandibular atrophy, aided by recent improvements in digital dentistry. Traditional dentures in such cases often face challenges with support and retention, necessitating complex regenerative procedures. This paper presents a case report of a 54-year-old male patient with significant mandibular atrophy who received a custom-made subperiosteal implant, showcasing promising results. The implant was precisely designed utilizing computed tomography (CT) scans, a 3D-printed model, the selective laser melting (SLM) technique, and constructed with biocompatible Ti6Al4V material. This innovative approach offered a practical solution, resulting in high patient satisfaction and no complications over a year of use.

Effect of shape and design of the internal connection of tissue-level and bone-level implants on detorque values and removal forces: An in vitro study.

STATEMENT OF PROBLEM: Optimal implant stability and preventing complications such as screw loosening are paramount concerns for implant-supported prostheses. However, studies examining the influence of various internal connection designs on detorque values and removal forces, critical aspects of implant success, are lacking. PURPOSE: The purpose of this in vitro study was to assess the impact of the shape and design of the internal connection in tissue-level and bone-level implants on the detorque value and the force required for abutment removal from the implant. MATERIAL AND METHODS: Forty dental implants were securely mounted in 10×6×20-mm acrylic resin blocks positioned perpendicular to the surface. The implants were divided into 4 groups (n=10): bone-level SM Torx, tissue-level PSI Torx, bone-level UF Hex, and tissue-level UF Hex implants. After exposure to a dynamic loading test at 31.2 N, 2 Hz and 106 cycles, measurements were made of both detorque values and removal forces. Statistical analyses, including 1-way ANOVA with a post hoc Tukey test and Kolmogorov-Smirnov test, were conducted to assess the results (α=.05). RESULTS: The differences in detorque values among the 4 groups were statistically similar (P=.087). In terms of removal force values, tissue-level PSI implants exhibited the highest values, while bone-level UF implants had the lowest values, with significant differences in the removal forces among the 4 groups (P<.001). Pairwise comparisons revealed significant differences among the groups (P<.001), except for the comparison between tissue-level PSI and bone-level SM implants (P=.108). CONCLUSIONS: While detorque values remain consistent across implant types, the shape and design of the internal connection of implants has a significant impact on the removal force required for abutment detachment from the implant.

Comparison of Stress and Strain Distribution Patterns in Canine Implant and Maxillary Bone in Three Occlusal Schemes Using Finite Element Analysis.

OBJECTIVES: This study aimed to compare the pattern of stress and strain distribution in canine implant and maxillary bone in the anterior group function (AGF), posterior group function (PGF), and canine guidance (CG) occlusal schemes by finite element analysis (FEA). MATERIAL AND METHODS: In this in vitro experimental study, a dental implant (10 × 4.1 mm) was inserted at the site of the maxillary canine in a model of the maxilla in Mimics software. The implant was scanned three-dimensionally and the data were transferred to SolidWorks software. The von Mises stress, shear stress, deformation, and strain were calculated in the AGF, PGF, and CG occlusal schemes by FEA. STATISTICAL ANALYSIS: Data were analyzed by ABAQUS software to calculate the stress transferred to the canine implant and maxillary bone in the three occlusal schemes. RESULTS: The maximum and minimum von Mises stress, elastic strain, shear stress, and deformation were noted in the AGF and PGF occlusal schemes, respectively, in all teeth. CONCLUSION: The PGF showed minimum von Mises stress, elastic strain, shear stress, and deformation in the canine implant and maxillary bone. Thus, it appears than the PGF is the best occlusal scheme for maxillary canine implant followed by the CG scheme.

Electromyographic Evaluation of Masticatory Muscle Activity in Individuals with and without Cleft Lip/Palate: A Systematic Review and Meta-analysis.

OBJECTIVE: This study aims to systematically review and meta-analyze the electromyographic activity of masticatory muscles in cleft palate and non-cleft patients, and identify influencing factors. DESIGN: Systematic Review and Meta-analysis. PATIENTS AND EXPOSURES: Patients with cleft lip/ palate. COMPARISON: Patients without CL/P. MAIN OUTCOME MEASURES: Electrical activity of masseter and temporalis muscles at rest and during peak activation. RESULTS: After a comprehensive search in MEDLINE, Web of Science, EMBASE, Scopus, and Cochrane's CENTRAL up to December 2022, without language or date restrictions. Eligible trials were selected based on the PECO question and assessed for bias using Cochrane's ROBINS-E tool. Eight clinical trials with 474 participants were included in the review. Then relevant data was extracted from included studies using customized forms. A random-effects meta-analysis was performed to combine the results of the studies, meta-analyses showed that CL/P patients have elevated electrical activity in the masseter (P = .01) and temporalis (P = <.01) muscles at rest compared to non-cleft control patients. During maximum bite force, cleft patients exhibited a statistically significant decrease in electrical activity in both the masseter (P = .03) and temporalis (P = <.01) muscles. CONCLUSIONS: According to our meta-analysis, cleft patients exhibited increased resting muscle activity but decreased activity during maximum bite force, indicating reduced efficiency of masticatory muscles compared to non-cleft patients. These differences can be attributed to anatomical variations, compensatory mechanisms, and previous treatments.

Synovial sarcoma of the maxilla: A challenging diagnostic case report and literature review.

Synovial sarcoma, a malignant mesenchymal tumor, is primarily associated with the extremities. Nevertheless, its appearance within the head and neck region, particularly in the maxillary area, is remarkably rare. This rarity underscores the significance of each case in unraveling the complexities of its behavior and management strategies. The core focus of this research is a detailed case report involving a 6-year-old female patient who presented with a conspicuous swelling in the left posterior maxilla. Subsequent incisional biopsy led to microscopic identification of malignant spindle cell proliferation, marked by dysplastic changes, and abundant mitoses. Immunohistochemical (IHC) analysis demonstrated negative reactivity for neural and muscular markers, while positive expression of Vimentin, Bcl-2, and TLE1. These morphological and IHC findings coalesced to definitively diagnose synovial sarcoma, substantiated by a notable 40% Ki67 proliferative index. The chosen treatment strategy encompassed surgery and radiotherapy, which yielded successful outcomes, with no recurrence observed during the one-year follow-up period. Beyond the specific case, this article undertakes a review of existing literature, meticulously analyzing nine similar cases reported in scholarly sources.

A comparison of CAD/CAM-based fixed retainers versus conventional fixed retainers in orthodontic patients: a systematic review and network meta-analysis.

OBJECTIVE: Comparing computer-aided design and computer-aided manufacturing (CAD/CAM) fixed retainers and conventional fixed retainers for their effectiveness in orthodontic patients using systematic review and meta-analysis of literature. SEARCH METHODS: A comprehensive search was conducted in MEDLINE, Web of Science, EMBASE, Scopus, Cochrane's CENTRAL, Google Scholar, Ovid, and LILACS up to May 2023, with no language or date restrictions. SELECTION CRITERIA: Only randomized clinical trials (RCTs) that complied with PICO questions were included, and the Cochrane Risk of Bias 2.0 (RoB 2) tool was used to assess the risk of bias in the included studies. DATA COLLECTION AND ANALYSIS: Using custom-piloted forms, relevant data were retrieved from the included studies. Then a random-effects inverse variance meta-analysis was used to pool the results. Primary outcomes were stability of treatment results measured through dental cast measurements and periodontal status, while secondary outcomes were failure rates and patient-reported outcomes. RESULTS: Seven RCTs with 601 participants were included in the review. In the short term (≤6 months), the meta-analysis showed no significant differences in inter-canine distance or arch length between CAD/CAM and conventional fixed retainers in mandibular retainers. However, for Little's irregularity index, single-stranded stainless-steel retainers were notably worse than Ni-Ti CAD/CAM retainers at 3 and 6 months, while multi-stranded stainless-steel retainers only diverged from CAD/CAM at the 6-month milestone, despite the overall clinical inconsequence of these changes. CAD/CAM retainers were associated with a lower plaque index than traditional retainers but no significant difference in gingival index. Failure rates did not differ significantly between CAD/CAM and other types of retainers in mandibular retainers. Nonetheless, one study had a high amount of CAD/CAM retainer failures leading to the study being stopped. CONCLUSIONS: In the short term, CAD/CAM fixed retainers show promise as an alternative to traditional retainers. They may enhance periodontal health, as indicated by lower plaque index scores than conventional retainers. However, extensive research is needed to determine the long-term durability and effectiveness of CAD/CAM retainers in orthodontic treatment, particularly regarding their failure rate. Until comprehensive evidence is available, the use of CAD/CAM retainers should be tailored for each case. REGISTRATION: The protocol for this systematic review was registered at PROSPERO with the ID CRD42023412741.

The Effects of Intrusion of Anterior Teeth by Skeletal Anchorage in Deep Bite Patients; A Systematic Review and Meta-Analysis.

BACKGROUND: Deep bite is known as one of the most common malocclusions, and its treatment and retention are often challenging. The use of mini-screws has been suggested as an ideal method for the intrusion of incisors in deep-bite patients. Still, there are conflicting reports regarding the superiority of this method compared to other common treatments. AIM: The aim of this systematic review and meta-analysis was to evaluate the effects of the intrusion of anterior teeth by skeletal anchorage in deep bite patients. METHODS: From the beginning to 15 September 2022, articles on the topic of interest were searched in electronic databases including PubMed, Web of Science, Scopus, EMBASE, and Cochrane's CENTRAL. Additionally, a hand search for pertinent studies and a search of the grey literature were carried out. After the selection of eligible studies, data extraction was performed using piloted forms. Inverse-variance random-effects meta-analyses were used to combine the outcome measures of dental indices, skeletal cephalometric indices, and dental cephalometric indices. RESULTS: A total of 15 studies (6 RCT; 9 CCT) were included in the systematic review and 14 were used in the meta-analyses. The differences in overbite changes (MD = -0.45, p = 0.04), true incisor intrusion [u1-pp] (MD = -0.62, p = 0.003) and molar extrusion [u6-pp] (MD = -0.40, p = 0.01) were statistically significant and TADs showed better treatment results than other intrusion methods (segmented intrusion arch, utility arch, J hook headgear). No significant differences regarding overjet, molar and incisor tipping, and skeletal indices between mini-screw and other intrusion methods could be found. CONCLUSION: The use of mini-screws leads to lower overbite and higher true intrusion (about 0.45 and 0.62 mm, respectively) compared to the use of other methods for intruding upper incisors. Furthermore, the effect of TAD on extrusion of molar teeth is less (by 0.4 mm) than other methods.

Stages of endometriosis: Does it affect oocyte quality, embryo development and fertilization rate?

OBJECTIVE: To investigate the effect of endometriosis and its different stages over Intracytoplasmic Sperm Injection (ICSI) outcomes among infertile women without previous history of ovarian surgery. METHODS: A total of 440 women enrolled in ICSI cycles were recruited and divided into two groups: endometriosis (n=220) and control group (n=220). Endometriosis patients without previous surgical treatment and with diagnostic laparoscopy were further stratified based on disease stage. Clinical and laboratory parameters, ovarian reserve markers, the number and quality of oocytes and embryos and fertilization rate were analyzed and compared among the various severity grades of endometriosis and the control group. RESULTS: Patients with advanced endometriosis had significantly fewer retrieved oocytes with small effect size (p<0.001, η2=0.04), lower metaphase II oocytes (p<0.001, η2=0.09) and fewer total numbers of embryos (p<0.001, η2=0.11) compared with less severe disease or women with tubal factor infertility. The fertilization rate in women with severe endometriosis was similar to that of the control group and in those with minimal/mild endometriosis (p=0.187). CONCLUSIONS: Severe endometriosis negatively affects ovarian response, oocyte quality and embryos. However, fertilization rate is not different among the various stages of endometriosis.

RA-GCN: Graph convolutional network for disease prediction problems with imbalanced data.

Disease prediction is a well-known classification problem in medical applications. Graph Convolutional Networks (GCNs) provide a powerful tool for analyzing the patients' features relative to each other. This can be achieved by modeling the problem as a graph node classification task, where each node is a patient. Due to the nature of such medical datasets, class imbalance is a prevalent issue in the field of disease prediction, where the distribution of classes is skewed. When the class imbalance is present in the data, the existing graph-based classifiers tend to be biased towards the major class(es) and neglect the samples in the minor class(es). On the other hand, the correct diagnosis of the rare positive cases (true-positives) among all the patients is vital in a healthcare system. In conventional methods, such imbalance is tackled by assigning appropriate weights to classes in the loss function which is still dependent on the relative values of weights, sensitive to outliers, and in some cases biased towards the minor class(es). In this paper, we propose a Re-weighted Adversarial Graph Convolutional Network (RA-GCN) to prevent the graph-based classifier from emphasizing the samples of any particular class. This is accomplished by associating a graph-based neural network to each class, which is responsible for weighting the class samples and changing the importance of each sample for the classifier. Therefore, the classifier adjusts itself and determines the boundary between classes with more attention to the important samples. The parameters of the classifier and weighting networks are trained by an adversarial approach. We show experiments on synthetic and three publicly available medical datasets. Our results demonstrate the superiority of RA-GCN compared to recent methods in identifying the patient's status on all three datasets. The detailed analysis of our method is provided as quantitative and qualitative experiments on synthetic datasets.

HOXC10 is significantly overexpressed in colorectal cancer.

Colorectal cancer (CRC) is one of the most common types of cancer in world and has a high rate of mortality. The majority of cases of CRC are sporadic; however, factors such as age, a family history of inflammatory diseases, diet, lifestyle and genetics increase the risk. HOX genes and lncRNAs are two classes of genes, and alterations in the expression levels of these genes are significantly associated with numerous different types of cancer. In the present study, the expression levels of HOXC10, HOXC-AS3, HOTAIR, HOXC13 and HOXC13-AS in tumor tissues were compared with normal healthy tissues in patients with CRC. Paired tumor and normal tissues were collected from 39 patients with CRC, and reverse transcription-quantitative PCR was used the expression of HOXC-AS3, HOXC13 and HOXC10 in the tumor tissues compared with the respective normal tissues. Expression of these genes were increased in the tumor tissues compared with normal tissues; however, the difference was only significant for HOXC10. Additionally, there was a strong and significant correlation between the expression of HOTAIR and HOXC13, a moderate and significant correlation between the expression of HOTAIR and HOXC13-AS, and between HOXC13 and HOXC13-AS genes. The expression of HOXC10 was significantly higher in tumor tissues compared with the normal tissues; whereas the upregulation of HOXC-AS3 and HOXC13 were not significant. Only the correlation between the expression of HOTAIR and HOXC13 was strong and significant. As HOXC10 expression was significantly upregulated in the tumor tissues relative to normal tissues, it may serve as a biomarker for the diagnosis of CRC and as a potential therapeutic target.

The role of FDG PET/CT in the evaluation of treatment response in a case of calcified ovarian metastases.

Evaluation of calcified metastatic lesions by conventional imaging can be challenging. Ovarian cancer metastases can present with calcification which might increase in size and number following therapy. It is not entirely clear whether these calcifications are associated with tumor response or disease progression. Calcified lesions which do not change in size or configuration are particularly problematic when assessed by RECIST criteria. Positron emission tomography (PET)/computed tomography (CT) is of particular value as it demonstrates the metabolic activity of the calcified lesions, in addition, it might reveal metastases in unexpected sites. We report a case of serous papillary ovarian cancer with extensive abdomino-pelvic calcified metastases referred for evaluation of therapy response. Despite being reported as stable disease on CT evaluation, we observed increased metabolic activity in the calcified lesions both on CT-attenuation corrected and non-attenuation corrected images, which was indicative of inadequate response to therapy. PET/CT is an ideal modality in follow-up of patients with ovarian cancer presenting with calcified metastatic tumoral deposits.

Stock price prediction using principal components.

The literature provides strong evidence that stock price values can be predicted from past price data. Principal component analysis (PCA) identifies a small number of principle components that explain most of the variation in a data set. This method is often used for dimensionality reduction and analysis of the data. In this paper, we develop a general method for stock price prediction using time-varying covariance information. To address the time-varying nature of financial time series, we assign exponential weights to the price data so that recent data points are weighted more heavily. Our proposed method involves a dimension-reduction operation constructed based on principle components. Projecting the noisy observation onto a principle subspace results in a well-conditioned problem. We illustrate our results based on historical daily price data for 150 companies from different market-capitalization categories. We compare the performance of our method to two other methods: Gauss-Bayes, which is numerically demanding, and moving average, a simple method often used by technical traders and researchers. We investigate the results based on mean squared error and directional change statistic of prediction, as measures of performance, and volatility of prediction as a measure of risk.