Diagnosing oral and maxillofacial diseases using deep learning.

The classification and localization of odontogenic lesions from panoramic radiographs is a challenging task due to the positional biases and class imbalances of the lesions. To address these challenges, a novel neural network, DOLNet, is proposed that uses mutually influencing hierarchical attention across different image scales to jointly learn the global representation of the entire jaw and the local discrepancy between normal tissue and lesions. The proposed approach uses local attention to learn representations within a patch. From the patch-level representations, we generate inter-patch, i.e., global, attention maps to represent the positional prior of lesions in the whole image. Global attention enables the reciprocal calibration of path-level representations by considering non-local information from other patches, thereby improving the generation of whole-image-level representation. To address class imbalances, we propose an effective data augmentation technique that involves merging lesion crops with normal images, thereby synthesizing new abnormal cases for effective model training. Our approach outperforms recent studies, enhancing the classification performance by up to 42.4% and 44.2% in recall and F1 scores, respectively, and ensuring robust lesion localization with respect to lesion size variations and positional biases. Our approach further outperforms human expert clinicians in classification by 10.7 % and 10.8 % in recall and F1 score, respectively.

Impaction of multiple dilacerated primary incisors: a case report.

Dental complications such as defective alveolar bone development, delayed eruption, and tooth impaction are related to neonatal oral intubation. This case report presents an example of potential complications that occur in children who have undergone oral intubation as neonates. A 20-month-old girl visited our pediatric clinic. We observed delayed, non-erupted teeth #51, #71, and #81 and determined a history of intubation during the neonatal period as a related factor. After 22 months of observation, tooth #71 erupted spontaneously. After 40 months of monitoring, teeth #51 and #81 were extracted surgically, and normal permanent teeth erupted six months later. This study is helpful for pediatric anesthesiologists, pediatricians, and dentists who diagnose and treat eruption disorders of the primary dentition.

Prediction Model for Future Success of Early Orthopedic Treatment of Class III Malocclusion.

This study aimed to identify predictors for successful post-treatment outcomes in early orthopedic class III malocclusion treatment with a facemask and hyrax expander appliance. The study was performed on lateral cephalograms from 37 patients at the start of treatment (T0), post-treatment (T1), and a minimum of three years after treatment (T2). The patients were grouped as stable or unstable according to the existence of a 2-mm overjet at T2. For statistical analysis, independent t-tests were used to compare the baseline characteristics and measurements of the two groups, considering a significance level of < 0.05. Thirty variables of pretreatment cephalograms were considered during logistic regression analysis to identify predictors. A discriminant equation was established using a stepwise method. The success rate and area under the curve were calculated, with AB to the mandibular plane, ANB, ODI, APDI, and A-B plane angles as predictors. The A-B plane angle was the most significantly different between the stable and unstable groups. In terms of the A-B plane angle, the success rate of early class III treatment with a facemask and hyrax expander appliance was 70.3%, and the area under the curve indicated a fair grade.

HOXA­AS3 induces tumor progression through the epithelial­mesenchymal transition pathway in epithelial ovarian cancer.

HOXA cluster antisense RNA 3 (HOXA­AS3) is considered to be involved in several malignancies, however, its biological function in the progression of epithelial ovarian cancer (EOC) remains unclear. The present study compared the expression of HOXA­AS3 in ovarian cancer and normal ovarian tissues and analyzed the association between the expression of HOXA­AS3 and the survival outcomes of patients with ovarian cancer. RNA interference was used to suppress HOXA­AS3 expression in ovarian cancer cell lines in order to demonstrate the function of HOXA­AS3 in ovarian cancer progression. The associations between HOXA­AS3 and epithelial­mesenchymal transition (EMT) markers were explored to verify the mechanism of action of HOXA­AS3 in ovarian cancer. The results of the present study revealed that ovarian cancer tissues exhibited higher HOXA­AS3 expression than normal ovarian tissues. Clinical data indicated that HOXA­AS3 was a significant predictor of progression­free survival and overall survival. Patients with high HOXA­AS3 expression had a poorer prognosis than patients with low HOXA­AS3 expression. In vitro experiments using HOXA­AS3­knockdown ovarian cancer cell lines demonstrated that HOXA­AS3 knockdown inhibited cell proliferation and migration. HOXA­AS3 was a potent inducer and modulator of the expression of EMT pathway­related markers and interacted with both the mRNA and protein forms of HOXA3. Collectively, the findings of the present study demonstrated that HOXA­AS3 expression is associated with ovarian cancer progression and thus, may be employed as a prognostic marker and therapeutic target in EOC.

Deep learning for osteoarthritis classification in temporomandibular joint.

OBJECTIVES: This study aimed to develop a diagnostic support tool using pretrained models for classifying panoramic images of the temporomandibular joint (TMJ) into normal and osteoarthritis (OA) cases. SUBJECTS AND METHODS: A total of 858 panoramic images of the TMJ (395 normal and 463 TMJ-OA) were obtained from 518 individuals from January 2015 to December 2018. The data were randomly divided into training, validation, and testing sets (6:2:2). We used pretrained Resnet152 and EfficientNet-B7 as transfer learning models. The accuracy, specificity, sensitivity, area under the curve, and gradient-weighted class activation mapping (grad-CAM) of both trained models were evaluated. The performances of the trained models were compared to that of dentists (both TMD specialists and general dentists). RESULTS: The classification accuracies of ResNet-152 and EfficientNet-B7 were 0.87 and 0.88, respectively. The trained models exhibited the highest accuracy in OA classification. In the grad-CAM analysis, the trained models focused on specific areas in osteoarthritis images where erosion or osteophyte were observed. CONCLUSIONS: The artificial intelligence model improved the diagnostic power of TMJ-OA when trained with two-dimensional panoramic condyle images and can be effectively applied by dentists as a screening diagnostic tool for TMJ-OA.

Prognostic Significance of Clinical Factors Including BRCA Mutation in Epithelial Ovarian, Peritoneal, Fallopian Tube Cancer.

BACKGROUND/AIM: We analyzed the survival outcomes of patients with epithelial ovarian, peritoneal, or fallopian tube cancer with BRCA1/2 mutations and the clinical factors associated with the prognosis of these cancers. PATIENTS AND METHODS: We included patients who had been diagnosed with and treated for epithelial ovarian, peritoneal, or fallopian tube cancer and had undergone germline BRCA testing in six hospitals between January 2012 and December 2019. RESULTS: Of the 378 identified patients, 76 (20.1%) carried a BRCA1/2 mutation. Progression-free survival (PFS) and overall survival (OS) did not differ between patients with and without BRCA1/2 mutation. Multivariate analysis for 18 months after the primary treatment showed higher PFS in the BRCA1/2 mutation group (p=0.024). Subgroup analysis in patients with high-grade serous carcinoma showed that BRCA1/2 mutation was an independent favorable prognostic factor for PFS (p=0.035). Subgroup analysis of patients with stage III or IV disease demonstrated an independent gain in PFS in patients with BRCA1/2 mutation (p=0.015). Neoadjuvant chemotherapy as a primary treatment was related to poor PFS (p<0.001) and reduced OS (p=0.005). CONCLUSION: Having a germline BRCA1/2 mutation improved short-term PFS in patients with epithelial ovarian, peritoneal, or fallopian tube cancer. Elevated initial CA125 level and primary neoadjuvant chemotherapy were related to poor prognosis.

Informed consent forms for gynecologic cancer surgery: recommendations from the Korean Society of Gynecologic Oncology.

The sociomedical environment is changing. In the traditional physician-patient relationship, the physician was authoritative and the patient was obedient. The contractual relationship featured patient consent to the physician's decision. Today, the physician must explain fully the planned medical treatment, and any alternative, to the patient, who has the right to choose her treatment after considering the benefits and side-effects. The Korean Society of Gynecologic Oncology thus decided to standardize the surgical consent forms to meet the legal requirements of modern medicine, improve patient understanding of the surgical details, and protect medical staff from legal disputes. To determine the format and content, subcommittees for each cancer type collected and reviewed all relevant articles and the current consent forms of domestic medical institutions. After several meetings, 16 basic items to be included for each type of gynecologic cancer were selected. Also, to help patients understand the surgical details, figures were included. The revised forms were legally reviewed in terms of the appropriateness of the format and content. We also developed English versions to provide adequate information for foreign patients. We hope that these efforts will promote trust between patients and physicians, and contribute to effective treatment by laying a foundation of mutual respect.

Informed consent forms for gynecologic cancer surgery: recommendations from the Korean Society of Gynecologic Oncology.

The sociomedical environment is changing. In the traditional physician-patient relationship, the physician was authoritative and the patient was obedient. The contractual relationship featured patient consent to the physician's decision. Today, the physician must explain fully the planned medical treatment, and any alternative, to the patient, who has the right to choose her treatment after considering the benefits and side-effects. The Korean Society of Gynecologic Oncology (KSGO) thus decided to standardize the surgical consent forms to meet the legal requirements of modern medicine, improve patient understanding of the surgical details, and protect medical staff from legal disputes. To determine the format and content, subcommittees for each cancer type collected and reviewed all relevant articles and the current consent forms of domestic medical institutions. After several meetings, 16 basic items to be included for each type of gynecologic cancer were selected. Also, to help patients understand the surgical details, figures were included. The revised forms were legally reviewed in terms of the appropriateness of the format and content. We also developed English versions to provide adequate information for foreign patients. We hope that these efforts will promote trust between patients and physicians, and contribute to effective treatment by laying a foundation of mutual respect.

Effectiveness of Human-Artificial Intelligence Collaboration in Cephalometric Landmark Detection.

Detection of cephalometric landmarks has contributed to the analysis of malocclusion during orthodontic diagnosis. Many recent studies involving deep learning have focused on head-to-head comparisons of accuracy in landmark identification between artificial intelligence (AI) and humans. However, a human-AI collaboration for the identification of cephalometric landmarks has not been evaluated. We selected 1193 cephalograms and used them to train the deep anatomical context feature learning (DACFL) model. The number of target landmarks was 41. To evaluate the effect of human-AI collaboration on landmark detection, 10 images were extracted randomly from 100 test images. The experiment included 20 dental students as beginners in landmark localization. The outcomes were determined by measuring the mean radial error (MRE), successful detection rate (SDR), and successful classification rate (SCR). On the dataset, the DACFL model exhibited an average MRE of 1.87 ± 2.04 mm and an average SDR of 73.17% within a 2 mm threshold. Compared with the beginner group, beginner-AI collaboration improved the SDR by 5.33% within a 2 mm threshold and also improved the SCR by 8.38%. Thus, the beginner-AI collaboration was effective in the detection of cephalometric landmarks. Further studies should be performed to demonstrate the benefits of an orthodontist-AI collaboration.

Long Non-coding RNA LOC285194 Promotes Epithelial Ovarian Cancer Progression via the Apoptosis Signaling Pathway.

BACKGROUND/AIM: To explore the molecular mechanism and clinical significance of a newly identified lncRNA LOC285194 in epithelial ovarian cancer (EOC). MATERIALS AND METHODS: LOC285194 transcript levels were analyzed in EOC cells compared to normal cells. Small interfering RNAs were used to suppress LOC285194 expression. Levels of apoptosis-related proteins were determined by western blot. LOC285194 expression in ovarian cancer and non-tumor tissues were compared with clinicopathologic and survival data. RESULTS: Knockdown of LOC285194 decreased cell migration and proliferation, enhanced reactive oxygen species production and resulted in increased levels of proteins of the extrinsic apoptotic signaling pathway. LOC285194 expression level was higher in ovarian cancer tissues compared to control. Overall survival was significantly shorter in patients with high LOC285194 expression. Lymph node metastasis and high LOC285194 expression were significant prognostic factors of mortality (HR=4.614 and 5.880; p=0.026 and p=0.002, respectively). CONCLUSION: LOC285194 can promote the progression of EOC via an anti-apoptotic mechanism. It may serve as a novel biomarker for predicting prognosis of EOC.

Clinical diagnosis and treatment of temporomandibular disorders in children and adolescents: a case series.

The early diagnosis of temporomandibular disorders (TMDs) in children and adolescents is important because they can affect oral and maxillofacial growth and development. This case series introduces patients with various clinical features of TMDs and demonstrates how symptoms were reduced through appropriate interventions in collaboration with oral medicine specialists and pediatric dentists. TMDs symptoms in children are often mild and difficult to express accurately; therefore, diagnosis through clinical evaluation is important. Pediatric dentists should be aware of TMDs in children and adolescents, and should diagnose, treat, and refer to specialists in a timely manner.

Estimating Cervical Vertebral Maturation with a Lateral Cephalogram Using the Convolutional Neural Network.

Recently, the estimation of bone maturation using deep learning has been actively conducted. However, many studies have considered hand-wrist radiographs, while a few studies have focused on estimating cervical vertebral maturation (CVM) using lateral cephalograms. This study proposes the use of deep learning models for estimating CVM from lateral cephalograms. As the second, third, and fourth cervical vertebral regions (denoted as C2, C3, and C4, respectively) are considerably smaller than the whole image, we propose a stepwise segmentation-based model that focuses on the C2-C4 regions. We propose three convolutional neural network-based classification models: a one-step model with only CVM classification, a two-step model with region of interest (ROI) detection and CVM classification, and a three-step model with ROI detection, cervical segmentation, and CVM classification. Our dataset contains 600 lateral cephalogram images, comprising six classes with 100 images each. The three-step segmentation-based model produced the best accuracy (62.5%) compared to the models that were not segmentation-based.

Dental Management of Congenital Granular Cell Lesion and Neonatal Teeth: A Case Report.

Congenital granular cell lesion (CGCL) is a rare benign oral cavity tumor in infants. Neonatal teeth are also rare dental anomalies that appear during the first month of life. This report describes a case of eruption of neonatal teeth after surgical excision of CGCL. Surprisingly, residual neonatal teeth erupted after extraction of the neonatal teeth. If neonatal teeth are mobile, they should be carefully extracted with curettage of the underlying tissues of the dental papilla; failure to curette the socket might result in eruption of odontogenic remnants. If neonatal teeth were exfoliated, parents should be informed of the need for regular checkups with a dentist due to possibility of development of residual neonatal teeth.

Knockdown of E2F4 suppresses the growth of ovarian cancer cells through the cell cycle pathway.

Ovarian cancer remains one of the major causes of death from gynecologic cancer in developed countries. The E2F family has been shown to have a central role in the control of cell proliferation, differentiation, and cell cycle progression in various types of cancer. Despite advances in cancer research, the carcinogenic role of E2F transcription factor 4 (E2F4) in ovarian cancer remains unclear. In this study, we investigated the underlying molecular mechanism of E2F4 in human ovarian cancer cells (OCC). E2F4 expression was demonstrated by quantitative real time polymerase chain reaction (qRT-PCR) in OCC. The alterations of expression values were determined using 2(-ΔΔCt) method. The effects of suppressing E2F4 on cell proliferation, migration, and differentiation were evaluated by cell proliferation assay, colony formation assay and wound healing assay in vitro. Overexpression of E2F4 was found at both mRNA and protein levels in OCC. Small interfering RNA was used to suppress E2F4 expression. Depletion of E2F4 inhibited cell proliferation and suppressed the cell migration and colony formation ability compared to controls. The expression of cell cycle machinery including cyclin A, cyclin D and cyclin dependent kinase 2 (CDK2) was increased after E2F4 knockdown. E2F4 modulates ovarian cancer cell proliferation and migration through cell cycle components including cyclin A, cyclin D, and CDK2. Our findings indicate that E2F4 may serve as a valuable candidate and therapeutic target for ovarian cancer treatment in regard to cell cycle control.

EARLY STARVATION 1 Is a Functionally Conserved Protein Promoting Gravitropic Responses in Plants by Forming Starch Granules.

Starch granules in the endodermis of plant hypocotyls act as statoliths that promote hypocotyl negative gravitropism-the directional growth of hypocotyls against gravity-in the dark. To identify the molecular components that regulate hypocotyl negative gravitropism, we performed a mutagenesis screen and isolated reduced gravitropic 1 (rgv1) mutants that lack starch granules in their hypocotyl endodermis and show reduced hypocotyl negative gravitropism in the dark. Using whole genome sequencing, we identified three different rgv1 mutants that are allelic to the previously reported early starvation 1 mutant, which is rapidly depleted of starch just before the dawn. ESV1 orthologs are present in starch-producing green organisms, suggesting ESV1 is a functionally conserved protein necessary for the formation of starch granules. Consistent with this, we found that liverwort and rice ESV1 can complement the Arabidopsis ESV1 mutant phenotype for both starch granules and hypocotyl negative gravitropism. To further investigate the function of ESV1 in other plants, we isolated rice ESV1 mutants and found that they show reduced levels of starch in their leaves and loosely packed starch granules in their grains. Both Arabidopsis and rice ESV1 mutants also lack starch granules in root columella and show reduced root gravitropism. Together, these results indicate ESV1 is a functionally conserved protein that promotes gravitropic responses in plants via its role in starch granule formation.

Secondhand smoke exposure, diabetes, and high BMI are risk factors for uterine cervical cancer: a cross-sectional study from the Korea national health and nutrition examination survey (2010-2018).

BACKGROUND: Human papilloma virus infection and tobacco smoking are the major risk factors for cervical cancer. There are limited studies searching other risk factors for cervical cancer and the results are not consistent. This study investigated the relations between cervical cancer and possible risk factors, including secondhand cigarette smoke exposure, diabetes, body mass index (BMI), and work schedule. METHODS: In this cross-sectional study, 29,557 women completed a cervical cancer questionnaire and were selected using 2010-2018 data from the Korea National Health and Nutrition Examination Survey. Details in secondhand smoke exposure, diabetes, BMI, and work schedule were assessed with participants' health interviews and health-related surveys. RESULTS: Two hundred sixty-two women (0.89%) in the sample were diagnosed with cervical cancer. Domestic secondhand smoke exposure, diabetes, and high BMI significantly increased cervical cancer risk. Respective odds ratios and 95% confidence intervals were: 1.547 (1.042-2.297), 2.156 (1.535-3.027), and 1.036 (1.006-1.067). Weekly work hours, and work schedule were not significantly related to cervical cancer incidence. CONCLUSION: Among Korean women, passive exposure to cigarette smoke at home, diabetes, and high BMI increase risk for cervical cancer.

Risk Factors for Early Childhood Caries: An Umbrella Review.

Purpose: The purpose of this umbrella review was to summarize and evaluate the available evidence concerning risk factors for early childhood caries (ECC). Methods: Literature searches were performed until July 2020 in Medline, Web of Science, and EMBASE databases. Systematic reviews were selected, and their methodological qualities were assessed using the AMSTAR 2 tool (16 items). Results: A total of 977 articles for possible inclusion were identified, and 15 studies were finally selected for qualitative analysis. In these 15 studies, the risk of bias varied from critically low to high. The included studies reported risk factors for ECC such as dietary factors, mutans streptococci, low maternal education, maternal age, low family income and parental education level, low social class, enamel defects, obesity, the presence of dentinal caries, presence of Candida albicans, moderate to late preterm birth, and prenatal maternal cigarette smoking. Conclusions: The potential risk factors for early childhood caries are enamel defects, high levels of mutans streptococci, the presence of dentinal caries, increased consumption of soda, daily intake of sugary snacks, and obesity. In the future, longitudinal studies are needed to explore the potential relationship between these risk factors and ECC.

Dentist Job Satisfaction: A Systematic Review and Meta-analysis.

OBJECTIVES: Because of the heterogeneous nature of the evidence regarding dentists' job satisfaction, an overview was necessary to examine dentists' level of job satisfaction and to determine related work environmental factors. MATERIALS AND METHODS: A literature search was conducted using preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. Electronic database searches of PubMed/MEDLINE, EMBASE, and Web of Science were performed until March 1, 2020. Two independent authors collected data and assessed the methodological quality of primary studies using the Newcastle Ottawa Scale. RESULTS: Nine studies were included from the 1987 initially retrieved. Among the included studies, 5 exhibited a neutral level of satisfaction and originated from China, South Korea, Egypt, and the United States, and 3 studies from Canada, Lithuania, and the United States showed a high level of satisfaction. Only 1 study did not report the mean job satisfaction score. According to bias evaluation, 9 studies were considered low risk. CONCLUSION: The findings showed that dentists were satisfied with their jobs at a moderate to high level, and specialists were more satisfied than general dentists. Regarding work environmental factors, the 6 most satisfied factors were patient relationships, respect, delivery of care, staff, professional relationship, and professional environment. Five of the least satisfied factors were personal time, stress, income, practice management, and professional time. However, longitudinal studies would be required to identify changes in these factors. Further studies should be performed in middle- and low-income countries using the Dentist Satisfaction Survey, including stress evaluation.

Low serum T3 levels are associated with false-positive results when using the risk of ovarian malignancy algorithm (ROMA) in women with benign ovarian disease.

OBJECTIVE: We investigated factors that could cause false-positive results when using the risk of ovarian malignancy algorithm (ROMA) for assessing ovarian cancer risk. MATERIALS AND METHODS: ROMA scores were calculated from patients followed surgery to remove a pelvic mass. We compared a false-positive group with a true-negative group of ROMA scores. RESULTS: We analyzed 324 patients using medical records. There were 22 with an epithelial ovarian cancer (EOC), 15 with a borderline ovarian tumor, and 287 with benign disease. Twenty-nine (10.1%) of the patients with benign disease showed high-risk ROMA score (false positive) and 13/37 (35%) patients with EOC, or borderline ovarian tumor showed low ROMA scores (false negatives). The median serum triiodothyronine (T3) level of the false-positive ROMA group in patients with benign disease was lower than in the true-negative ROMA group (p < 0.001) and the estimated glomerular filtration rate (eGFR) was also lower (p = 0.001) in the false-positive ROMA group. Median serum T3 levels in the true-positive ROMA group among patients with EOC, or borderline ovarian tumor were lower than in the false-negative ROMA group (p = 0.043). CONCLUSION: Median serum T3 level and eGFR in the false-positive ROMA group in patients with benign ovarian disease were lower than in the true-negative group.

Influence of mouth breathing on atopic dermatitis risk and oral health in children: A population-based cross-sectional study.

BACKGROUND/PURPOSE: Previous studies have suggested that mouth breathing has harmful effects on atopic dermatitis (AD) and oral health in children, but the evidence has been insufficient. To investigate the association of mouth breathing with AD and oral health in Korean schoolchildren aged 8-11 years. MATERIALS AND METHODS: Cross-sectional data were obtained from March to April 2016. A questionnaire was used to investigate children's mouth breathing habits and personal/family histories related to allergic disease. Oral health status was determined through a clinical oral examination. Data were analyzed with multivariable logistic regression. RESULTS: In total, 1507 children were included. A moderate relationship was observed between mouth breathing and AD (adjusted odds ratio, 1.05; 95% confidence interval, 1.00-1.10; p-value, 0.035), whereas no association was found between mouth breathing and dental caries in children. Mouth breathing during sleep (MBS) was closely related to allergic diseases and other respiratory diseases. Furthermore, mouth breathing was associated with child's tonsillitis and was identified as a possible risk factor for class II dental malocclusion. CONCLUSION: We confirmed the positive association between mouth breathing (especially during sleep) and allergic diseases, including the AD in school-aged children. The influence of mouth breathing on dental caries remains uncertain. An intervention trial is required to evaluate whether the prevention of mouth breathing can reduce the risk of allergic diseases.