Differential Diagnosis of OKC and SBC on Panoramic Radiographs: Leveraging Deep Learning Algorithms.

This study aims to determine whether it can distinguish odontogenic keratocyst (OKC) and simple bone cyst (SBC) based solely on preoperative panoramic radiographs through a deep learning algorithm. (1) Methods: We conducted a retrospective analysis of patient data from January 2018 to December 2022 at Pusan National University Dental Hospital. This study included 63 cases of OKC confirmed by histological examination after surgical excision and 125 cases of SBC that underwent surgical curettage. All panoramic radiographs were obtained utilizing the Proline XC system (Planmeca Co., Helsinki, Finland), which already had diagnostic data on them. The panoramic images were cut into 299 × 299 cropped sizes and divided into 80% training and 20% validation data sets for 5-fold cross-validation. Inception-ResNet-V2 system was adopted to train for OKC and SBC discrimination. (2) Results: The classification network for diagnostic performance evaluation achieved 0.829 accuracy, 0.800 precision, 0.615 recall, and a 0.695 F1 score. (4) Conclusions: The deep learning algorithm demonstrated notable accuracy in distinguishing OKC from SBC, facilitated by CAM visualization. This progress is expected to become an essential resource for clinicians, improving diagnostic and treatment outcomes.

Deep learning and clustering approaches for dental implant size classification based on periapical radiographs.

This study investigated two artificial intelligence (AI) methods for automatically classifying dental implant diameter and length based on periapical radiographs. The first method, deep learning (DL), involved utilizing the pre-trained VGG16 model and adjusting the fine-tuning degree to analyze image data obtained from periapical radiographs. The second method, clustering analysis, was accomplished by analyzing the implant-specific feature vector derived from three key points coordinates of the dental implant using the k-means++ algorithm and adjusting the weight of the feature vector. DL and clustering model classified dental implant size into nine groups. The performance metrics of AI models were accuracy, sensitivity, specificity, F1-score, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC-ROC). The final DL model yielded performances above 0.994, 0.950, 0.994, 0.974, 0.952, 0.994, and 0.975, respectively, and the final clustering model yielded performances above 0.983, 0.900, 0.988, 0.923, 0.909, 0.988, and 0.947, respectively. When comparing the AI model before tuning and the final AI model, statistically significant performance improvements were observed in six out of nine groups for DL models and four out of nine groups for clustering models based on AUC-ROC. Two AI models showed reliable classification performances. For clinical applications, AI models require validation on various multicenter data.

Deep focus approach for accurate bone age estimation from lateral cephalogram.

Background/purpose: Bone age is a useful indicator of children's growth and development. Recently, the rapid development of deep-learning technique has shown promising results in estimating bone age. This study aimed to devise a deep-learning approach for accurate bone-age estimation by focusing on the cervical vertebrae on lateral cephalograms of growing children using image segmentation. Materials and methods: We included 900 participants, aged 4-18 years, who underwent lateral cephalogram and hand-wrist radiograph on the same day. First, cervical vertebrae segmentation was performed from the lateral cephalogram using DeepLabv3+ architecture. Second, after extracting the region of interest from the segmented image for preprocessing, bone age was estimated through transfer learning using a regression model based on Inception-ResNet-v2 architecture. The dataset was divided into train:test sets in a ratio of 4:1; five-fold cross-validation was performed at each step. Results: The segmentation model possessed average accuracy, intersection over union, and mean boundary F1 scores of 0.956, 0.913, and 0.895, respectively, for the segmentation of cervical vertebrae from lateral cephalogram. The regression model for estimating bone age from segmented cervical vertebrae images yielded average mean absolute error and root mean squared error values of 0.300 and 0.390 years, respectively. The coefficient of determination of the proposed method for the actual and estimated bone age was 0.983. Our method visualized important regions on cervical vertebral images to make a prediction using the gradient-weighted regression activation map technique. Conclusion: Results showed that our proposed method can estimate bone age by lateral cephalogram with sufficiently high accuracy.

Aggressive central odontogenic fibroma in the maxilla: A case report.

A central odontogenic fibroma is a rare benign tumor composed of mature fibrous connective tissue with variable amounts of odontogenic epithelium. It appears at similar rates in the maxilla and mandible. In the maxilla, it usually occurs anterior to the molars. Radiographically, central odontogenic fibroma commonly presents as a multilocular or unilocular radiolucency with a distinct border. This paper reports a case of an aggressive central odontogenic fibroma involving the right posterior maxilla of a 53-year-old man. Radiographs showed an extensive soft tissue mass involving the entire right maxilla with frank bone resorption. The patient had a history of 2 operations in the region, both more than 2 decades ago. Although it was impossible to confirm the previous diagnoses, it was presumed that this case was a recurrent lesion.

Analysis of the root position and angulation of maxillary premolars in alveolar bone using cone-beam computed tomography.

Purpose: This study investigated whether the relationship between the maxillary sinus and the root of the maxillary premolar is correlated with the root position and whether there is a difference in the long axis angle of premolars and the buccal bone thickness according to the sinus-root relationship and root position. Materials and Methods: Cone-beam computed tomographic images of 587 maxillary first premolars and 580 second premolars from 303 patients were retrospectively reviewed. The maxillary sinus floor-root relationship was classified into 4 types, and the root position in the alveolar bone was evaluated as buccal, middle, or palatal. The long axis angle of the maxillary premolars in the alveolar bone and the buccal bone thickness were measured. The correlation between these parameters was analyzed. Results: The maxillary sinus floor-root relationship showed a statistically significant correlation with the root position in the alveolar bone. Most maxillary first premolars were buccally located, and more than half of the second premolars had their roots in the middle. The long axis angle of the premolars was significantly larger in buccal-positioned teeth than in middle-positioned teeth, and the buccal bone was thinner. Conclusion: When the root of the maxillary premolar was separated from the sinus floor, the premolar was often located on the buccal side. Most of the maxillary first premolars had a thinner buccal bone and larger inclination than the second premolars. It is recommended to evaluate the root position, sagittal angle and buccal bone thickness using CBCT for implant treatment planning.

Comparison of Deep Learning Models for Cervical Vertebral Maturation Stage Classification on Lateral Cephalometric Radiographs.

The purpose of this study is to evaluate and compare the performance of six state-of-the-art convolutional neural network (CNN)-based deep learning models for cervical vertebral maturation (CVM) on lateral cephalometric radiographs, and implement visualization of CVM classification for each model using gradient-weighted class activation map (Grad-CAM) technology. A total of 600 lateral cephalometric radiographs obtained from patients aged 6-19 years between 2013 and 2020 in Pusan National University Dental Hospital were used in this study. ResNet-18, MobileNet-v2, ResNet-50, ResNet-101, Inception-v3, and Inception-ResNet-v2 were tested to determine the optimal pre-trained network architecture. Multi-class classification metrics, accuracy, recall, precision, F1-score, and area under the curve (AUC) values from the receiver operating characteristic (ROC) curve were used to evaluate the performance of the models. All deep learning models demonstrated more than 90% accuracy, with Inception-ResNet-v2 performing the best, relatively. In addition, visualizing each deep learning model using Grad-CAM led to a primary focus on the cervical vertebrae and surrounding structures. The use of these deep learning models in clinical practice will facilitate dental practitioners in making accurate diagnoses and treatment plans.

Clinical significance of C-Reactive Protein to Lymphocyte Count Ratio as a prognostic factor for Survival in Non-small Cell Lung Cancer Patients undergoing Curative Surgical Resection.

Purpose: We assessed the clinical feasibility of C-reactive protein to lymphocyte ratio (CLR) as a determinant of survival in patients with non-small cell lung cancer (NSCLC) undergoing curative surgical resection. Methods: A retrospective study was conducted on patients with stage I and II NSCLC undergoing curative resection. Demographic and clinical variables, including CLR, were collected and analyzed. The Cox proportional hazards model was used to calculate hazard ratios for overall survival (OS) and cancer-specific survival (CSS). The Mann-Whitney U test was used to compare differences between two independent groups. Results: The median age of the patients was 69.0 years, and male patients comprised 63.9% of all patients. A total of 164 (75.9%) patients were categorized as having stage I disease and 52 (24.1%) as having stage II disease. Using the multivariate Cox model, age (hazard ratio [HR] 1.08, p<0.001), lymphatic invasion (HR 3.12, p=0.004), stage (HR 5.10, p<0.001), and CLR (HR 1.01, p=0.003) were significant determinants of OS. In addition, age (HR 1.11, p=0.002), lymphatic invasion (HR 3.16, p=0.010), stage (HR 6.89, p<0.001), and CLR (HR 1.05, p=0.002) were significant determinants of CSS. Conclusions: Our findings show that CLR could be a determinant of survival in NSCLC patients undergoing curative surgical resection.

Attenuation effect of polydeoxyribonucleotide on inflammatory cytokines and apoptotic factors induced by particulate matter (PM10) damage in human bronchial cells.

Particulate matter (PM) of 10-µm-sized fine dust in the air penetrates the respiratory tract and contributes to the increasing incidence of various lung diseases, but its definite mechanism is not known. Recently, polydeoxyribonucleotide (PDRN) has been shown to have anti-inflammatory and regenerative effects in various tissues. However, the bronchial-related mechanism is not well-understood. Hence, this experiment is intended to demonstrate the beneficial effect of PDRN administration on PM10-induced injury in human bronchial-derived NCI-H358 cells. To confirm the protective effect of PDRN, PM10 was applied after PDRN pretreatment to confirm changes in NCI-H358 cells. Experiments were conducted to measure cell survival, cytotoxicity, inflammation, and apoptotic factor changes. WST-8 assay was used to confirm cell viability, and lactate dehydrogenase assay was used to obtain cytotoxicity. In addition, changes in inflammatory cytokines and apoptotic factors were confirmed by enzyme-linked immunosorbent assay and Western blot. Decreased cell viability and increased cytotoxicity, inflammatory cytokines, and apoptotic factors were observed after exposure to PM10. However, pretreatment with PDRN enhanced cell viability and reduced cytotoxicity. In addition, the expression of inflammatory cytokines such as tumor necrosis factor-α, interleukin-6 (IL-6), and IL-1ß, and cell death factors such as Apaf-1, cyt c, caspase-3, caspase-9, Bid, and Bax/Bcl-2 ratio were decreased by PDRN administration in PM10-exposed NCI-H358 cells. PDRN, an A2AR agonist, affects cAMP activation and regulation of phosphorylation of PKA and CREB. In addition, treatment with A2AR antagonist 3,7-dimethyl-1-propargylxanthine significantly blocked PDRN's effect. These anti-cytotoxicity, anti-inflammation, and anti-apoptosis effects of PDRN can be attributed to the adenosine A2AR enhancing effect on PM10-exposed bronchial cells.

Artificial intelligence in oral and maxillofacial radiology: what is currently possible?

Artificial intelligence, which has been actively applied in a broad range of industries in recent years, is an active area of interest for many researchers. Dentistry is no exception to this trend, and the applications of artificial intelligence are particularly promising in the field of oral and maxillofacial (OMF) radiology. Recent researches on artificial intelligence in OMF radiology have mainly used convolutional neural networks, which can perform image classification, detection, segmentation, registration, generation, and refinement. Artificial intelligence systems in this field have been developed for the purposes of radiographic diagnosis, image analysis, forensic dentistry, and image quality improvement. Tremendous amounts of data are needed to achieve good results, and involvement of OMF radiologist is essential for making accurate and consistent data sets, which is a time-consuming task. In order to widely use artificial intelligence in actual clinical practice in the future, there are lots of problems to be solved, such as building up a huge amount of fine-labeled open data set, understanding of the judgment criteria of artificial intelligence, and DICOM hacking threats using artificial intelligence. If solutions to these problems are presented with the development of artificial intelligence, artificial intelligence will develop further in the future and is expected to play an important role in the development of automatic diagnosis systems, the establishment of treatment plans, and the fabrication of treatment tools. OMF radiologists, as professionals who thoroughly understand the characteristics of radiographic images, will play a very important role in the development of artificial intelligence applications in this field.

Utilization of pain and sedation therapy on noninvasive mechanical ventilation in Korean intensive care units: a multi-center prospective observational study.

BACKGROUND: The use of sedative drugs may be an important therapeutic intervention during noninvasive ventilation (NIV) in intensive care units (ICUs). The purpose of this study was to assess the current application of analgosedation in NIV and its impact on clinical outcomes in Korean ICUs. METHODS: Twenty Korean ICUs participated in the study, and data was collected on NIV use during the period between June 2017 and February 2018. Demographic data from all adult patients, NIV clinical parameters, and hospital mortality were included. RESULTS: A total of 155 patients treated with NIV in the ICUs were included, of whom 26 received pain and sedation therapy (sedation group) and 129 did not (control group). The primary cause of ICU admission was due to acute exacerbation of obstructed lung disease (45.7%) in the control group and pneumonia treatment (53.8%) in the sedation group. In addition, causes of NIV application included acute hypercapnic respiratory failure in the control group (62.8%) and post-extubation respiratory failure in the sedation group (57.7%). Arterial partial pressure of carbon dioxide (PaCO2) levels before and after 2 hours of NIV treatment were significantly decreased in both groups: from 61.9±23.8 mm Hg to 54.9±17.6 mm Hg in the control group (P<0.001) and from 54.9±15.1 mm Hg to 51.1±15.1 mm Hg in the sedation group (P=0.048). No significant differences were observed in the success rate of NIV weaning, complications, length of ICU stay, ICU survival rate, or hospital survival rate between the groups. CONCLUSIONS: In NIV patients, analgosedation therapy may have no harmful effects on complications, NIV weaning success, and mortality compared to the control group. Therefore, sedation during NIV may not be unsafe and can be used in patients for pain control when indicated.

Combination Therapy With Polydeoxyribonucleotide and Pirfenidone Alleviates Symptoms of Acute Respiratory Distress Syndrome in Human Lung Epithelial A549 Cells.

PURPOSE: Acute respiratory distress syndrome (ARDS) is characterized by its acute onset of symptoms such as bilateral pulmonary infiltrates, severe hypoxemia, and pulmonary edema. Many patients with ARDS survive in the acute phase, but then die from significant lung fibrosis. METHODS: The effect of combination therapy with polydeoxyribonucleotide (PDRN) and pirfenidone on ARDS was investigated using human lung epithelial A549 cells. ARDS environment was induced by treatment with lipopolysaccharide and transforming growth factor (TGF)-ß. Enzyme-linked immunoassay for connective tissue growth factor (CTGF) and hydroxyproline were conducted. Western blot for collagen type I, fibroblast growth factor (FGF), tumor necrosis factor (TNF)-α, and interleukin (IL)-6 was performed. RESULTS: In this study, 8-µg/mL PDRN enhanced cell viability. Combination therapy with PDRN and pirfenidone and pirfenidone monotherapy suppressed expressions of CTGF and hydroxyproline and inhibited expressions of collagen type I and FGF. Combination therapy with PDRN and pirfenidone and PDRN monotherapy suppressed expression of TNF-α and IL-1ß. CONCLUSION: The combination therapy with PDRN and pirfenidone exerted stronger therapeutic effect against lipopolysaccharide and TGF-ß-induced ARDS environment compared to the PDRN monotherapy or pirfenidone monotherapy. The excellent therapeutic effect of combination therapy with PDRN and pirfenidone on ARDS was shown by promoting the rapid anti-inflammatory effect and inhibiting the fibrotic processes.

Safety of early orthopedic surgery in patients with intermediate/low- or low-risk pulmonary embolism.

BACKGROUND: Preoperative pulmonary embolism (PE) is one of the comorbidities in patients with hip fracture. However, previous studies have not identified the optimal timing of surgery in these patients, who might require early surgery. This study aimed to investigate the safety and clinical feasibility of early surgery in patients with hip fracture and acute PE. METHODS: The medical records of 156 patients with hip fracture, who were suspected to have PE and underwent pulmonary computed tomography angiography at Asan Medical Center from January 2008 to December 2017, were retrospectively reviewed. After excluding patients who were diagnosed with PE during the postoperative period, the baseline characteristics and clinical course were compared between patients preoperatively diagnosed with PE (PE group) and patients without PE during the hospital stay (non-PE group). Adverse outcomes were evaluated during 3 months postoperatively. RESULTS: The baseline characteristics were not different between the PE group (n=90) and the non-PE group (n=50). All patients in the PE group were classified as having an intermediate/low or low risk according to the European Society of Cardiology guidelines and underwent surgery within 30 days after the PE diagnosis (median duration: 2 days). None of the patients in both groups developed symptomatic venous thromboembolism (VTE) during the follow-up. Moreover, there were no statistically significant differences in major bleeding, clinically relevant nonmajor (CRNM) bleeding, transfusion amount, bleeding site, and length of hospital stay between the PE and non-PE groups. CONCLUSIONS: Our results suggest that early surgery might be a reasonable treatment option in patients with hip fracture and acute PE.

Automatic three-dimensional analysis of bone volume and quality change after maxillary sinus augmentation.

INTRODUCTION: Maxillary sinus augmentation is a widely used surgical procedure to increase the bone volume before implant placement. In order to predict the stability of the implant, analysis of the change in bone volume and quality after a sinus graft procedure is necessary. The purpose of this study was to analyze the change in volume and quality of bone graft material after maxillary sinus augmentation using cone beam computed tomography (CBCT). METHODS AND MATERIALS: Maxillary sinus lift procedures using bovine bone materials (Bio-Oss, Geistrich, Swiss) without immediate implantation were performed at the Pusan National University Dental Hospital in 22 patients, from 2014 to 2017. CBCT images were captured before surgery (T1), a day after surgery (T2), and after 4 to 7 months at follow-up (T3). The T2 and T3 images were registered to the T1 image using histogram matching and intensity-based registration. A total of 30 sinuses were analyzed three-dimensionally (3-D), using self-made software MATLAB 2018a (MathWorks, Natick, Massachusetts). The volume and structural indices of the bone graft material were measured and analyzed. RESULTS: The average volume of graft material showed a decrease, while the average gray value showed an increase during the follow-up period, but these changes were not statistically significant. The structural indices of the graft material after histogram matching showed a significant difference in homogeneity, connectivity, thickness, and roughness at the postoperative follow-up. CONCLUSIONS: The volume and gray value showed no statistically significant changes after the maxillary sinus lift procedures. The results of this study show that structural analysis using histogram matching can be used as a promising tool to analyze the quality of graft materials.

An overview of deep learning in the field of dentistry.

PURPOSE: Artificial intelligence (AI), represented by deep learning, can be used for real-life problems and is applied across all sectors of society including medical and dental field. The purpose of this study is to review articles about deep learning that were applied to the field of oral and maxillofacial radiology. MATERIALS AND METHODS: A systematic review was performed using Pubmed, Scopus, and IEEE explore databases to identify articles using deep learning in English literature. The variables from 25 articles included network architecture, number of training data, evaluation result, pros and cons, study object and imaging modality. RESULTS: Convolutional Neural network (CNN) was used as a main network component. The number of published paper and training datasets tended to increase, dealing with various field of dentistry. CONCLUSION: Dental public datasets need to be constructed and data standardization is necessary for clinical application of deep learning in dental field.

Maxillary antroliths detected by cone-beam computed tomography in an adult dental population.

PURPOSE: This study evaluated the prevalence and characteristics of maxillary antroliths using cone-beam computed tomography (CBCT) scans performed for maxillofacial diagnostic purposes. MATERIALS AND METHODS: CBCT scans of 13,946 patients over the age of 20 were reviewed for maxillary antroliths, and prevalence according to sex, age, and the side of the jaw was calculated. The relationships of single or multiple antroliths with sex, side, and the degree of sinus inflammation were evaluated. The shape and dimension of antroliths were also assessed. The data were analyzed using descriptive statistics, the chi-square or Fisher exact tests, and Kendall's tau-b. RESULTS: A total of 138 (0.99%) of the 13,946 patients showed an antrolith in at least 1 sinus. Only 18 patients presented a bilateral manifestation, which brought the total number of sinuses containing an antrolith to 156 (0.56%). Multiple antroliths were observed in 36 sinuses, and the total number of antroliths was 207: 110 punctate, 65 linear, and 32 amorphous. The antrolith dimensions varied from 1 mm2 to 91 mm2 (average, 10.2±15.5 mm2). No statistically significant differences were found according to sex, side, and age group (P>0.05). However, there was a statistically significant difference between the multiplicity of antrolith and the degree of sinus inflammation (P<0.05). CONCLUSION: Cone-beam computed tomography is an effective modality for the detection of incidental antroliths. Maxillary antroliths were found to be very rare and were usually asymptomatic. Dentists should have a comprehensive understanding of their diagnosis and treatment in light of possible associated dental problems.

Polydeoxyribonucleotide Ameliorates Lipopolysaccharide-Induced Lung Injury by Inhibiting Apoptotic Cell Death in Rats.

Lung injury is characterized by diffuse lung inflammation, alveolar-capillary destruction, and alveolar flooding, resulting in respiratory failure. Polydexyribonucleotide (PDRN) has an anti-inflammatory effect, decreasing inflammatory cytokines, and suppressing apoptosis. Thus, we investigated its efficacy in the treatment of lung injury, which was induced in rats using lipopolysaccharide (LPS). Rats were randomly divided into three groups according to sacrifice time, and each group split into control, lung injury-induced, and lung injury-induced + PDRN-treated groups. Rats were sacrificed 24 h and 72 h after PDRN administration, according to each group. Lung injury was induced by intratracheal instillation of LPS (5 mg/kg) in 0.2 mL saline. Rats in PDRN-treated groups received a single intraperitoneal injection of 0.3 mL distilled water including PDRN (8 mg/kg), 1 h after lung injury induction. Percentages of terminal deoxynucleotidyl transferase-mediated dUTP nick end labeling (TUNEL)-positive, cleaved caspase-3-, -8-, and -9-positive cells, the ratio of Bcl-2-associated X protein (Bax) to B-cell lymphoma 2 (Bcl-2), and expressions of inflammatory cytokines (tumor necrosis factor-α, interleukin-6) were decreased by PDRN treatment in the LPS-induced lung injury rats. Therefore, treatment with PDRN reduced lung injury score. This anti-apoptotic effect of PDRN can be ascribed to the enhancing effect of PDRN on adenosine A2A receptor expression. Based on these results, PDRN might be considered as a new therapeutic agent for the treatment of lung injury.

Advanced Age as a Predictor of Survival and Weaning in Venoarterial Extracorporeal Oxygenation: A Retrospective Observational Study.

Background. In most reports on ECMO treatment, advanced age is classified as a contraindication to VA ECMO. We attempted to investigate whether advanced age would be a main risk factor deciding VA ECMO application and performing VA ECMO support. We determined whether advanced age should be regarded as an absolute or relative contraindication to VA ECMO and could affect weaning and survival rates of VA ECMO patients. Methods. VA ECMO was performed on 135 adult patients with primary cardiogenic shock between January 2010 and December 2014. Successful weaning was defined as weaning from ECMO followed by survival for more than 48 hours. Results. Among the 135 patients, 35 survived and were discharged uneventfully, and the remaining 100 did not survive. There were significant differences in survival between age groups, and older age showed a lower survival rate with statistical significance (P = .01). By multivariate logistic regression analysis, age was not significantly associated with in-hospital mortality (P = .83) and was not significantly associated with VA ECMO weaning (P = .11). Conclusions. Advanced age is an undeniable risk factor for VA ECMO; however, patients of advanced age should not be excluded from the chance of recovery after VA ECMO treatment.