Deep Learning-Based Multi-Class Segmentation of the Paranasal Sinuses of Sinusitis Patients Based on Computed Tomographic Images.

Accurate paranasal sinus segmentation is essential for reducing surgical complications through surgical guidance systems. This study introduces a multiclass Convolutional Neural Network (CNN) segmentation model by comparing four 3D U-Net variations-normal, residual, dense, and residual-dense. Data normalization and training were conducted on a 40-patient test set (20 normal, 20 abnormal) using 5-fold cross-validation. The normal 3D U-Net demonstrated superior performance with an F1 score of 84.29% on the normal test set and 79.32% on the abnormal set, exhibiting higher true positive rates for the sphenoid and maxillary sinus in both sets. Despite effective segmentation in clear sinuses, limitations were observed in mucosal inflammation. Nevertheless, the algorithm's enhanced segmentation of abnormal sinuses suggests potential clinical applications, with ongoing refinements expected for broader utility.

Deep Learning-Based Nystagmus Detection for BPPV Diagnosis.

In this study, we propose a deep learning-based nystagmus detection algorithm using video oculography (VOG) data to diagnose benign paroxysmal positional vertigo (BPPV). Various deep learning architectures were utilized to develop and evaluate nystagmus detection models. Among the four deep learning architectures used in this study, the CNN1D model proposed as a nystagmus detection model demonstrated the best performance, exhibiting a sensitivity of 94.06 ± 0.78%, specificity of 86.39 ± 1.31%, precision of 91.34 ± 0.84%, accuracy of 91.02 ± 0.66%, and an F1-score of 92.68 ± 0.55%. These results indicate the high accuracy and generalizability of the proposed nystagmus diagnosis algorithm. In conclusion, this study validates the practicality of deep learning in diagnosing BPPV and offers avenues for numerous potential applications of deep learning in the medical diagnostic sector. The findings of this research underscore its importance in enhancing diagnostic accuracy and efficiency in healthcare.

Fully automated deep learning approach to dental development assessment in panoramic radiographs.

BACKGROUND: Dental development assessment is an important factor in dental age estimation and dental maturity evaluation. This study aimed to develop and evaluate the performance of an automated dental development staging system based on Demirjian's method using deep learning. METHODS: The study included 5133 anonymous panoramic radiographs obtained from the Department of Pediatric Dentistry database at Seoul National University Dental Hospital between 2020 and 2021. The proposed methodology involves a three-step procedure for dental staging: detection, segmentation, and classification. The panoramic data were randomly divided into training and validating sets (8:2), and YOLOv5, U-Net, and EfficientNet were trained and employed for each stage. The models' performance, along with the Grad-CAM analysis of EfficientNet, was evaluated. RESULTS: The mean average precision (mAP) was 0.995 for detection, and the segmentation achieved an accuracy of 0.978. The classification performance showed F1 scores of 69.23, 80.67, 84.97, and 90.81 for the Incisor, Canine, Premolar, and Molar models, respectively. In the Grad-CAM analysis, the classification model focused on the apical portion of the developing tooth, a crucial feature for staging according to Demirjian's method. CONCLUSIONS: These results indicate that the proposed deep learning approach for automated dental staging can serve as a supportive tool for dentists, facilitating rapid and objective dental age estimation and dental maturity evaluation.

Correlation between dental and skeletal maturity in Korean children based on dental maturity percentile: a retrospective study.

BACKGROUND: The correlation between dental maturity and skeletal maturity has been proposed, but its clinical application remains challenging. Moreover, the varying correlations observed in different studies indicate the necessity for research tailored to specific populations. AIM: To compare skeletal maturity in Korean children with advanced and delayed dental maturity using dental maturity percentile. DESIGN: Dental panoramic radiographs and cephalometric radiographs were obtained from 5133 and 395 healthy Korean children aged between 4 and 16 years old. Dental maturity was assessed with Demirjian's method, while skeletal maturity was assessed with the cervical vertebral maturation method. Standard percentile curves were developed through quantile regression. Advanced (93 boys and 110 girls) and delayed (92 boys and 100 girls) dental maturity groups were defined by the 50th percentile. RESULTS: The advanced group showed earlier skeletal maturity in multiple cervical stages (CS) in both boys (CS 1, 2, 3, 4, and 6) and girls (CS 1, 3, 4, 5, and 6). Significant differences, as determined by Mann-Whitney U tests, were observed in CS 1 for boys (p = 0.004) and in CS 4 for girls (p = 0.037). High Spearman correlation coefficients between dental maturity and cervical vertebral maturity exceeded 0.826 (p = 0.000) in all groups. CONCLUSION: A correlation between dental and skeletal maturity, as well as advanced skeletal maturity in the advanced dental maturity group, was observed. Using percentile curves to determine dental maturity may aid in assessing skeletal maturity, with potential applications in orthodontic diagnosis and treatment planning.

Clinical Outcomes of Transarterial Embolization for Chronic Achilles Tendinopathy Refractory to Conservative Treatment: A Pilot Study.

PURPOSE: To evaluate the effectiveness and safety of transarterial embolization (TAE) for chronic Achilles tendinopathy (AT) refractory to conservative treatment. MATERIALS AND METHODS: This retrospective study included 20 patients (12 men and 8 women; mean age, 30.3 years) who received TAE using imipenem/cilastatin sodium for refractory chronic AT from May 2019 to April 2021. Nine patients had bilateral involvement. A total of 29 procedures were performed (8 for nonathletes and 21 for athletes). If feasible, embolization was performed superselectively of the arterial branch demonstrating hypervascularity, early venous drainage, and/or supplying the pain site noted using a radiopaque marker. The visual analog scale (VAS, 0-10) score was used to assess pain symptoms at baseline and during the follow-up period (1 day; 1 week; 1, 3, and 6 months; and open period). Clinical success was defined as a decrease of >50% in the VAS score at 6 months when compared with baseline. RESULTS: In 25 (86.2%) of 29 procedures, clinical success was achieved. Significant decreases in the VAS scores were noted at 1 day, 1 week, 1 month, 3 months, and 6 months (6.86 at the baseline vs 3.48, 3.41, 3.10, 2.55, and 1.62, respectively; all P < .01). For patients available for the 12- and 24-month follow-ups (n = 19 and 6, respectively), the mean VAS scores significantly decreased (6.84 vs 2.00 and 7.33 vs 1.17, respectively; all P < .01). No serious adverse events were observed during follow-up. CONCLUSIONS: TAE may alleviate pain for patients with chronic AT refractory to the conservative treatment with a low risk of adverse events.

Clinicoprognostic Study of Hydroa Vacciniforme-like Lymphoproliferative Diseases: A Systematic Review.

BACKGROUND: Limited clinicopathological and prognostic data are available on hydroa vacciniforme (HV)-like lymphoproliferative diseases (HVLPD). METHODS: This systematic review searched HVLPD reports in Medline via PubMed, Embase, Cochrane, and CINAHL databases in October 2020. RESULTS: A total of 393 patients (65 classic HV, 328 severe HV/HV-like T-cell lymphoma [HVLL]) were analyzed. Among severe HV/HVLL cases, 56.0% were Asians, whereas 3.1% were Caucasians. Facial edema, hypersensitivity to mosquito bites, the onset of skin lesion, and percentage of severe HV/HVLL differed significantly by race. Progression to systemic lymphoma was confirmed in 9.4% of HVLPD patients. Death occurred in 39.7% patients with severe HV/HVLL. Facial edema was the only risk factor associated with progression and overall survival. Mortality risk was higher in Latin Americans than in Asians and Caucasians. CD4/CD8 double-negativity was significantly associated with the worst prognosis and increased mortality. CONCLUSION: HVLPD is a heterogeneous entity with variable clinicopathological features associated with genetic predispositions.

Prevalence of anxiety during the COVID-19 pandemic in patients diagnosed with subglottic stenosis.

OBJECTIVES: In the wake of the novel coronavirus disease (COVID-19), patients with subglottic stenosis (SGS) have a new, seemingly ubiquitous, respiratory disease to contend with. Whether real or perceived, it is likely that patients with SGS will feel exposed during the current pandemic. This study seeks to determine whether patients with SGS have increased rates of anxiety during the COVID-19 pandemic relative to healthy controls, as well as how much of an impact the pandemic itself plays in the mental health of this population. METHODS: Retrospective review of 10 patients with a confirmed SGS diagnosis and 21 control patients were surveyed via telephone. Patients of all ages that had an in-person or virtual visit within 3 months of the survey start date were included. RESULTS: A total of 30 patients were surveyed in this study, of whom 67.8 % were in the control group and 32.2 % were comprised of patients diagnosed with SGS. SGS patients reported a significantly higher level of anxiety on the GAD-7 scale with severe anxiety in 20 % of patients, moderate anxiety in 50 % of patients, mild anxiety in 20 %, and 10 % reporting no anxiety. Overall, the average reported GAD-7 score of the SGS patients and control patients were 10.8 ± 4.96 and 6.67 ± 2.96 respectively (p < 0.05). CONCLUSIONS: This study is the first of its kind to analyze the rates and causes of anxiety within the context of the COVID-19 pandemic on patients diagnosed with subglottic stenosis. SGS patients were found to have a significantly higher anxiety based on the GAD-7 survey in comparison to patients without SGS. LEVEL OF EVIDENCE: IV.

Automatic Spine Segmentation and Parameter Measurement for Radiological Analysis of Whole-Spine Lateral Radiographs Using Deep Learning and Computer Vision.

Radiographic examination is essential for diagnosing spinal disorders, and the measurement of spino-pelvic parameters provides important information for the diagnosis and treatment planning of spinal sagittal deformities. While manual measurement methods are the golden standard for measuring parameters, they can be time consuming, inefficient, and rater dependent. Previous studies that have used automatic measurement methods to alleviate the downsides of manual measurements showed low accuracy or could not be applied to general films. We propose a pipeline for automated measurement of spinal parameters by combining a Mask R-CNN model for spine segmentation with computer vision algorithms. This pipeline can be incorporated into clinical workflows to provide clinical utility in diagnosis and treatment planning. A total of 1807 lateral radiographs were used for the training (n = 1607) and validation (n = 200) of the spine segmentation model. An additional 200 radiographs, which were also used for validation, were examined by three surgeons to evaluate the performance of the pipeline. Parameters automatically measured by the algorithm in the test set were statistically compared to parameters measured manually by the three surgeons. The Mask R-CNN model achieved an average precision at 50% intersection over union (AP50) of 96.2% and a Dice score of 92.6% for the spine segmentation task in the test set. The mean absolute error values of the spino-pelvic parameters measurement results were within the range of 0.4° (pelvic tilt) to 3.0° (lumbar lordosis, pelvic incidence), and the standard error of estimate was within the range of 0.5° (pelvic tilt) to 4.0° (pelvic incidence). The intraclass correlation coefficient values ranged from 0.86 (sacral slope) to 0.99 (pelvic tilt, sagittal vertical axis).

Effect of Water Vapor on Oxidation Processes of the Cu(111) Surface and Sublayer.

Copper-based catalysts have different catalytic properties depending on the oxidation states of Cu. We report operando observations of the Cu(111) oxidation processes using near-ambient pressure scanning tunneling microscopy (NAP-STM) and near-ambient pressure X-ray photoelectron spectroscopy (NAP-XPS). The Cu(111) surface was chemically inactive to water vapor, but only physisorption of water molecules was observed by NAP-STM. Under O2 environments, dry oxidation started at the step edges and proceeded to the terraces as a Cu2O phase. Humid oxidation of the H2O/O2 gas mixture was also promoted at the step edges to the terraces. After the Cu2O covered the surface under humid conditions, hydroxides and adsorbed water layers formed. NAP-STM observations showed that Cu2O was generated at lower steps in dry oxidation with independent terrace oxidations, whereas Cu2O was generated at upper steps in humid oxidation. The difference in the oxidation mechanisms was caused by water molecules. When the surface was entirely oxidized, the diffusion of Cu and O atoms with a reconstruction of the Cu2O structures induced additional subsurface oxidation. NAP-XPS measurements showed that the Cu2O thickness in dry oxidation was greater than that in humid oxidation under all pressure conditions.

Mesenchymal Stem Cells and Exosomes: A Novel Therapeutic Approach for Corneal Diseases.

The cornea, with its delicate structure, is vulnerable to damage from physical, chemical, and genetic factors. Corneal transplantation, including penetrating and lamellar keratoplasties, can restore the functions of the cornea in cases of severe damage. However, the process of corneal transplantation presents considerable obstacles, including a shortage of available donors, the risk of severe graft rejection, and potentially life-threatening complications. Over the past few decades, mesenchymal stem cell (MSC) therapy has become a novel alternative approach to corneal regeneration. Numerous studies have demonstrated the potential of MSCs to differentiate into different corneal cell types, such as keratocytes, epithelial cells, and endothelial cells. MSCs are considered a suitable candidate for corneal regeneration because of their promising therapeutic perspective and beneficial properties. MSCs compromise unique immunomodulation, anti-angiogenesis, and anti-inflammatory properties and secrete various growth factors, thus promoting corneal reconstruction. These effects in corneal engineering are mediated by MSCs differentiating into different lineages and paracrine action via exosomes. Early studies have proven the roles of MSC-derived exosomes in corneal regeneration by reducing inflammation, inhibiting neovascularization, and angiogenesis, and by promoting cell proliferation. This review highlights the contribution of MSCs and MSC-derived exosomes, their current usage status to overcome corneal disease, and their potential to restore different corneal layers as novel therapeutic agents. It also discusses feasible future possibilities, applications, challenges, and opportunities for future research in this field.

Deep learning-based prediction of osseointegration for dental implant using plain radiography.

BACKGROUND: In this study, we investigated whether deep learning-based prediction of osseointegration of dental implants using plain radiography is possible. METHODS: Panoramic and periapical radiographs of 580 patients (1,206 dental implants) were used to train and test a deep learning model. Group 1 (338 patients, 591 dental implants) included implants that were radiographed immediately after implant placement, that is, when osseointegration had not yet occurred. Group 2 (242 patients, 615 dental implants) included implants radiographed after confirming successful osseointegration. A dataset was extracted using random sampling and was composed of training, validation, and test sets. For osseointegration prediction, we employed seven different deep learning models. Each deep-learning model was built by performing the experiment 10 times. For each experiment, the dataset was randomly separated in a 60:20:20 ratio. For model evaluation, the specificity, sensitivity, accuracy, and AUROC (Area under the receiver operating characteristic curve) of the models was calculated. RESULTS: The mean specificity, sensitivity, and accuracy of the deep learning models were 0.780-0.857, 0.811-0.833, and 0.799-0.836, respectively. Furthermore, the mean AUROC values ranged from to 0.890-0.922. The best model yields an accuracy of 0.896, and the worst model yields an accuracy of 0.702. CONCLUSION: This study found that osseointegration of dental implants can be predicted to some extent through deep learning using plain radiography. This is expected to complement the evaluation methods of dental implant osseointegration that are currently widely used.

Criteria for early diagnosis of mandibular third molar agenesis based on the developmental stages of mandibular canine, first and second premolars, and second molar: a retrospective cohort study.

BACKGROUND: Permanent first molars with severe dental caries, developmental defects, or involved in oral pathologies are at risk of poor prognosis in children. Accordingly, using the third molar to replace the first molar can be a good treatment option when third molar agenesis is predicted early. Thus, this retrospective cohort study aimed to develop criteria for early detection of mandibular third molar (L8) agenesis based on the developmental stages of mandibular canine (L3), first premolar (L4), second premolar (L5), and second molar (L7). METHOD: Overall, 1,044 and 919 panoramic radiographs of 343 males and 317 females, respectively, taken between the ages of 6 and 12 years were included. All developmental stages of L3, L4, L5, L7, and L8 were analyzed based on the dental age, as suggested by Demirjian et al. The independent t-test was used to assess age differences between males and females. The rank correlation coefficients were examined using Kendall's tau with bootstrap analysis and Bonferroni's correction to confirm the teeth showing developmental stages most similar to those of L8s. Finally, a survival analysis was performed to determine the criteria for the early diagnosis of mandibular third molar agenesis. RESULTS: Some age differences were found in dental developmental stages between males and females. Correlation coefficients between all stages of L3, L4, L5, and L7 and L8 were high. In particular, the correlation coefficient between L7 and L8 was the highest, whereas that between L3 and L8 was the lowest. CONCLUSION: If at least two of the following criteria (F stage of L3, F stage of L4, F stage of L5, and E stage of L7) are met in the absence of L8 crypt, agenesis of L8 can be confirmed.

Increased adolescent game usage and health-related risk behaviors during the COVID-19 pandemic.

This study examines adolescent game usage and corresponding health-related risk behaviors during a period of limited social interaction and activity due to the COVID-19 pandemic. Participants included 225 middle- and 225 high-school students in Seoul who completed a survey online from October 1 to 30, 2021. The study measured participants' game usage level and the health-related risk behavior index. Findings showed that participants who engaged in excessive gaming showed higher levels of health-related risk behaviors. A multivariate analysis of variance was conducted to compare the health-related risk behaviors of students in the general, potential, and high-risk groups on excessive gaming. Results indicated that female students in the high-risk group showed higher stress levels and fatigue (f = 5.549, p < .01, Cohen's d = 0.016) than the males of the same group. However, male students showed higher physical inactivity levels (f = 3.195, p > .05, Cohen's d = 0.009) than females. The post hoc test indicated clear sex distinctions among the general, potential, and high-risk groups on excessive gaming (p < .001). Among the high-risk game usage group, female students displayed a higher level of risk behaviors than males. Adolescent gaming addiction should be considered an emotional and behavioral disorder for which parental guidance and support are needed, and counseling experts and professionals must come together to provide a cure and reform program.

Deep learning-based fully automated body composition analysis of thigh CT: comparison with DXA measurement.

OBJECTIVES: To compare volumetric CT with DL-based fully automated segmentation and dual-energy X-ray absorptiometry (DXA) in the measurement of thigh tissue composition. METHODS: This prospective study was performed from January 2019 to December 2020. The participants underwent DXA to determine the body composition of the whole body and thigh. CT was performed in the thigh region; the images were automatically segmented into three muscle groups and adipose tissue by custom-developed DL-based automated segmentation software. Subsequently, the program reported the tissue composition of the thigh. The correlation and agreement between variables measured by DXA and CT were assessed. Then, CT thigh tissue volume prediction equations based on DXA-derived thigh tissue mass were developed using a general linear model. RESULTS: In total, 100 patients (mean age, 44.9 years; 60 women) were evaluated. There was a strong correlation between the CT and DXA measurements (R = 0.813~0.98, p < 0.001). There was no significant difference in total soft tissue mass between DXA and CT measurement (p = 0.183). However, DXA overestimated thigh lean (muscle) mass and underestimated thigh total fat mass (p < 0.001). The DXA-derived lean mass was an average of 10% higher than the CT-derived lean mass and 47% higher than the CT-derived lean muscle mass. The DXA-derived total fat mass was approximately 20% lower than the CT-derived total fat mass. The predicted CT tissue volume using DXA-derived data was highly correlated with actual CT-measured tissue volume in the validation group (R2 = 0.96~0.97, p < 0.001). CONCLUSIONS: Volumetric CT measurements with DL-based fully automated segmentation are a rapid and more accurate method for measuring thigh tissue composition. KEY POINTS: • There was a positive correlation between CT and DXA measurements in both the whole body and thigh. • DXA overestimated thigh lean mass by 10%, lean muscle mass by 47%, but underestimated total fat mass by 20% compared to the CT method. • The equations for predicting CT volume (cm3) were developed using DXA data (g), age, height (cm), and body weight (kg) and good model performance was proven in the validation study.

Diagnostic effect of artificial intelligence solution for referable thoracic abnormalities on chest radiography: a multicenter respiratory outpatient diagnostic cohort study.

OBJECTIVES: We aim ed to evaluate a commercial artificial intelligence (AI) solution on a multicenter cohort of chest radiographs and to compare physicians' ability to detect and localize referable thoracic abnormalities with and without AI assistance. METHODS: In this retrospective diagnostic cohort study, we investigated 6,006 consecutive patients who underwent both chest radiography and CT. We evaluated a commercially available AI solution intended to facilitate the detection of three chest abnormalities (nodule/masses, consolidation, and pneumothorax) against a reference standard to measure its diagnostic performance. Moreover, twelve physicians, including thoracic radiologists, board-certified radiologists, radiology residents, and pulmonologists, assessed a dataset of 230 randomly sampled chest radiographic images. The images were reviewed twice per physician, with and without AI, with a 4-week washout period. We measured the impact of AI assistance on observer's AUC, sensitivity, specificity, and the area under the alternative free-response ROC (AUAFROC). RESULTS: In the entire set (n = 6,006), the AI solution showed average sensitivity, specificity, and AUC of 0.885, 0.723, and 0.867, respectively. In the test dataset (n = 230), the average AUC and AUAFROC across observers significantly increased with AI assistance (from 0.861 to 0.886; p = 0.003 and from 0.797 to 0.822; p = 0.003, respectively). CONCLUSIONS: The diagnostic performance of the AI solution was found to be acceptable for the images from respiratory outpatient clinics. The diagnostic performance of physicians marginally improved with the use of AI solutions. Further evaluation of AI assistance for chest radiographs using a prospective design is required to prove the efficacy of AI assistance. KEY POINTS: • AI assistance for chest radiographs marginally improved physicians' performance in detecting and localizing referable thoracic abnormalities on chest radiographs. • The detection or localization of referable thoracic abnormalities by pulmonologists and radiology residents improved with the use of AI assistance.

Machine Learning Model Based on Radiomic Features for Differentiation between COVID-19 and Pneumonia on Chest X-ray.

Machine learning approaches are employed to analyze differences in real-time reverse transcription polymerase chain reaction scans to differentiate between COVID-19 and pneumonia. However, these methods suffer from large training data requirements, unreliable images, and uncertain clinical diagnosis. Thus, in this paper, we used a machine learning model to differentiate between COVID-19 and pneumonia via radiomic features using a bias-minimized dataset of chest X-ray scans. We used logistic regression (LR), naive Bayes (NB), support vector machine (SVM), k-nearest neighbor (KNN), bagging, random forest (RF), extreme gradient boosting (XGB), and light gradient boosting machine (LGBM) to differentiate between COVID-19 and pneumonia based on training data. Further, we used a grid search to determine optimal hyperparameters for each machine learning model and 5-fold cross-validation to prevent overfitting. The identification performances of COVID-19 and pneumonia were compared with separately constructed test data for four machine learning models trained using the maximum probability, contrast, and difference variance of the gray level co-occurrence matrix (GLCM), and the skewness as input variables. The LGBM and bagging model showed the highest and lowest performances; the GLCM difference variance showed a high overall effect in all models. Thus, we confirmed that the radiomic features in chest X-rays can be used as indicators to differentiate between COVID-19 and pneumonia using machine learning.

FILM: Filtering and Machine Learning for Malware Detection in Edge Computing.

Machine learning with static-analysis features extracted from malware files has been adopted to detect malware variants, which is desirable for resource-constrained edge computing and Internet-of-Things devices with sensors; however, this learned model suffers from a misclassification problem because some malicious files have almost the same static-analysis features as benign ones. In this paper, we present a new detection method for edge computing that can utilize existing machine learning models to classify a suspicious file into either benign, malicious, or unpredictable categories while existing models make only a binary decision of either benign or malicious. The new method can utilize any existing deep learning models developed for malware detection after appending a simple sigmoid function to the models. When interpreting the sigmoid value during the testing phase, the new method determines if the model is confident about its prediction; therefore, the new method can take only the prediction of high accuracy, which reduces incorrect predictions on ambiguous static-analysis features. Through experiments on real malware datasets, we confirm that the new scheme significantly enhances the accuracy, precision, and recall of existing deep learning models. For example, the accuracy is enhanced from 0.96 to 0.99, while some files are classified as unpredictable that can be entrusted to the cloud for further dynamic or human analysis.

Segmentation Performance Comparison Considering Regional Characteristics in Chest X-ray Using Deep Learning.

Chest radiography is one of the most widely used diagnostic methods in hospitals, but it is difficult to read clearly because several human organ tissues and bones overlap. Therefore, various image processing and rib segmentation methods have been proposed to focus on the desired target. However, it is challenging to segment ribs elaborately using deep learning because they cannot reflect the characteristics of each region. Identifying which region has specific characteristics vulnerable to deep learning is an essential indicator of developing segmentation methods in medical imaging. Therefore, it is necessary to compare the deep learning performance differences based on regional characteristics. This study compares the differences in deep learning performance based on the rib region to verify whether deep learning reflects the characteristics of each part and to demonstrate why this regional performance difference has occurred. We utilized 195 normal chest X-ray datasets with data augmentation for learning and 5-fold cross-validation. To compare segmentation performance, the rib image was divided vertically and horizontally based on the spine, clavicle, heart, and lower organs, which are characteristic indicators of the baseline chest X-ray. Resultingly, we found that the deep learning model showed a 6-7% difference in the segmentation performance depending on the regional characteristics of the rib. We verified that the performance differences in each region cannot be ignored. This study will enable a more precise segmentation of the ribs and the development of practical deep learning algorithms.

RGB Channel Superposition Algorithm with Acetowhite Mask Images in a Cervical Cancer Classification Deep Learning Model.

Cervical cancer is one of the main causes of death from cancer in women. However, it can be treated successfully at an early stage. This study aims to propose an image processing algorithm based on acetowhite, which is an important criterion for diagnosing cervical cancer, to increase the accuracy of the deep learning classification model. Then, we mainly compared the performance of the model, the original image without image processing, a mask image made with acetowhite as the region of interest, and an image using the proposed algorithm. In conclusion, the deep learning classification model based on images with the proposed algorithm achieved an accuracy of 81.31%, which is approximately 9% higher than the model with original images and approximately 4% higher than the model with acetowhite mask images. Our study suggests that the proposed algorithm based on acetowhite could have a better performance than other image processing algorithms for classifying stages of cervical images.

A Study on 3D Deep Learning-Based Automatic Diagnosis of Nasal Fractures.

This paper reported a study on the 3-dimensional deep-learning-based automatic diagnosis of nasal fractures. (1) Background: The nasal bone is the most protuberant feature of the face; therefore, it is highly vulnerable to facial trauma and its fractures are known as the most common facial fractures worldwide. In addition, its adhesion causes rapid deformation, so a clear diagnosis is needed early after fracture onset. (2) Methods: The collected computed tomography images were reconstructed to isotropic voxel data including the whole region of the nasal bone, which are represented in a fixed cubic volume. The configured 3-dimensional input data were then automatically classified by the deep learning of residual neural networks (3D-ResNet34 and ResNet50) with the spatial context information using a single network, whose performance was evaluated by 5-fold cross-validation. (3) Results: The classification of nasal fractures with simple 3D-ResNet34 and ResNet50 networks achieved areas under the receiver operating characteristic curve of 94.5% and 93.4% for binary classification, respectively, both indicating unprecedented high performance in the task. (4) Conclusions: In this paper, it is presented the possibility of automatic nasal bone fracture diagnosis using a 3-dimensional Resnet-based single classification network and it will improve the diagnostic environment with future research.