Radiomics and machine learning analysis of liver magnetic resonance imaging for prediction and early detection of tumor response in colorectal liver metastases.

PURPOSE: The aim of this study was to demonstrate the effectiveness of a machine learning-based radiomics model for distinguishing tumor response and overall survival in patients with unresectable colorectal liver metastases (CRLM) treated with targeted biological therapy. METHODS: We prospectively recruited 17 patients with unresectable liver metastases of colorectal cancer, who had been given targeted biological therapy as the first line of treatment. All patients underwent liver magnetic resonance imaging (MRI) three times up until 8 weeks after chemotherapy. We evaluated the diagnostic performance of machine learning-based radiomics model in tumor response of liver MRI compared with the guidelines for the Response Evaluation Criteria in Solid Tumors. Overall survival was evaluated using the Kaplan-Meier analysis and compared to the Cox proportional hazard ratios following univariate and multivariate analyses. RESULTS: Performance measurement of the trained model through metrics showed the accuracy of the machine learning model to be 76.5%, and the area under the receiver operating characteristic curve was 0.857 (95% confidence interval [CI], 0.605-0.976; P < 0.001). For the patients classified as non-progressing or progressing by the radiomics model, the median overall survival was 17.5 months (95% CI, 12.8-22.2), and 14.8 months (95% CI, 14.2-15.4), respectively (P = 0.431, log-rank test). CONCLUSION: Machine learning-based radiomics models could have the potential to predict tumor response in patients with unresectable CRLM treated with biologic therapy.

Alterations in pH of Coffee Bean Extract and Properties of Chlorogenic Acid Based on the Roasting Degree.

Factors influencing the sour taste of coffee and the properties of chlorogenic acid are not yet fully understood. This study aimed to evaluate the impact of roasting degree on pH-associated changes in coffee bean extract and the thermal stability of chlorogenic acid. Coffee bean extract pH decreased up to a chromaticity value of 75 but increased with higher chromaticity values. Ultraviolet-visible spectrophotometry and structural analysis attributed this effect to chlorogenic and caffeic acids. Moreover, liquid chromatography-mass spectrometry analysis identified four chlorogenic acid types in green coffee bean extract. Chlorogenic acid isomers were eluted broadly on HPLC, and a chlorogenic acid fraction graph with two peaks, fractions 5 and 9, was obtained. Among the various fractions, the isomer in fraction 5 had significantly lower thermal stability, indicating that thermal stability differs between chlorogenic acid isomers.

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.

Image segmentation of impacted mesiodens using deep learning.

This study aimed to evaluate the performance of deep learning algorithms for the classification and segmentation of impacted mesiodens in pediatric panoramic radiographs. A total of 850 panoramic radiographs of pediatric patients (aged 3-9 years) was included in this study. The U-Net semantic segmentation algorithm was applied for the detection and segmentation of mesiodens in the upper anterior region. For enhancement of the algorithm, pre-trained ResNet models were applied to the encoding path. The segmentation performance of the algorithm was tested using the Jaccard index and Dice coefficient. The diagnostic accuracy, precision, recall, F1-score and time to diagnosis of the algorithms were compared with those of human expert groups using the test dataset. Cohen's kappa statistics were compared between the model and human groups. The segmentation model exhibited a high Jaccard index and Dice coefficient (>90%). In mesiodens diagnosis, the trained model achieved 91-92% accuracy and a 94-95% F1-score, which were comparable with human expert group results (96%). The diagnostic duration of the deep learning model was 7.5 seconds, which was significantly faster in mesiodens detection compared to human groups. The agreement between the deep learning model and human experts is moderate (Cohen's kappa = 0.767). The proposed deep learning algorithm showed good segmentation performance and approached the performance of human experts in the diagnosis of mesiodens, with a significantly faster diagnosis time.

Machine learning model based on radiomics features for AO/OTA classification of pelvic fractures on pelvic radiographs.

Depending on the degree of fracture, pelvic fracture can be accompanied by vascular damage, and in severe cases, it may progress to hemorrhagic shock. Pelvic radiography can quickly diagnose pelvic fractures, and the Association for Osteosynthesis Foundation and Orthopedic Trauma Association (AO/OTA) classification system is useful for evaluating pelvic fracture instability. This study aimed to develop a radiomics-based machine-learning algorithm to quickly diagnose fractures on pelvic X-ray and classify their instability. data used were pelvic anteroposterior radiographs of 990 adults over 18 years of age diagnosed with pelvic fractures, and 200 normal subjects. A total of 93 features were extracted based on radiomics:18 first-order, 24 GLCM, 16 GLRLM, 16 GLSZM, 5 NGTDM, and 14 GLDM features. To improve the performance of machine learning, the feature selection methods RFE, SFS, LASSO, and Ridge were used, and the machine learning models used LR, SVM, RF, XGB, MLP, KNN, and LGBM. Performance measurement was evaluated by area under the curve (AUC) by analyzing the receiver operating characteristic curve. The machine learning model was trained based on the selected features using four feature-selection methods. When the RFE feature selection method was used, the average AUC was higher than that of the other methods. Among them, the combination with the machine learning model SVM showed the best performance, with an average AUC of 0.75±0.06. By obtaining a feature-importance graph for the combination of RFE and SVM, it is possible to identify features with high importance. The AO/OTA classification of normal pelvic rings and pelvic fractures on pelvic AP radiographs using a radiomics-based machine learning model showed the highest AUC when using the SVM classification combination. Further research on the radiomic features of each part of the pelvic bone constituting the pelvic ring is needed.

Deep-learning-based pelvic automatic segmentation in pelvic fractures.

With the recent increase in traffic accidents, pelvic fractures are increasing, second only to skull fractures, in terms of mortality and risk of complications. Research is actively being conducted on the treatment of intra-abdominal bleeding, the primary cause of death related to pelvic fractures. Considerable preliminary research has also been performed on segmenting tumors and organs. However, studies on clinically useful algorithms for bone and pelvic segmentation, based on developed models, are limited. In this study, we explored the potential of deep-learning models presented in previous studies to accurately segment pelvic regions in X-ray images. Data were collected from X-ray images of 940 patients aged 18 or older at Gachon University Gil Hospital from January 2015 to December 2022. To segment the pelvis, Attention U-Net, Swin U-Net, and U-Net were trained, thereby comparing and analyzing the results using five-fold cross-validation. The Swin U-Net model displayed relatively high performance compared to Attention U-Net and U-Net models, achieving an average sensitivity, specificity, accuracy, and dice similarity coefficient of 96.77%, of 98.50%, 98.03%, and 96.32%, respectively.

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.

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.

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.

Automatic Segmentation and Radiologic Measurement of Distal Radius Fractures Using Deep Learning.

Background: Recently, deep learning techniques have been used in medical imaging studies. We present an algorithm that measures radiologic parameters of distal radius fractures using a deep learning technique and compares the predicted parameters with those measured by an orthopedic hand surgeon. Methods: We collected anteroposterior (AP) and lateral X-ray images of 634 wrists in 624 patients with distal radius fractures treated conservatively with a follow-up of at least 2 months. We allocated 507 AP and 507 lateral images to the training set (80% of the images were used to train the model, and 20% were utilized for validation) and 127 AP and 127 lateral images to the test set. The margins of the radius and ulna were annotated for ground truth, and the scaphoid in the lateral views was annotated in the box configuration to determine the volar side of the images. Radius segmentation was performed using attention U-Net, and the volar/dorsal side was identified using a detection and classification model based on RetinaNet. The proposed algorithm measures the radial inclination, dorsal or volar tilt, and radial height by index axes and points from the segmented radius and ulna. Results: The segmentation model for the radius exhibited an accuracy of 99.98% and a Dice similarity coefficient (DSC) of 98.07% for AP images, and an accuracy of 99.75% and a DSC of 94.84% for lateral images. The segmentation model for the ulna showed an accuracy of 99.84% and a DSC of 96.48%. Based on the comparison of the radial inclinations measured by the algorithm and the manual method, the Pearson correlation coefficient was 0.952, and the intraclass correlation coefficient was 0.975. For dorsal/volar tilt, the correlation coefficient was 0.940, and the intraclass correlation coefficient was 0.968. For radial height, it was 0.768 and 0.868, respectively. Conclusions: The deep learning-based algorithm demonstrated excellent segmentation of the distal radius and ulna in AP and lateral radiographs of the wrist with distal radius fractures and afforded automatic measurements of radiologic parameters.

Automated Segmentation and Diagnostic Measurement for the Evaluation of Cervical Spine Injuries Using X-Rays.

Accurate assessment of cervical spine X-ray images through diagnostic metrics plays a crucial role in determining appropriate treatment strategies for cervical injuries and evaluating surgical outcomes. Such assessment can be facilitated through the use of automatic methods such as machine learning and computer vision algorithms. A total of 852 cervical X-rays obtained from Gachon Medical Center were used for multiclass segmentation of the craniofacial bones (hard palate, basion, opisthion) and cervical spine (C1-C7), incorporating architectures such as EfficientNetB4, DenseNet201, and InceptionResNetV2. Diagnostic metrics automatically measured using computer vision algorithms were compared with manually measured metrics through Pearson's correlation coefficient and paired t-tests. The three models demonstrated high average dice coefficient values for the cervical spine (C1, 0.93; C2, 0.96; C3, 0.96; C4, 0.96; C5, 0.96; C6, 0.96; C7, 0.95) and lower values for the craniofacial bones (hard palate, 0.69; basion, 0.81; opisthion, 0.71). Comparison of manually measured metrics and automatically measured metrics showed high Pearson's correlation coefficients in McGregor's line (r = 0.89), space available cord (r = 0.94), cervical sagittal vertical axis (r = 0.99), cervical lordosis (r = 0.88), lower correlations in basion-dens interval (r = 0.65), basion-axial interval (r = 0.72), and Powers ratio (r = 0.62). No metric showed adjusted significant differences at P < 0.05 between manual and automatic metric measuring methods. These findings demonstrate the potential of multiclass segmentation in automating the measurement of diagnostic metrics for cervical spine injuries and showcase the clinical potential for diagnosing cervical spine injuries and evaluating cervical surgical outcomes.

Predicting Mismatch Repair Deficiency Status in Endometrial Cancer through Multi-Resolution Ensemble Learning in Digital Pathology.

For molecular classification of endometrial carcinoma, testing for mismatch repair (MMR) status is becoming a routine process. Mismatch repair deficiency (MMR-D) is caused by loss of expression in one or more of the 4 major MMR proteins: MLH1, MSH2, MSH6, PHS2. Over 30% of patients with endometrial cancer have MMR-D. Determining the MMR status holds significance as individuals with MMR-D are potential candidates for immunotherapy. Pathological whole slide image (WSI) of endometrial cancer with immunohistochemistry results of MMR proteins were gathered. Color normalization was applied to the tiles using a CycleGAN-based network. The WSI was divided into tiles at three different magnifications (2.5 × , 5 × , and 10 ×). Three distinct networks of the same architecture were employed to include features from all three magnification levels and were stacked for ensemble learning. Three architectures, InceptionResNetV2, EfficientNetB2, and EfficientNetB3 were employed and subjected to comparison. The per-tile results were gathered to classify MMR status in the WSI, and prediction accuracy was evaluated using the following performance metrics: AUC, accuracy, sensitivity, and specificity. The EfficientNetB2 was able to make predictions with an AUC of 0.821, highest among the three architectures, and an overall AUC range of 0.767 - 0.821 was reported across the three architectures. In summary, our study successfully predicted MMR classification from pathological WSIs in endometrial cancer through a multi-resolution ensemble learning approach, which holds the potential to facilitate swift decisions on tailored treatment, such as immunotherapy, in clinical settings.

A Comparative Study of Performance Between Federated Learning and Centralized Learning Using Pathological Image of Endometrial Cancer.

Federated learning, an innovative artificial intelligence training method, offers a secure solution for institutions to collaboratively develop models without sharing raw data. This approach offers immense promise and is particularly advantageous for domains dealing with sensitive information, such as patient data. However, when confronted with a distributed data environment, challenges arise due to data paucity or inherent heterogeneity, potentially impacting the performance of federated learning models. Hence, scrutinizing the efficacy of this method in such intricate settings is indispensable. To address this, we harnessed pathological image datasets of endometrial cancer from four hospitals for training and evaluating the performance of a federated learning model and compared it with a centralized learning model. With optimal processing techniques (data augmentation, color normalization, and adaptive optimizer), federated learning exhibited lower precision but higher recall and Dice similarity coefficient (DSC) than centralized learning. Hence, considering the critical importance of recall in the context of medical image processing, federated learning is demonstrated as a viable and applicable approach in this field, offering advantages in terms of both performance and data security.

In Situ Probing of CO2 Reduction on Cu-Phthalocyanine-Derived Cux O Complex.

An in situ measurement of a CO2 reduction reaction (CO2 RR) in Cu-phthalocyanine (CuPC) molecules adsorbed on an Au(111) surface is performed using electrochemical scanning tunneling microscopy. One intriguing phenomenon monitored in situ during CO2 RR is that a well-ordered CuPC adlayer is formed into an unsuspected nanocluster via molecular restructuring. At an electrode potential of -0.7 V versus Ag/AgCl, the Au surface is covered mainly with the clusters, showing restructuring-induced CO2 RR catalytic activity. Using a measurement of X-ray photoelectron spectroscopy, it is revealed that the nanocluster represents a Cu complex with its formation mechanism. This work provides an in situ observation of the restructuring of the electrocatalyst to understand the surface-reactive correlations and suggests the CO2 RR catalyst works at a relatively low potential using the CuPC-derived Cu nanoclusters as active species.

Examining the relationship between sleep quality and depressive symptoms in Korean women engaged in soccer during the coronavirus pandemic.

Introduction: The COVID-19 pandemic has caused sudden changes to daily lives, such as self-isolation and social distancing, and has negatively affected sleep quality and patterns. The resulting psychological discomfort has caused many Korean women to experience depressive moods. Vigorous physical activity is considered effective in improving sleep quality and alleviating depressive symptoms. As a form of vigorous physical activity, soccer could be used to improve women's mental health. This study aimed to ascertain the effects of playing soccer on sleep quality and depressive symptoms in women. Methods: Non-face-to-face questionnaires were administered using Pittsburgh Sleep Quality Index to measure sleep quality and Patient Health Questionnaire-9 to measure depressive symptoms, targeting 200 of 297 soccer-playing Korean women aged 20-50 years, from October 13, 2022, to January 15, 2023. A total of 172 questionnaires administered to soccer participants were used, while 28 with insincere and double or no-responses were excluded. Additionally, 124 samples of non-exercise participants were collected, with the help of "EMBRAIN," a Korean research and survey company. This study analyzed differences in sleep quality and depressive symptoms, and correlations and multiple regression analysis were performed. Results: The soccer group was shown to have a high quality of sleep. In relation to the effect of sleep quality on depressive symptoms, subjective sleep quality, sleep latency, sleep disturbance, use of sleeping pills, and daytime functional disorder had a significant effect. In the relation to the effect of sleep quality on depressive symptoms, significant effect was found in subjective sleep quality, sleep latency, sleep disturbance, and daytime functional disorder of soccer participants, and non-exercise participants displayed significant effect in subjective sleep quality, sleep disturbance, and the use of sleeping pills. Discussion: This study examined the effect of soccer participation on sleep quality and depressive symptoms among women. Soccer, which requires high activity and teamwork levels, improves sociability in women by enhancing their sense of belonging, self-confidence, and team spirit.

Machine learning based prediction of recurrence after curative resection for rectal cancer.

PURPOSE: Patients with rectal cancer without distant metastases are typically treated with radical surgery. Post curative resection, several factors can affect tumor recurrence. This study aimed to analyze factors related to rectal cancer recurrence after curative resection using different machine learning techniques. METHODS: Consecutive patients who underwent curative surgery for rectal cancer between 2004 and 2018 at Gil Medical Center were included. Patients with stage IV disease, colon cancer, anal cancer, other recurrent cancer, emergency surgery, or hereditary malignancies were excluded from the study. The Synthetic Minority Oversampling Technique with Tomek link (SMOTETomek) technique was used to compensate for data imbalance between recurrent and no-recurrent groups. Four machine learning methods, logistic regression (LR), support vector machine (SVM), random forest (RF), and Extreme gradient boosting (XGBoost), were used to identify significant factors. To overfit and improve the model performance, feature importance was calculated using the permutation importance technique. RESULTS: A total of 3320 patients were included in the study. After exclusion, the total sample size of the study was 961 patients. The median follow-up period was 60.8 months (range:1.2-192.4). The recurrence rate during follow-up was 13.2% (n = 127). After applying the SMOTETomek method, the number of patients in both groups, recurrent and non-recurrent group were equalized to 667 patients. After analyzing for 16 variables, the top eight ranked variables {pathologic Tumor stage (pT), sex, concurrent chemoradiotherapy, pathologic Node stage (pN), age, postoperative chemotherapy, pathologic Tumor-Node-Metastasis stage (pTNM), and perineural invasion} were selected based on the order of permutational importance. The highest area under the curve (AUC) was for the SVM method (0.831). The sensitivity, specificity, and accuracy were found to be 0.692, 0.814, and 0.798, respectively. The lowest AUC was obtained for the XGBoost method (0.804), with a sensitivity, specificity, and accuracy of 0.308, 0.928, and 0.845, respectively. The variable with highest importance was pT as assessed through SVM, RF, and XGBoost (0.06, 0.12, and 0.13, respectively), whereas pTNM had the highest importance when assessed by LR (0.05). CONCLUSIONS: In the current study, SVM showed the best AUC, and the most influential factor across all machine learning methods except LR was found to be pT. The rectal cancer patients who have a high pT stage during postoperative follow-up are need to be more close surveillance.

A Comparative Study of Bipolar Hemiarthroplasty for Intertrochanteric Fracture: Direct Anterior Approach versus Conventional Posterolateral Approach.

Purpose: The aim of this study was to compare short-term results from use of the direct anterior approach (DAA) and the conventional posterolateral approach (PLA) in performance of bipolar hemiarthroplasty for treatment of femoral intertrochanteric fractures in elderly patients. Materials and Methods: A retrospective review of 100 patients with intertrochanteric fractures who underwent bipolar hemiarthroplasty was conducted. The PLA was used in 50 cases from 2016 to 2019; since that time we have used the DAA in 50 cases from 2019 to 2021. Measurements of mean operative time, blood loss, hospitalization period, and ambulation status, greater trochanter (GT) migration and stem subsidence were performed. And the incidence of complications was examined. Results: Operative time was 73.60±14.56 minutes in the PLA group and 79.80±8.89 minutes in the DAA group (P<0.05). However, after experiencing 20 cases using DAA, there was no statistically difference in operative time between two groups (P=0.331). Blood loss was 380.76±180.67 mL in the PLA group and 318.14±138.51 mL in the DAA group (P<0.05). The hospitalization was 23.76±11.89 days in the PLA group and 21.45±4.18 days in the DAA group (P=0.207). In both groups, there were no progressive GT migration, intraoperative fractures or dislocations, although there was one case of infection in the PLA group. Conclusion: Although use of the DAA in performance of bipolar hemiarthroplasty required slightly more time in the beginning compared with the PLA, the DAA may well be an alternative, safe surgical technique as a muscle preserving procedure in elderly patients with intertrochanteric fractures.

Improving the Accuracy of Otitis Media with Effusion Diagnosis in Pediatric Patients Using Deep Learning.

Otitis media with effusion (OME), primarily seen in children aged 2 years and younger, is characterized by the presence of fluid in the middle ear, often resulting in hearing loss and aural fullness. While deep learning networks have been explored to aid OME diagnosis, prior work did not often specify if pediatric images were used for training, causing uncertainties about their clinical relevance, especially due to important distinctions between the tympanic membranes of small children and adults. We trained cross-validated ResNet50, DenseNet201, InceptionV3, and InceptionResNetV2 models on 1150 pediatric tympanic membrane images from otoendoscopes to classify OME. When assessed using a separate dataset of 100 pediatric tympanic membrane images, the models achieved mean accuracies of 92.9% (ResNet50), 97.2% (DenseNet201), 96.0% (InceptionV3), and 94.8% (InceptionResNetV2), compared to the seven otolaryngologists that achieved accuracies between 84.0% and 69.0%. The results showed that even the worst-performing model trained on fold 3 of InceptionResNetV2 with an accuracy of 88.0% exceeded the accuracy of the highest-performing otolaryngologist at 84.0%. Our findings suggest that these specifically trained deep learning models can potentially enhance the clinical diagnosis of OME using pediatric otoendoscopic tympanic membrane images.

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.