Search

Background: Notwithstanding the encouraging results of previous studies reporting on the efficiency of deep learning (DL) in COVID-19 prognostication, clinical adoption of the developed methodology still needs to be improved. To overcome this limitation, we set out to predict the prognosis of a large multi-institutional cohort of patients with COVID-19 using a DL-based model., Purpose: This study aimed to evaluate the performance of deep privacy-preserving federated learning (DPFL) in predicting COVID-19 outcomes using chest CT images., Methods: After applying inclusion and exclusion criteria, 3055 patients from 19 centers, including 1599 alive and 1456 deceased, were enrolled in this study. Data from all centers were split (randomly with stratification respective to each center and class) into a training/validation set (70%/10%) and a hold-out test set (20%). For the DL model, feature extraction was performed on 2D slices, and averaging was performed at the final layer to construct a 3D model for each scan. The DensNet model was used for feature extraction. The model was developed using centralized and FL approaches. For FL, we employed DPFL approaches. Membership inference attack was also evaluated in the FL strategy. For model evaluation, different metrics were reported in the hold-out test sets. In addition, models trained in two scenarios, centralized and FL, were compared using the DeLong test for statistical differences., Results: The centralized model achieved an accuracy of 0.76, while the DPFL model had an accuracy of 0.75. Both the centralized and DPFL models achieved a specificity of 0.77. The centralized model achieved a sensitivity of 0.74, while the DPFL model had a sensitivity of 0.73. A mean AUC of 0.82 and 0.81 with 95% confidence intervals of (95% CI: 0.79-0.85) and (95% CI: 0.77-0.84) were achieved by the centralized model and the DPFL model, respectively. The DeLong test did not prove statistically significant differences between the two models (p-value = 0.98). The AUC values for the inference attacks fluctuate between 0.49 and 0.51, with an average of 0.50 ± 0.003 and 95% CI for the mean AUC of 0.500 to 0.501., Conclusion: The performance of the proposed model was comparable to centralized models while operating on large and heterogeneous multi-institutional datasets. In addition, the model was resistant to inference attacks, ensuring the privacy of shared data during the training process., (© 2024 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

This study evaluates the reproducibility of machine learning models that integrate radiomics and deep features (features extracted from a 3D autoencoder neural network) to classify various brain hemorrhages effectively. Using a dataset of 720 patients, we extracted 215 radiomics features (RFs) and 15,680 deep features (DFs) from CT brain images. With rigorous screening based on Intraclass Correlation Coefficient thresholds (>0.75), we identified 135 RFs and 1054 DFs for analysis. Feature selection techniques such as Boruta, Recursive Feature Elimination (RFE), XGBoost, and ExtraTreesClassifier were utilized alongside 11 classifiers, including AdaBoost, CatBoost, Decision Trees, LightGBM, Logistic Regression, Naive Bayes, Neural Networks, Random Forest, Support Vector Machines (SVM), and k-Nearest Neighbors (k-NN). Evaluation metrics included Area Under the Curve (AUC), Accuracy (ACC), Sensitivity (SEN), and F1-score. The model evaluation involved hyperparameter optimization, a 70:30 train-test split, and bootstrapping, further validated with the Wilcoxon signed-rank test and q-values. Notably, DFs showed higher accuracy. In the case of RFs, the Boruta + SVM combination emerged as the optimal model for AUC, ACC, and SEN, while XGBoost + Random Forest excelled in F1-score. Specifically, RFs achieved AUC, ACC, SEN, and F1-scores of 0.89, 0.85, 0.82, and 0.80, respectively. Among DFs, the ExtraTreesClassifier + Naive Bayes combination demonstrated remarkable performance, attaining an AUC of 0.96, ACC of 0.93, SEN of 0.92, and an F1-score of 0.92. Distinguished models in the RF category included SVM with Boruta, Logistic Regression with XGBoost, SVM with ExtraTreesClassifier, CatBoost with XGBoost, and Random Forest with XGBoost, each yielding significant q-values of 42. In the DFs realm, ExtraTreesClassifier + Naive Bayes, ExtraTreesClassifier + Random Forest, and Boruta + k-NN exhibited robustness, with 43, 43, and 41 significant q-values, respectively. This investigation underscores the potential of synergizing DFs with machine learning models to serve as valuable screening tools, thereby enhancing the interpretation of head CT scans for patients with brain hemorrhages.

Purpose: Our study investigated the association between dental caries, periodontal diseases, and tooth loss with diabetes mellitus (DM) among the elderly population, representing the first study of its kind in Iran., Methods: This was a cross-sectional community-based study as a part of the second wave of the Birjand longitudinal aging study (BLAS, 2021-2022) for people older than 60. We used the Comprehensive Geriatric Oral Health Assessment Tool (CGOHAT) for the oral health evaluation. Participants were initially categorized into diabetic and non-diabetic groups. Those patients with DM were further categorised into uncontrolled and controlled diabetes based on their HbA1c level. The association between periodontitis, gingivitis, and edentulism with type II diabetes mellitus and uncontrolled diabetes was assessed using logistic regression., Results: Among the 1,011 participants, 324 (32.04%) had DM. The mean ± SD DMFT was 27.06 ± 7.71 and 27.07 ± 7.72 among those with and without DM, respectively ( p  =  0.976 ). The M index comprised 85.46% of the total DMFT among those without DM and 84.51% among those with DM. The prevalence of periodontitis was higher among those without DM (110, 32.84%, p  =  0.390 ). The prevalence of gingivitis was higher among those with DM (73, 45.06%, p  =  0.617 ). Among the diabetic group, 137 (42.28%) had controlled DM. Based on the adjusted matched multivariate logistic model, decayed teeth (1.24, 95%CI: 1.06 - 1.46, p-value  =  0.006 ), periodontitis (2.78, 95%CI: 1.02 - 7.56, p-value  =  0.044 ), and moderate tooth loss (5.73, 95%CI: 1.13 - 28.88, p-value  =  0.034 ) were significantly associated with increased odds of uncontrolled DM., Conclusions: Based on the findings of this study, tooth loss was highly prevalent among the elderly Iranians regardless of their diabetes status. Also, periodontitis, tooth loss, and decayed teeth were significantly associated with increased odds of poor glycemic control among those with DM. Thus, it can be concluded that improving the oral health of the geriatric population may be a crucial part of improving the glycemic control among those with diabetes which has been frequently neglected., Supplementary Information: The online version contains supplementary material available at 10.1007/s40200-024-01434-2., Competing Interests: Conflict of interestThe authors declare that they have no conflict of interest., (© The Author(s), under exclusive licence to Tehran University of Medical Sciences 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.)

Background: There is some concern that root resection may alter the surface features and crack formation of the previously set orthograde material. The aim of this in vitro study was to evaluate the crack formation in orthograde mineral trioxide aggregate (MTA) and calcium-enriched mixture (CEM) plugs after root resection., Materials and Methods: This in vitro study was conducted on 170 extracted human maxillary anterior teeth. The teeth were randomly divided three experimental ( n = 50) and control ( n = 20) groups. In Group 1, after root canal treatment, half of the roots were cut with a bur, and the other half with an ultrasonic cutter. In Groups 2 and 3, after the 4-mm CEM and MTA plugs were placed and set, the root ends of half of the samples were cut with a bur and the other half by an ultrasonic cutter. The prevalence of cracks in the dentin and orthograde apical plugs of MTA and CEM was then assessed by scanning electron microscopy. Data were analyzed using the McNemar's, Chi-square, and Fisher's exact tests at P ≤ 0.05 level of significance., Results: In general, the prevalence of crack in dentin in Groups 2 and 3 was significantly higher than in the plug ( P < 0.05). There was no significant difference in the prevalence of dentin crack in the studied groups ( P > 0.05). The prevalence of crack in dentin was lower when the bur was used to cut off the end of the root, although the difference was not significant. The prevalence of crack in the plug was similar in CEM and MTA., Conclusion: Based on the results of this study, the prevalence of crack in dentin is always significantly higher than its prevalence in the plug, and the prevalence of crack in the plug was similar in CEM and MTA; then, when there is an orthograde access to the root canal and surgery is likely in future, MTA and CEM can be placed in an orthograde technique and it just resects the root during surgery., Competing Interests: The authors of this manuscript declare that they have no conflicts of interest, real or perceived, financial or nonfinancial in this article., (Copyright: © 2022 Dental Research Journal.)

Exosomes (EXOs) are natural nanoparticles of endosome origin that are secreted by a variety of cells in the body. Exosomes have been found in bio-fluids such as urine, saliva, amniotic fluid, and ascites, among others. Milk is the only commercially available biological liquid containing EXOs. Proof that exosomes are essential for cell-to-cell communication is increasingly being reported. Studies have shown that they migrate from the cell of origin to various bioactive substances, including membrane receptors, proteins, mRNAs, microRNAs, and organelles, or they can stimulate target cells directly through interactions with receptors. Because of the presence of specific proteins, lipids, and RNAs, exosomes act in physiological and pathological conditions in vivo . Other salient features of EXOs include their long half-life in the body, no tumorigenesis, low immune response, good biocompatibility, ability to target cells through their surface biomarkers, and capacity to carry macromolecules. EXOs have been introduced to the scientific community as important, efficient, and attractive nanoparticles. They can be extracted from different sources and have the same characteristics as their parents. EXOs present in milk can be separated by size exclusion chromatography, density gradient centrifugation, or (ultra) centrifugation; however, the complex composition of milk that includes casein micelles and milk fat globules makes it necessary to take additional issues into consideration when employing the mentioned techniques with milk. As a rich source of EXOs, milk has unique properties that, in addition to its role as a carrier, promotes its use in treating diseases such as digestive problems, skin ulcers, and cancer, Moreover, EXOs derived from camel milk are reported to reduce the risk of oxidative stress and cancer. Milk-derived exosomes (MDEs) from yak milk improves gastrointestinal tract (GIT) development under hypoxic conditions. Furthermore, yak-MDEs have been suggested to be the best treatment for intestinal epithelial cells (IEC-6 cell line). Because of their availability as well as the non-invasiveness and cost-effectiveness of their preparation, isolates from mammals milk can be excellent resources for studies related to EXOs. These features also make it possible to exploit MDEs in clinical trials. The current study aimed to investigate the therapeutic applications of EXOs isolated from various milk sources., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Rashidi, Bijari, Khazaei, Shojaei-Ghahrizjani and Rezakhani.)

Due to different treatment strategies, it is extremely important to differentiate between glioblastoma multiforme (GBM) and brain metastases (MET). It often proves difficult to distinguish between GBM and MET using MRI due to their similar appearance on the imaging modalities. Surgical methods are still necessary for definitive diagnosis, despite the importance of magnetic resonance imaging in detecting, characterizing, and monitoring brain tumors. We introduced an accurate, convenient, and user-friendly method to differentiate between GBM and MET through routine MRI sequence and radiomics analyses. We collected 91 patients from one institution, including 50 with GBM and 41 with MET, which were proven pathologically. The tumors separately were segmented on all MRI images (T1-weighted imaging (T1WI), contrast-enhanced T1-weighted imaging (T1C), T2-weighted imaging (T2WI), and fluid-attenuated inversion recovery (FLAIR)) to form the volume of interest (VOI). Eight ML models and feature reduction strategies were evaluated using routine MRI sequences (T1W, T2W, T1-CE, and FLAIR) in two methods with (second model) and without wavelet transform (first model) radiomics. The optimal model was selected based on each model's accuracy, AUC-roc, and F1-score values. In this study, we have achieved the result of 0.98, 0.99, and 0.98 percent for accuracy, AUC-roc, and F1-score, respectively, which have yielded a better result than the first model. In most investigated models, there were significant improvements in the multidimensional wavelets model compared to the non-multidimensional wavelets model. Multidimensional discrete wavelet transform can analyze hidden features of the MRI from a different perspective and generate accurate features which are highly correlated with the model accuracy., Competing Interests: The authors declare that they have no competing interests., (Copyright © 2022 Salar Bijari et al.)

Background: We aimed to analyze the prognostic power of CT-based radiomics models using data of 14,339 COVID-19 patients., Methods: Whole lung segmentations were performed automatically using a deep learning-based model to extract 107 intensity and texture radiomics features. We used four feature selection algorithms and seven classifiers. We evaluated the models using ten different splitting and cross-validation strategies, including non-harmonized and ComBat-harmonized datasets. The sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were reported., Results: In the test dataset (4,301) consisting of CT and/or RT-PCR positive cases, AUC, sensitivity, and specificity of 0.83 ± 0.01 (CI95%: 0.81-0.85), 0.81, and 0.72, respectively, were obtained by ANOVA feature selector + Random Forest (RF) classifier. Similar results were achieved in RT-PCR-only positive test sets (3,644). In ComBat harmonized dataset, Relief feature selector + RF classifier resulted in the highest performance of AUC, reaching 0.83 ± 0.01 (CI95%: 0.81-0.85), with a sensitivity and specificity of 0.77 and 0.74, respectively. ComBat harmonization did not depict statistically significant improvement compared to a non-harmonized dataset. In leave-one-center-out, the combination of ANOVA feature selector and RF classifier resulted in the highest performance., Conclusion: Lung CT radiomics features can be used for robust prognostic modeling of COVID-19. The predictive power of the proposed CT radiomics model is more reliable when using a large multicentric heterogeneous dataset, and may be used prospectively in clinical setting to manage COVID-19 patients., (Copyright © 2022 The Authors. Published by Elsevier Ltd.. All rights reserved.)

This equivalence, randomized, clinical trial aimed to compare the postoperative pain of root canal therapy (RCT) with pulpotomy with mineral trioxide aggregate (PMTA) or calcium-enriched mixture (PCEM) in permanent mature teeth. In seven academic centers, 550 cariously exposed pulps were included and randomly allocated into PMTA ( n  = 188), PCEM ( n  = 194), or RCT ( n  = 168) arms. Preoperative "Pain Intensity" (PI) on Numerical Rating Scale and postoperative PIs until day 7 were recorded. Patients' demographic and pre-/intra-/postoperative factors/conditions were recorded/analysed. The arms were homogeneous in terms of demographics. The mean preoperative PIs were similar ( P =0.998), the mean sum PIs recorded during 10 postoperative intervals were comparable ( P =0.939), and the trend/changes in pain relief were parallel ( P =0.821) in all study arms. The incidences of preoperative moderate-severe pain in RCT, PMTA, and PCEM arms were 56.5%, 55.7%, and 56.7%, which after 24 hours considerably decreased to 13.1%, 10.6%, and 12.9%, respectively ( P =0.578). The time span of endodontic procedures was statistically different; RCT = 69.73, PMTA = 35.37, and PCEM = 33.62 minutes ( P < 0.001). Patients with greater preoperative pain, symptomatic apical periodontitis, or presence of PDL widening suffered more pain ( P =0.002, 0.035, and 0.023, resp.); however, other pre-/intra-/postoperative factors/conditions were comparable. Pulpotomy with MTA/CEM and RCT demonstrate comparable and effective postoperative pain relief., Competing Interests: Saeed Asgary is the inventor of CEM cement (Endodontic Filling Material, USA, 7,942,961, 17 May, 2011). All other authors declare that there are no conflicts of interest regarding the publication of this paper., (Copyright © 2020 Mohammad Jafar Eghbal et al.)

Introduction: This study is aimed at evaluating root canal transportation in the mesiobuccal canal of mandibular first molars prepared with One Shape, Reciproc, and M-One nickel titanium (NiTi) single-file rotary systems using cone beam computed tomography (CBCT)., Materials and Methods: In this ex vivo study, CBCT scans of 45 extracted human mandibular first molars with 20-40° curvature were obtained. The teeth were randomly divided into three groups ( n =15) for preparation of the mesiobuccal canal with One Shape, Reciproc, and M-One rotary systems according to the manufacturers' instructions. CBCT scans were obtained again after canal preparation. Changes caused by preparation in the coronal, middle, and apical thirds were determined on CBCT scans and analyzed using the Kruskal-Wallis test at P ≤ 0.05 level of significance., Results: No significant difference was noted in the amount of canal transportation among the three groups ( P > 0.05). M-One caused greater transportation in the apical third compared with Reciproc and One Shape, and One Shape caused greater transportation in the coronal third compared with other groups, although its magnitude was less than 0.3 mm., Conclusion: Reciproc, One Shape, and M-One are not significantly different in terms of canal transportation.